feat(crm): add FluentCRM MCP integration for sales and marketing#64
feat(crm): add FluentCRM MCP integration for sales and marketing#64marcusquinn merged 9 commits intomainfrom
Conversation
- Add services/crm/fluentcrm.md with comprehensive FluentCRM MCP documentation - Enhance sales.md with CRM integration, pipeline management, and lead workflows - Enhance marketing.md with email campaigns, automation, and segmentation - Add FluentCRM to mcp-integrations.md with setup instructions - Update AGENTS.md with CRM services folder reference FluentCRM MCP provides: - Contact management (CRUD, search, segmentation) - Tag and list management for audience organization - Email campaign creation and management - Marketing automation (funnels) setup - Smart links for trackable URLs - Webhook configuration - Dashboard stats and custom fields
|
Warning Rate limit exceeded@marcusquinn has exceeded the limit for the number of commits that can be reviewed per hour. Please wait 16 minutes and 15 seconds before requesting another review. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. 📒 Files selected for processing (4)
WalkthroughAdds FluentCRM MCP integration and documentation: updates Marketing and Sales agents to reference FluentCRM, introduces a new Changes
Sequence Diagram(s)sequenceDiagram
participant Agent as Marketing/Sales Agent
participant MCP as FluentCRM MCP (OpenCode wrapper)
participant FluentCRM as FluentCRM API (WordPress)
participant WP as WordPress Site/DB
Agent->>MCP: call tool (e.g., create_campaign, list_contacts)
MCP->>FluentCRM: translate to REST/API request
FluentCRM->>WP: read/write contacts, campaigns, automations
WP-->>FluentCRM: return data/status
FluentCRM-->>MCP: return API response
MCP-->>Agent: return structured result/status
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Summary of ChangesHello @marcusquinn, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request significantly expands the system's capabilities by integrating FluentCRM, a powerful WordPress-based CRM, into the existing sales and marketing agents. The changes provide a robust framework for managing customer relationships, automating marketing campaigns, and streamlining sales pipelines directly within the agent ecosystem. This integration aims to centralize CRM operations, improve lead nurturing, and enhance overall business process efficiency. Highlights
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Mon Jan 12 14:37:35 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces a comprehensive integration for FluentCRM, enhancing the sales and marketing agents with CRM capabilities. A new detailed documentation file for the FluentCRM MCP is added, and existing agent files are updated to reflect the new tools and workflows. The changes are well-structured and thorough. I've provided a few comments on the new documentation to improve clarity and consistency, particularly regarding configuration examples and tool usage syntax.
| { | ||
| "fluentcrm": { | ||
| "type": "local", | ||
| "command": ["/bin/bash", "-c", "source ~/.config/aidevops/mcp-env.sh && npx @netflyapp/fluentcrm-mcp-server"], | ||
| "enabled": true | ||
| } | ||
| } |
There was a problem hiding this comment.
The JSON configuration for OpenCode provided here is inconsistent with the one in the detailed documentation (.agent/services/crm/fluentcrm.md). This snippet is missing the parent mcpServers object, which could lead to incorrect configuration. To ensure consistency and prevent user error, the example should reflect the full structure needed in the opencode.json file.
| { | |
| "fluentcrm": { | |
| "type": "local", | |
| "command": ["/bin/bash", "-c", "source ~/.config/aidevops/mcp-env.sh && npx @netflyapp/fluentcrm-mcp-server"], | |
| "enabled": true | |
| } | |
| } | |
| { | |
| "mcpServers": { | |
| "fluentcrm": { | |
| "type": "local", | |
| "command": ["/bin/bash", "-c", "source ~/.config/aidevops/mcp-env.sh && npx @netflyapp/fluentcrm-mcp-server"], | |
| "enabled": true | |
| } | |
| } | |
| } |
| ```text | ||
| fluentcrm_create_email_template with: | ||
| - title: "Welcome Email Template" | ||
| - subject: "Welcome to {{company_name}}, {{contact.first_name}}!" |
There was a problem hiding this comment.
The example for fluentcrm_create_email_template uses a {{company_name}} variable in the subject line. This is not a standard FluentCRM personalization tag, and its origin is not explained. This could be confusing for users. If this is a placeholder, it should be made more explicit.
| - subject: "Welcome to {{company_name}}, {{contact.first_name}}!" | |
| - subject: "Welcome to [Your Company Name], {{contact.first_name}}!" |
| - title: "Product Demo CTA" | ||
| - slug: "demo-cta" | ||
| - target_url: "https://your-site.com/demo" | ||
| - apply_tags: [tag_id for 'clicked-demo-cta'] |
There was a problem hiding this comment.
The example for fluentcrm_create_smart_link uses Python-like list comprehension syntax ([tag_id for 'clicked-demo-cta']) for the apply_tags parameter. This is confusing in a documentation context. It would be clearer to use a placeholder that indicates a tag ID is expected.
| - apply_tags: [tag_id for 'clicked-demo-cta'] | |
| - apply_tags: ['<tag_id_for_clicked_demo_cta>'] |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In @.agent/sales.md:
- Around line 320-322: Update the internal documentation link text in
.agent/sales.md: replace the reference "services/crm/fluentcrm.md" with the
correct path ".agent/services/crm/fluentcrm.md" so the troubleshooting link
points to the existing file; ensure the link formatting and surrounding list
item remain unchanged.
🧹 Nitpick comments (2)
.agent/sales.md (1)
64-69: Consider adding security guidance for credential management.While the example uses placeholder values, it would be helpful to include a brief security reminder about:
- Never committing actual credentials to version control
- Using secure methods to source environment variables (e.g., from a
.gitignore'd file or secret manager)- Rotating application passwords regularly
📝 Suggested addition
**Environment Setup**: +> **Security Note**: Never commit actual credentials to version control. Store environment variables in a `.gitignore`'d file or use a secret manager. Rotate application passwords regularly. + ```bash # Add to ~/.config/aidevops/mcp-env.sh export FLUENTCRM_API_URL="https://your-domain.com/wp-json/fluent-crm/v2" export FLUENTCRM_API_USERNAME="your_username" export FLUENTCRM_API_PASSWORD="your_application_password"</details> </blockquote></details> <details> <summary>.agent/marketing.md (1)</summary><blockquote> `68-73`: **Consider adding security guidance for credential management.** Similar to the sales documentation, it would be helpful to include a security reminder about credential handling best practices. <details> <summary>📝 Suggested addition</summary> ```diff **Environment Setup**: +> **Security Note**: Never commit actual credentials to version control. Store environment variables in a `.gitignore`'d file or use a secret manager. Rotate application passwords regularly. + ```bash # Add to ~/.config/aidevops/mcp-env.sh export FLUENTCRM_API_URL="https://your-domain.com/wp-json/fluent-crm/v2" export FLUENTCRM_API_USERNAME="your_username" export FLUENTCRM_API_PASSWORD="your_application_password"</details> </blockquote></details> </blockquote></details> <details> <summary>📜 Review details</summary> **Configuration used**: Path: .coderabbit.yaml **Review profile**: CHILL **Plan**: Pro <details> <summary>📥 Commits</summary> Reviewing files that changed from the base of the PR and between 87df9870740dd9e193df84fe88e3ff2e9ed874ed and 83259a026f01678279401bb540e21eca8ad1cb32. </details> <details> <summary>📒 Files selected for processing (5)</summary> * `.agent/AGENTS.md` * `.agent/aidevops/mcp-integrations.md` * `.agent/marketing.md` * `.agent/sales.md` * `.agent/services/crm/fluentcrm.md` </details> <details> <summary>🧰 Additional context used</summary> <details> <summary>🧠 Learnings (8)</summary> <details> <summary>📓 Common learnings</summary>Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-11-29T04:34:27.158Z
Learning: All instructions, documentation, and operational guidance should be maintained in AGENTS.md as the single source of truthLearnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: GEMINI.md:0-0
Timestamp: 2025-11-29T04:34:30.742Z
Learning: Maintain all instructions, documentation, and operational guidance in AGENTS.md as the single source of truth</details> <details> <summary>📚 Learning: 2025-11-29T04:34:42.033Z</summary>Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENT.md:0-0
Timestamp: 2025-11-29T04:34:42.033Z
Learning: Reference AGENTS.md (authoritative) instead of AGENT.md for AI assistant guidance**Applied to files:** - `.agent/AGENTS.md` </details> <details> <summary>📚 Learning: 2025-11-29T04:34:27.158Z</summary>Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-11-29T04:34:27.158Z
Learning: All instructions, documentation, and operational guidance should be maintained in AGENTS.md as the single source of truth**Applied to files:** - `.agent/AGENTS.md` </details> <details> <summary>📚 Learning: 2026-01-06T15:57:56.008Z</summary>Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-01-06T15:57:56.008Z
Learning: Applies to **/AGENTS.md : Use progressive disclosure in AGENTS.md with pointers to subagents rather than inline content**Applied to files:** - `.agent/AGENTS.md` </details> <details> <summary>📚 Learning: 2025-11-29T04:34:30.742Z</summary>Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: GEMINI.md:0-0
Timestamp: 2025-11-29T04:34:30.742Z
Learning: Reference AGENTS.md for authoritative AI assistant guidance instead of GEMINI.md**Applied to files:** - `.agent/AGENTS.md` </details> <details> <summary>📚 Learning: 2025-11-29T04:34:30.742Z</summary>Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: GEMINI.md:0-0
Timestamp: 2025-11-29T04:34:30.742Z
Learning: Maintain all instructions, documentation, and operational guidance in AGENTS.md as the single source of truth**Applied to files:** - `.agent/AGENTS.md` </details> <details> <summary>📚 Learning: 2026-01-06T15:57:56.008Z</summary>Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-01-06T15:57:56.008Z
Learning: Applies to **/AGENTS.md : Limit root AGENTS.md to ~50-100 max instructions with universal applicability to >80% of tasks**Applied to files:** - `.agent/AGENTS.md` </details> <details> <summary>📚 Learning: 2025-11-29T04:34:42.033Z</summary>Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENT.md:0-0
Timestamp: 2025-11-29T04:34:42.033Z
Learning: Maintain all AI assistant instructions, documentation, and operational guidance in AGENTS.md as the single source of truth**Applied to files:** - `.agent/AGENTS.md` </details> </details><details> <summary>🪛 Gitleaks (8.30.0)</summary> <details> <summary>.agent/services/crm/fluentcrm.md</summary> [high] 414-414: Discovered a potential basic authorization token provided in a curl command, which could compromise the curl accessed resource. (curl-auth-user) </details> </details> <details> <summary>🪛 LanguageTool</summary> <details> <summary>.agent/services/crm/fluentcrm.md</summary> [style] ~267-~267: Three successive sentences begin with the same word. Consider rewording the sentence or use a thesaurus to find a synonym. Context: ...can apply tags/lists when clicked. ### Smart Link Operations ```text # Create smart... (ENGLISH_WORD_REPEAT_BEGINNING_RULE) </details> </details> </details> <details> <summary>⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)</summary> * GitHub Check: Codacy Static Code Analysis </details> <details> <summary>🔇 Additional comments (10)</summary><blockquote> <details> <summary>.agent/services/crm/fluentcrm.md (5)</summary><blockquote> `1-48`: **LGTM! Excellent documentation structure and AI-CONTEXT markers.** The frontmatter configuration is appropriate for a CRM subagent, and the AI-CONTEXT section provides a clean quick reference with all essential information (environment variables, MCP tools table, and authentication details). This follows best practices for progressive disclosure. --- `66-78`: **Well-structured OpenCode configuration using bash wrapper pattern.** The bash wrapper pattern correctly sources the environment file before executing the MCP server, consistent with the Ahrefs MCP approach. This ensures environment variables are available without hardcoding credentials. --- `285-285`: **Good version compatibility note for Smart Links API.** The caveat about Smart Links API availability in different FluentCRM versions is helpful and prevents user confusion when the API returns 404. --- `380-407`: **Comprehensive best practices section covering critical aspects.** The best practices appropriately cover data quality, email deliverability, automation design, and GDPR compliance. These are essential for CRM operations and marketing automation. --- `413-416`: **Troubleshooting curl example is appropriate (Gitleaks false positive).** The static analysis tool flagged this as a potential credential exposure, but this is a documentation example showing users how to verify their credentials. This is expected and necessary in troubleshooting documentation. Based on static analysis hints: The Gitleaks warning here is a false positive—this is a legitimate troubleshooting example, not actual credential leakage. </blockquote></details> <details> <summary>.agent/AGENTS.md (2)</summary><blockquote> `360-361`: **LGTM! Marketing and sales agent descriptions appropriately reference FluentCRM.** The updates concisely indicate the new CRM integration capabilities without bloating the main agents table. This follows the progressive disclosure pattern from learnings. Based on learnings: These updates use concise pointers rather than inline content, maintaining AGENTS.md's role as a navigational hub. --- `399-399`: **Well-structured CRM subagent folder entry.** The new services/crm/ folder entry follows the established pattern with a clear description and associated tool reference. This maintains consistency with other subagent folder entries. Based on learnings: Progressive disclosure is maintained—detailed CRM documentation lives in services/crm/fluentcrm.md, not inline in AGENTS.md. </blockquote></details> <details> <summary>.agent/aidevops/mcp-integrations.md (2)</summary><blockquote> `61-64`: **LGTM! New CRM & Marketing category appropriately placed.** The FluentCRM MCP integration is logically categorized and follows the same structure as other MCP integration categories in this file. --- `137-164`: **Well-structured FluentCRM MCP setup following established patterns.** The setup instructions correctly: - Store credentials in `~/.config/aidevops/mcp-env.sh` - Use bash wrapper pattern for OpenCode (consistent with Ahrefs MCP) - List available tools for quick reference - Cross-reference detailed documentation in `services/crm/fluentcrm.md` This maintains consistency with other MCP integrations in this file. </blockquote></details> <details> <summary>.agent/marketing.md (1)</summary><blockquote> `436-438`: External documentation links in the troubleshooting section are accessible and current. </blockquote></details> </blockquote></details> </details> <!-- This is an auto-generated comment by CodeRabbit for review status -->
🤖 Augment PR SummarySummary: Adds FluentCRM MCP integration docs so the sales/marketing agents can operate a WordPress-hosted CRM (contacts, campaigns, automations) via MCP. Changes:
Technical Notes: Assumes WordPress application-password Basic Auth against 🤖 Was this summary useful? React with 👍 or 👎 |
![augmentcode[bot]](https://avatars.githubusercontent.com/in/1027498?s=60&v=4){kind=small}
|
|
||
| ```text | ||
| 1. fluentcrm_create_contact with lead details | ||
| 2. fluentcrm_attach_tag_to_contact with ['lead-new', 'source-website'] |
There was a problem hiding this comment.
fluentcrm_attach_tag_to_contact is described earlier as taking a tagIds array, but this example passes tag slugs (e.g. 'lead-new'), which may fail if the MCP expects numeric IDs. Consider clarifying whether these examples are IDs vs slugs (also applies to .agent/sales.md:81 and .agent/sales.md:217).
Other Locations
.agent/sales.md:81.agent/sales.md:217
🤖 Was this useful? React with 👍 or 👎
- Add security notes for credential management in sales.md and marketing.md - Fix internal documentation links to use correct .agent/ prefix - Clarify mcp-env.sh permissions (600) for secure storage
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Mon Jan 12 15:18:13 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
Address Augment review feedback - make clear that fluentcrm_attach_tag_to_contact and similar tools expect numeric tag/list IDs, not string slugs.
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Mon Jan 12 15:22:52 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Fix all issues with AI agents
In @.agent/sales.md:
- Line 231: Update the internal doc reference that currently reads "See
`services/accounting/quickfile.md`" to include the `.agent/` prefix so it
becomes "See `.agent/services/accounting/quickfile.md`", matching other
references in this file and preventing broken cross-links.
🧹 Nitpick comments (1)
.agent/sales.md (1)
62-71: Good security guidance with clear environment setup.The security note properly emphasizes credential protection, file permissions, and rotation. The environment variable setup is clear and actionable.
📝 Optional: Add explicit file permission setup
Consider adding an explicit command to set file permissions for users who may be unfamiliar:
```bash # Add to ~/.config/aidevops/mcp-env.sh +# Ensure file has restrictive permissions: +# chmod 600 ~/.config/aidevops/mcp-env.sh + export FLUENTCRM_API_URL="https://your-domain.com/wp-json/fluent-crm/v2" export FLUENTCRM_API_USERNAME="your_username" export FLUENTCRM_API_PASSWORD="your_application_password"</details> </blockquote></details> </blockquote></details> <details> <summary>📜 Review details</summary> **Configuration used**: Path: .coderabbit.yaml **Review profile**: CHILL **Plan**: Pro <details> <summary>📥 Commits</summary> Reviewing files that changed from the base of the PR and between 83259a026f01678279401bb540e21eca8ad1cb32 and fbfd4455be929248c2587bb77dc1007cc95a28c1. </details> <details> <summary>📒 Files selected for processing (2)</summary> * `.agent/marketing.md` * `.agent/sales.md` </details> <details> <summary>🧰 Additional context used</summary> <details> <summary>🧠 Learnings (8)</summary> <details> <summary>📚 Learning: 2025-11-29T04:34:42.033Z</summary>Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENT.md:0-0
Timestamp: 2025-11-29T04:34:42.033Z
Learning: Reference AGENTS.md (authoritative) instead of AGENT.md for AI assistant guidance**Applied to files:** - `.agent/sales.md` </details> <details> <summary>📚 Learning: 2026-01-06T15:57:56.008Z</summary>Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-01-06T15:57:56.008Z
Learning: Applies to **/AGENTS.md : Include code examples in AGENTS.md only when authoritative, otherwise use file:line references**Applied to files:** - `.agent/sales.md` </details> <details> <summary>📚 Learning: 2025-11-29T04:34:42.033Z</summary>Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENT.md:0-0
Timestamp: 2025-11-29T04:34:42.033Z
Learning: Maintain all AI assistant instructions, documentation, and operational guidance in AGENTS.md as the single source of truth**Applied to files:** - `.agent/sales.md` </details> <details> <summary>📚 Learning: 2025-11-29T04:34:30.742Z</summary>Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: GEMINI.md:0-0
Timestamp: 2025-11-29T04:34:30.742Z
Learning: Maintain all instructions, documentation, and operational guidance in AGENTS.md as the single source of truth**Applied to files:** - `.agent/sales.md` </details> <details> <summary>📚 Learning: 2025-11-29T04:34:27.158Z</summary>Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-11-29T04:34:27.158Z
Learning: All instructions, documentation, and operational guidance should be maintained in AGENTS.md as the single source of truth**Applied to files:** - `.agent/sales.md` </details> <details> <summary>📚 Learning: 2025-11-29T04:34:30.742Z</summary>Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: GEMINI.md:0-0
Timestamp: 2025-11-29T04:34:30.742Z
Learning: Reference AGENTS.md for authoritative AI assistant guidance instead of GEMINI.md**Applied to files:** - `.agent/sales.md` </details> <details> <summary>📚 Learning: 2026-01-06T15:57:56.008Z</summary>Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-01-06T15:57:56.008Z
Learning: Applies to **/AGENTS.md : Use progressive disclosure in AGENTS.md with pointers to subagents rather than inline content**Applied to files:** - `.agent/sales.md` </details> <details> <summary>📚 Learning: 2026-01-06T15:57:56.008Z</summary>Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-01-06T15:57:56.008Z
Learning: Applies to **/AGENTS.md : Limit root AGENTS.md to ~50-100 max instructions with universal applicability to >80% of tasks**Applied to files:** - `.agent/sales.md` </details> </details> </details> <details> <summary>⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)</summary> * GitHub Check: Codacy Static Code Analysis </details> <details> <summary>🔇 Additional comments (14)</summary><blockquote> <details> <summary>.agent/sales.md (6)</summary><blockquote> `5-12`: **LGTM! Appropriate tool declarations.** The tool set provides necessary capabilities for sales operations including file access, shell scripting, and web fetching for CRM integration. --- `75-112`: **Excellent lead management documentation.** The lead capture workflow, qualification stages, and scoring system are clearly documented with semantic tag naming and actionable steps. This provides strong guidance for sales operations. --- `113-168`: **Comprehensive pipeline and automation guidance.** The pipeline stage mapping, movement workflow, and sales automation triggers are well-structured and provide clear operational guidance. The tag-based stage tracking is a clean approach. --- `258-284`: **Well-designed marketing integration workflows.** The lead handoff and feedback loop between sales and marketing are clearly defined and align well with the corresponding workflows in `.agent/marketing.md`. The tag-based communication is clean and trackable. --- `286-324`: **Comprehensive best practices and troubleshooting guidance.** The operational best practices, troubleshooting table, and external help resources provide thorough support for sales operations. The documentation references use correct paths. --- `31-38`: **All FluentCRM tool names are correct—no runtime errors from documented tools.** Verification confirms that all 10 tools documented in the table (`fluentcrm_list_contacts`, `fluentcrm_create_contact`, `fluentcrm_find_contact_by_email`, `fluentcrm_update_contact`, `fluentcrm_attach_tag_to_contact`, `fluentcrm_detach_tag_from_contact`, `fluentcrm_attach_contact_to_list`, `fluentcrm_detach_contact_from_list`, `fluentcrm_dashboard_stats`, `fluentcrm_custom_fields`) match the official FluentCRM MCP server implementation exactly. The documentation is intentionally selective—covering key operations for sales workflows—rather than exhaustive. </blockquote></details> <details> <summary>.agent/marketing.md (8)</summary><blockquote> `5-12`: **LGTM! Appropriate tool declarations.** Consistent tool set with sales agent, providing necessary capabilities for marketing operations and CRM integration. --- `53-77`: **Consistent setup guidance with appropriate marketing-specific additions.** The FluentCRM setup section maintains consistency with sales documentation while appropriately adding email sending configuration as a prerequisite for marketing operations. Security guidance is properly emphasized. --- `79-152`: **Excellent campaign and template documentation.** The campaign types, creation workflow, and email template best practices provide comprehensive guidance aligned with email marketing standards. The template variable syntax examples are particularly helpful for implementation. --- `154-213`: **Well-designed marketing automation sequences.** The automation triggers and sequence examples demonstrate sound email marketing practices with appropriate timing and messaging progression. The acknowledgment that detailed configuration happens in FluentCRM admin is realistic and helpful. --- `215-284`: **Comprehensive segmentation and smart link tracking.** The audience segmentation strategies and smart link use cases provide thorough guidance for targeted marketing. Tag naming patterns are consistent with sales documentation, ensuring cross-team alignment. --- `286-336`: **Well-integrated content and lead generation workflows.** The content marketing integration and lead generation processes demonstrate strong cross-agent coordination. The lead handoff workflow (lines 330-336) properly aligns with the corresponding sales workflow in `.agent/sales.md` (lines 262-270), ensuring smooth marketing-to-sales transitions. --- `338-390`: **Solid analytics and A/B testing methodology.** The key metrics with industry-standard targets and the A/B testing process demonstrate sound email marketing practices. The testing methodology (10-20% test group, 24-48 hour wait) follows established best practices. --- `392-440`: **Comprehensive best practices with critical compliance coverage.** The deliverability, list hygiene, and compliance guidance provide essential operational and legal requirements for email marketing. The inclusion of GDPR, CAN-SPAM, and CASL requirements is particularly important for avoiding legal issues. </blockquote></details> </blockquote></details> </details> <!-- This is an auto-generated comment by CodeRabbit for review status -->
Address CodeRabbit review - consistent internal doc path formatting.
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (2)
.agent/sales.md (2)
236-259: Consider clarifying data requirements for advanced metrics.The reporting section defines useful sales metrics, but some calculations (Pipeline Value, Sales Velocity) require custom field data that isn't explicitly defined elsewhere in the documentation. Consider adding a brief note about which custom fields should be tracked to support these metrics, or reference where that's documented.
The dashboard stats approach using
fluentcrm_dashboard_statsis clean and straightforward.📊 Optional enhancement: Add custom field requirements
Consider adding a brief note before the Key Metrics table:
+**Note**: Advanced metrics like Pipeline Value and Sales Velocity require custom fields for opportunity value and stage dates. See `services/crm/fluentcrm.md` for custom field configuration. + ### Key Metrics
289-310: Solid best practices with room for compliance guidance.The best practices section covers essential CRM hygiene, pipeline management, and automation guidelines. The advice is specific and actionable, particularly:
- "Review stale opportunities weekly" - provides a concrete cadence
- "Don't over-automate personal touches" - important human element
- "Test automations before activating" - prevents costly mistakes
Consider adding a brief compliance/privacy subsection covering GDPR consent, CAN-SPAM requirements, and data retention policies, or reference where this is documented.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
.agent/sales.md
🧰 Additional context used
🧠 Learnings (7)
📚 Learning: 2025-11-29T04:34:42.033Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENT.md:0-0
Timestamp: 2025-11-29T04:34:42.033Z
Learning: Reference AGENTS.md (authoritative) instead of AGENT.md for AI assistant guidance
Applied to files:
.agent/sales.md
📚 Learning: 2026-01-06T15:57:56.008Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-01-06T15:57:56.008Z
Learning: Applies to **/AGENTS.md : Include code examples in AGENTS.md only when authoritative, otherwise use file:line references
Applied to files:
.agent/sales.md
📚 Learning: 2025-11-29T04:34:30.742Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: GEMINI.md:0-0
Timestamp: 2025-11-29T04:34:30.742Z
Learning: Maintain all instructions, documentation, and operational guidance in AGENTS.md as the single source of truth
Applied to files:
.agent/sales.md
📚 Learning: 2025-11-29T04:34:42.033Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENT.md:0-0
Timestamp: 2025-11-29T04:34:42.033Z
Learning: Maintain all AI assistant instructions, documentation, and operational guidance in AGENTS.md as the single source of truth
Applied to files:
.agent/sales.md
📚 Learning: 2025-11-29T04:34:27.158Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-11-29T04:34:27.158Z
Learning: All instructions, documentation, and operational guidance should be maintained in AGENTS.md as the single source of truth
Applied to files:
.agent/sales.md
📚 Learning: 2025-11-29T04:34:30.742Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: GEMINI.md:0-0
Timestamp: 2025-11-29T04:34:30.742Z
Learning: Reference AGENTS.md for authoritative AI assistant guidance instead of GEMINI.md
Applied to files:
.agent/sales.md
📚 Learning: 2026-01-06T15:57:56.008Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-01-06T15:57:56.008Z
Learning: Applies to **/AGENTS.md : Use progressive disclosure in AGENTS.md with pointers to subagents rather than inline content
Applied to files:
.agent/sales.md
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Codacy Static Code Analysis
🔇 Additional comments (10)
.agent/sales.md (10)
1-13: LGTM - Agent configuration is appropriate.The frontmatter correctly defines the sales subagent with comprehensive tool permissions necessary for CRM operations. The combination of read/write/bash permissions is appropriate given the documented security practices in the environment setup section.
50-73: Strong security guidance - well done.The environment setup section demonstrates excellent security practices:
- Explicit warning against committing credentials
- 600 file permissions for sensitive config
- Application password rotation reminder
- Delegation to dedicated service documentation for detailed setup
This aligns well with the zero technical debt philosophy mentioned in the framework.
75-114: Excellent lead management workflows with clear ID handling.The lead management section provides well-structured guidance:
- Clear step-by-step lead capture process
- Explicit reminder about numeric IDs vs. slugs (addressing the fix mentioned in commit messages)
- Logical qualification progression from unqualified to customer/lost
- Comprehensive engagement scoring triggers
The emphasis on using
fluentcrm_list_tagsto retrieve numeric IDs prevents a common integration pitfall.
116-147: Pipeline management workflows are clear and actionable.The pipeline stage mapping and transition workflows are well-documented:
- Six logical stages from Prospect to Closed Won/Lost
- Clear tag-based stage tracking
- Simple three-step stage transition process
- Reporting approach that leverages both contact queries and dashboard stats
The workflow correctly detaches the old stage before attaching the new one, maintaining clean stage tracking.
173-202: Clean and consistent segmentation strategy.The contact segmentation section uses a well-organized tag taxonomy:
- Consistent naming convention (category-value format)
- Practical segmentation dimensions (interest, company size, industry)
- Example tags that are self-documenting
This approach allows for flexible multi-dimensional segmentation while keeping the implementation simple through tag-based categorization.
261-287: Excellent cross-functional integration design.The marketing integration section demonstrates thoughtful workflow design:
- Clear MQL → SQL qualification handoff with automation
- Structured feedback loop using quality and rejection reason tags
- Tag-based communication that enables marketing optimization
This approach creates a data-driven feedback mechanism for continuous improvement of lead generation efforts.
312-327: Practical troubleshooting guidance with good resource links.The troubleshooting section addresses common integration issues with specific solutions:
- Verification steps for tag/contact issues
- Credential checking for API errors
- Mix of MCP tool solutions and admin UI checks
The Getting Help section follows the framework's progressive disclosure pattern by delegating detailed troubleshooting to the dedicated service documentation.
149-171: Automation patterns are well-designed.The sales automation section implements excellent patterns with proper exit conditions (replied, converted, unsubscribed) to respect user preferences. The sequence management workflow correctly uses
fluentcrm_create_automation, which is properly documented in the FluentCRM MCP Tools reference.
204-234: Implementation correctly references valid FluentCRM smart link tool and QuickFile integration.The proposal workflow design with cross-agent integration (CRM → Accounting) is sound. Smart link tracking (
fluentcrm_create_smart_link) and QuickFile conversion pipeline are properly documented and available. No action required.
31-38: All FluentCRM MCP tool names are accurate and verified.The quick reference tools table (lines 31-38) contains 10 tools that are all properly documented in
.agent/services/crm/fluentcrm.mdand used consistently throughout with practical examples. The tools referenced in narrative sections (fluentcrm_list_tags,fluentcrm_list_lists,fluentcrm_create_automation,fluentcrm_create_smart_link) are also documented in the detailed CRM guide. Documentation is internally consistent with proper naming conventions and parameter specifications (e.g., numeric IDs for tags/lists, subscriberId references), mitigating runtime invocation errors.
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Mon Jan 12 15:28:48 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Fix all issues with AI agents
In @.agent/sales.md:
- Around line 215-223: The Smart Link Tracking example is missing the required
slug parameter; update the fluentcrm_create_smart_link example to include a slug
entry (e.g., slug: "proposal-{company-slug}") alongside title, target_url, and
apply_tags so the tool call is valid; keep the note about Smart Links API
availability if desired.
- Around line 31-38: Update the FluentCRM MCP Tools reference table in
.agent/sales.md to include the missing categories and operations: add rows for
Campaigns (e.g., fluentcrm_list_campaigns, fluentcrm_create_campaign,
fluentcrm_get_campaign, fluentcrm_delete_campaign), Templates
(fluentcrm_list_templates, fluentcrm_create_template, fluentcrm_get_template,
fluentcrm_delete_template), Automations (fluentcrm_list_automations,
fluentcrm_create_automation, fluentcrm_get_automation,
fluentcrm_delete_automation), Webhooks (fluentcrm_list_webhooks,
fluentcrm_create_webhook, fluentcrm_get_webhook, fluentcrm_delete_webhook) and
Smart Links (fluentcrm_list_smart_links, fluentcrm_create_smart_link,
fluentcrm_get_smart_link, fluentcrm_delete_smart_link); also expand Contacts to
include fluentcrm_get_contact and fluentcrm_delete_contact and expand Tags/Lists
to include list/create/get/delete variants such as fluentcrm_list_tags,
fluentcrm_create_tag, fluentcrm_get_tag, fluentcrm_delete_tag and
fluentcrm_list_lists, fluentcrm_create_list, fluentcrm_get_list,
fluentcrm_delete_list so the table mirrors the implementations in
.agent/services/crm/fluentcrm.md.
🧹 Nitpick comments (3)
.agent/sales.md (3)
131-138: Consider tag transition atomicity for stage changes.The pipeline movement workflow detaches the old stage tag then attaches the new one. If these operations aren't atomic, a contact could temporarily be in no stage or an error could leave them partially transitioned.
If the FluentCRM API doesn't guarantee atomicity across these operations, consider documenting error handling or verification steps.
Potential enhancement to the workflow documentation:
Enhanced workflow with verification
# Move contact to next stage 1. fluentcrm_detach_tag_from_contact with current stage tag 2. fluentcrm_attach_tag_to_contact with new stage tag 3. Update custom fields with stage date +4. Verify both operations succeeded before proceeding
248-259: Clarify that "Returns:" describes expected data, not literal API output.The Dashboard Stats section lists what the tool returns, but this could be interpreted as the exact API response format. Consider adding a brief note that these are the types of metrics available, not the literal response structure.
Suggested clarification
# Get CRM dashboard stats fluentcrm_dashboard_stats -Returns: +Provides metrics including: - Total contacts - New contacts this period - Email engagement metrics - Campaign performance
1-327: Consider further progressive disclosure opportunities.The file appropriately delegates detailed setup and troubleshooting to
services/crm/fluentcrm.md, following the progressive disclosure pattern from learnings. However, at 327 lines, some detailed workflow sections (e.g., detailed tag taxonomies, automation configurations) could potentially be moved to the CRM service doc, keeping this file focused on sales-specific workflows.This is optional and doesn't block the PR - the current structure is well-organized and usable.
Based on learnings:
- "Use progressive disclosure in AGENTS.md with pointers to subagents rather than inline content"
- "Limit root AGENTS.md to ~50-100 max instructions with universal applicability"
While this is already a subagent (not root AGENTS.md), consider whether detailed sections like tag taxonomies (lines 95-114, 175-202) could be referenced from the CRM service doc rather than duplicated here.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
.agent/sales.md
🧰 Additional context used
🧠 Learnings (8)
📚 Learning: 2026-01-06T15:57:56.008Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-01-06T15:57:56.008Z
Learning: Applies to **/AGENTS.md : Limit root AGENTS.md to ~50-100 max instructions with universal applicability to >80% of tasks
Applied to files:
.agent/sales.md
📚 Learning: 2025-11-29T04:34:42.033Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENT.md:0-0
Timestamp: 2025-11-29T04:34:42.033Z
Learning: Reference AGENTS.md (authoritative) instead of AGENT.md for AI assistant guidance
Applied to files:
.agent/sales.md
📚 Learning: 2026-01-06T15:57:56.008Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-01-06T15:57:56.008Z
Learning: Applies to **/AGENTS.md : Include code examples in AGENTS.md only when authoritative, otherwise use file:line references
Applied to files:
.agent/sales.md
📚 Learning: 2025-11-29T04:34:30.742Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: GEMINI.md:0-0
Timestamp: 2025-11-29T04:34:30.742Z
Learning: Maintain all instructions, documentation, and operational guidance in AGENTS.md as the single source of truth
Applied to files:
.agent/sales.md
📚 Learning: 2025-11-29T04:34:42.033Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENT.md:0-0
Timestamp: 2025-11-29T04:34:42.033Z
Learning: Maintain all AI assistant instructions, documentation, and operational guidance in AGENTS.md as the single source of truth
Applied to files:
.agent/sales.md
📚 Learning: 2025-11-29T04:34:27.158Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-11-29T04:34:27.158Z
Learning: All instructions, documentation, and operational guidance should be maintained in AGENTS.md as the single source of truth
Applied to files:
.agent/sales.md
📚 Learning: 2025-11-29T04:34:30.742Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: GEMINI.md:0-0
Timestamp: 2025-11-29T04:34:30.742Z
Learning: Reference AGENTS.md for authoritative AI assistant guidance instead of GEMINI.md
Applied to files:
.agent/sales.md
📚 Learning: 2026-01-06T15:57:56.008Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-01-06T15:57:56.008Z
Learning: Applies to **/AGENTS.md : Use progressive disclosure in AGENTS.md with pointers to subagents rather than inline content
Applied to files:
.agent/sales.md
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Codacy Static Code Analysis
🔇 Additional comments (8)
.agent/sales.md (8)
5-12: LGTM: Appropriate tool permissions for CRM operations.The tool configuration appropriately grants read/write/edit access plus bash scripting and web fetch capabilities needed for FluentCRM MCP integration and sales workflows.
50-73: Excellent security practices for credential management.Strong security guidance:
- Explicit warning against committing credentials
- Proper file permissions (600) on config file
- Application password usage (WordPress best practice)
- Regular rotation recommended
- Clear separation pointing to detailed setup documentation
75-114: Well-documented lead workflows with critical API implementation note.The Lead Management section provides clear workflows and tag taxonomies. The note at line 89 about numeric IDs vs slugs is particularly valuable - this prevents a common integration mistake.
Tag naming conventions are consistent and semantic (hyphenated, lowercase, prefixed by category).
149-171: LGTM: Balanced automation guidance.The section appropriately combines MCP-based automation triggers with admin UI configuration for complex sequences. The inclusion of exit conditions (replied, converted, unsubscribed) shows mature automation thinking.
173-202: LGTM: Comprehensive segmentation taxonomy.The segmentation section provides three clear segmentation dimensions with consistent tag naming conventions. The semantic prefixes (interest-, company-size-, industry-) make the taxonomy self-documenting.
225-234: LGTM: Clear quote-to-invoice workflow with proper cross-reference.The workflow appropriately separates quote generation (sales) from invoice generation (accounting) with a clear reference to the QuickFile integration documentation.
261-287: LGTM: Well-designed sales-marketing integration workflows.The Lead Handoff and Feedback Loop sections establish clear bidirectional communication between sales and marketing teams, using tag-based signals for both lead progression and quality feedback.
312-327: External documentation links are valid and current.Both FluentCRM documentation URLs in the Getting Help section return HTTP 200 and are accessible:
The troubleshooting references are solid and ready for users.
- Add missing slug parameter to Smart Link example - Expand FluentCRM MCP Tools table with Campaigns, Smart Links categories - Add missing CRUD operations (get, delete) to Contacts, Tags, Lists
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Mon Jan 12 15:34:52 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
Follow aidevops best practice for MCP token optimization: - Set enabled: false in global OpenCode config - Add fluentcrm_*: true to sales.md and marketing.md tools section - Update documentation to reflect per-agent enablement pattern
Move fluentcrm_*: true from sales.md/marketing.md to services/crm/fluentcrm.md subagent. Main agents reference the subagent for CRM operations - follows progressive disclosure pattern.
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Mon Jan 12 15:53:13 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Mon Jan 12 15:53:58 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
Learning from FluentCRM integration feedback: - add-new-mcp-to-aidevops.md: Clarify MCP enablement is subagent-only with explicit correct/wrong examples - build-agent.md: Add CRITICAL MCP Placement Rule section emphasizing subagents only, never main agents - AGENTS.md: Add CRM/email marketing to 'When to read subagents' table - configs/mcp-templates/fluentcrm.json: Add config template with disabled default and comment explaining per-subagent enablement This prevents future confusion about where to enable MCP tools.
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Mon Jan 12 16:53:52 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
There was a problem hiding this comment.
Actionable comments posted: 3
🤖 Fix all issues with AI agents
In @.agent/sales.md:
- Line 29: The cross-reference in .agent/sales.md uses an inconsistent path
`services/crm/fluentcrm.md`; update that reference to the standardized
`.agent/services/crm/fluentcrm.md` to match the other occurrences (lines
referencing the same doc at lines 75, 237, 330), ensuring all internal links use
the `.agent/` prefix for consistency.
- Around line 31-40: The tools table is out of sync with the server: add the
missing categories Templates, Automations, and Webhooks and their tools
(Templates: fluentcrm_list_email_templates, fluentcrm_create_email_template;
Automations: fluentcrm_list_automations, fluentcrm_create_automation; Webhooks:
fluentcrm_list_webhooks, fluentcrm_create_webhook), and correct the Smart Links
row to list fluentcrm_list_smart_links, fluentcrm_create_smart_link,
fluentcrm_generate_smart_link_shortcode instead of fluentcrm_get_smart_link and
fluentcrm_delete_smart_link; update the table so it lists all 32 server-exposed
tools across the 9 categories to match the authoritative tool list.
In @configs/mcp-templates/fluentcrm.json:
- Around line 1-12: The npm package referenced in the fluentcrm template
("@netflyapp/fluentcrm-mcp-server" in the "command" array for "fluentcrm") does
not exist and will cause npx to fail; either update that command to the correct
published package name or change it to a documented placeholder (or a local
binary script) and add a clear comment indicating the package must be published
before enabling, or keep the service disabled until the package is released—make
the change in the "command" entry for "fluentcrm" and ensure the accompanying
"_comment" or README notes the chosen resolution.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (7)
.agent/AGENTS.md.agent/aidevops/add-new-mcp-to-aidevops.md.agent/aidevops/mcp-integrations.md.agent/sales.md.agent/services/crm/fluentcrm.md.agent/tools/build-agent/build-agent.mdconfigs/mcp-templates/fluentcrm.json
🚧 Files skipped from review as they are similar to previous changes (1)
- .agent/AGENTS.md
🧰 Additional context used
🧠 Learnings (8)
📚 Learning: 2026-01-06T15:57:56.008Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-01-06T15:57:56.008Z
Learning: Applies to **/AGENTS.md : Use progressive disclosure in AGENTS.md with pointers to subagents rather than inline content
Applied to files:
.agent/aidevops/add-new-mcp-to-aidevops.md.agent/sales.md.agent/tools/build-agent/build-agent.md
📚 Learning: 2025-11-29T04:34:42.033Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENT.md:0-0
Timestamp: 2025-11-29T04:34:42.033Z
Learning: Reference AGENTS.md (authoritative) instead of AGENT.md for AI assistant guidance
Applied to files:
.agent/sales.md.agent/tools/build-agent/build-agent.md
📚 Learning: 2025-11-29T04:34:30.742Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: GEMINI.md:0-0
Timestamp: 2025-11-29T04:34:30.742Z
Learning: Maintain all instructions, documentation, and operational guidance in AGENTS.md as the single source of truth
Applied to files:
.agent/sales.md.agent/tools/build-agent/build-agent.md
📚 Learning: 2025-11-29T04:34:27.158Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-11-29T04:34:27.158Z
Learning: All instructions, documentation, and operational guidance should be maintained in AGENTS.md as the single source of truth
Applied to files:
.agent/sales.md.agent/tools/build-agent/build-agent.md
📚 Learning: 2026-01-06T15:57:56.008Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-01-06T15:57:56.008Z
Learning: Applies to **/AGENTS.md : Limit root AGENTS.md to ~50-100 max instructions with universal applicability to >80% of tasks
Applied to files:
.agent/sales.md.agent/tools/build-agent/build-agent.md
📚 Learning: 2026-01-06T15:57:56.008Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-01-06T15:57:56.008Z
Learning: Applies to **/AGENTS.md : Include code examples in AGENTS.md only when authoritative, otherwise use file:line references
Applied to files:
.agent/sales.md
📚 Learning: 2025-11-29T04:34:42.033Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: AGENT.md:0-0
Timestamp: 2025-11-29T04:34:42.033Z
Learning: Maintain all AI assistant instructions, documentation, and operational guidance in AGENTS.md as the single source of truth
Applied to files:
.agent/sales.md
📚 Learning: 2025-11-29T04:34:30.742Z
Learnt from: CR
Repo: marcusquinn/aidevops PR: 0
File: GEMINI.md:0-0
Timestamp: 2025-11-29T04:34:30.742Z
Learning: Reference AGENTS.md for authoritative AI assistant guidance instead of GEMINI.md
Applied to files:
.agent/sales.md
🪛 Gitleaks (8.30.0)
.agent/services/crm/fluentcrm.md
[high] 417-417: Discovered a potential basic authorization token provided in a curl command, which could compromise the curl accessed resource.
(curl-auth-user)
🪛 LanguageTool
.agent/services/crm/fluentcrm.md
[style] ~270-~270: Three successive sentences begin with the same word. Consider rewording the sentence or use a thesaurus to find a synonym.
Context: ...can apply tags/lists when clicked. ### Smart Link Operations ```text # Create smart...
(ENGLISH_WORD_REPEAT_BEGINNING_RULE)
.agent/tools/build-agent/build-agent.md
[uncategorized] ~151-~151: The official name of this content management system is spelled with a capital “P”.
Context: ...in subdirectories like services/crm/, tools/wordpress/) - **NEVER enable MCPs in main agents...
(WORDPRESS)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Codacy Static Code Analysis
🔇 Additional comments (18)
.agent/services/crm/fluentcrm.md (5)
1-13: Excellent subagent frontmatter configuration.MCP enablement (
fluentcrm_*: true) is correctly placed in this subagent rather than in main agents likesales.mdormarketing.md. This follows the "disabled globally, enabled per-subagent" pattern for optimal token efficiency.The
write: falsepermission is appropriate since CRM operations route through the MCP server, not direct file writes.
27-48: Comprehensive quick reference with proper placeholder values.The environment variables use safe placeholders, and the MCP tools table provides excellent at-a-glance coverage of all available operations. This serves as a solid quick-start reference for developers.
415-419: False positive from Gitleaks - documentation example is safe.The static analysis flagged the curl
-u "username:app_password"syntax, but this is clearly a documentation example with placeholder values, not actual credentials. This is a standard pattern for showing basic auth syntax in troubleshooting guides.
381-409: Solid best practices with essential compliance guidance.The GDPR compliance section (lines 404-409) is particularly valuable for users operating in regulated markets. The email deliverability and automation design guidance will help prevent common CRM operational issues.
436-442: Good cross-referencing to related documentation.The links to
sales.md,marketing.md, and external FluentCRM documentation support the integrated workflow described in the PR objectives. This helps users navigate the broader CRM ecosystem..agent/aidevops/mcp-integrations.md (2)
61-64: Proper categorization under CRM & Marketing.Adding FluentCRM as a new category alongside existing Web & Browser, SEO & Research, and Development Tools sections maintains good organizational structure.
137-166: Consistent setup instructions following established patterns.The FluentCRM setup mirrors the Ahrefs MCP pattern (bash wrapper for environment variables, globally disabled, per-agent enablement). The explicit reference to
services/crm/fluentcrm.mdfor subagent enablement reinforces the correct MCP placement pattern..agent/tools/build-agent/build-agent.md (2)
149-165: Excellent enforcement of subagent-only MCP placement.The CORRECT vs WRONG YAML examples provide unambiguous guidance that will prevent misconfiguration. Using FluentCRM as the concrete example ties directly to this PR's integration work.
This pattern ensures MCPs only load when the specific subagent is invoked, optimizing token usage—a key concern per the retrieved learnings about instruction limits.
151-151: Static analysis false positive - directory paths use lowercase.The LanguageTool hint about "WordPress" capitalization doesn't apply here since
tools/wordpress/is a filesystem path, which conventionally uses lowercase. No change needed..agent/aidevops/add-new-mcp-to-aidevops.md (1)
45-61: Clear, actionable MCP enablement strategy.The updated guidance codifies the "disabled globally, enabled per-subagent" pattern with a concrete YAML example. The inline comment
# NO fluentcrm_* here - main agents don't enable MCPsis particularly helpful for developers who might otherwise copy-paste incorrectly.This aligns well with the progressive disclosure pattern from retrieved learnings—main agents reference subagents rather than carrying MCP configurations directly.
.agent/sales.md (8)
5-12: LGTM: Tools configuration is appropriate.The tool permissions (read, write, edit, bash, glob, grep, webfetch) align well with a sales agent that needs to interact with CRM systems, generate reports, and manage contacts.
66-73: Security guidance looks solid.The security note correctly emphasizes:
- Not committing credentials to version control
- Storing in
~/.config/aidevops/mcp-env.shwith 600 permissions- Rotating application passwords regularly
The example uses placeholder values and follows good practice.
83-91: Excellent clarity on the numeric ID requirement.The lead capture workflow correctly emphasizes that FluentCRM MCP uses numeric IDs for tags and lists (not slugs), and instructs users to call
fluentcrm_list_tagsfirst to get IDs. This prevents a common API usage error.
135-140: Pipeline movement workflow is clear and correct.The three-step process (detach old stage tag → attach new stage tag → update custom fields) properly maintains pipeline state. The workflow prevents orphaned tags and ensures audit trail via custom fields.
220-226: Smart link tracking example reinforces the numeric ID requirement.The smart link creation example correctly shows
apply_tags: [tag_id]with a comment noting it's a numeric ID for the 'proposal-viewed' tag. This repetition helps reinforce the API pattern established in earlier sections.
268-290: Strong sales-marketing integration workflows.The lead handoff and feedback loop sections provide clear, actionable processes for cross-team collaboration. The tag-based quality indicators (lead-quality-high/medium/low) and rejection reasons enable data-driven marketing optimization.
310-313: Automation best practices strike the right balance.The guidance to "Don't over-automate personal touches" and "Review and update sequences quarterly" prevents automation fatigue while maintaining relevance. This aligns with modern sales engagement best practices.
328-329: External documentation URLs are accessible and current.Both FluentCRM documentation links are operational and properly configured.
- Fix sales.md line 29: add .agent/ prefix to fluentcrm.md path - Update FluentCRM installation to use local build (npm package not published) - Change command from npx to node with local dist path - Add clone/build instructions to fluentcrm.md and mcp-integrations.md - Update fluentcrm.json template with local build command
|
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Mon Jan 12 17:01:55 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
1 participant
Summary
Changes
New Files
.agent/services/crm/fluentcrm.md- Complete FluentCRM MCP documentation including:Enhanced Files
.agent/sales.md- Now includes:.agent/marketing.md- Now includes:.agent/aidevops/mcp-integrations.md- Added FluentCRM MCP setup instructions.agent/AGENTS.md- Added services/crm folder referenceFluentCRM MCP Capabilities
Testing
Related
Summary by CodeRabbit
Documentation
Chores
✏️ Tip: You can customize this high-level summary in your review settings.