feat: add mission statement with ROI and self-improvement directives #652
Conversation
Add foundational mission block to prompts/build.txt (system prompt root) establishing purpose, cost/time awareness, self-healing, self-improvement, and capability growth. Update AGENTS.md header and Quick Reference to reflect mission-driven identity.
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 establishes a core mission for the AI DevOps agent, focusing on maximizing efficiency and return on investment through strategic directives like self-healing, continuous improvement, and leveraging high-impact tools. These changes are integrated into the agent's primary prompt file and reflected in its documentation, ensuring a consistent and purposeful operational framework. Highlights
Changelog
Activity
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
|
WalkthroughThis change updates agent configuration and prompt documentation to establish clearer mission objectives emphasizing self-healing and self-improving automation alongside operational directives and behavioral constraints for DevOps efficiency. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 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. ✨ Finishing touches🧪 Generate unit tests (beta)
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 |
🔍 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: Sun Feb 8 19:32:58 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 mission statement, which is a great addition for clarifying the agent's purpose. The changes in AGENTS.md and prompts/build.txt are clear and well-described. I have a few suggestions to enhance consistency and readability in the new text, primarily around standardizing the term 'DevOps' and ensuring grammatical parallelism in the list of mission directives.
|
|
||
| **Supported tools:** [OpenCode](https://opencode.ai/) (TUI, Desktop, and Extension for Zed/VSCode/AntiGravity) is the only tested and supported AI coding tool for aidevops. The `opencode` CLI is used for headless worker dispatch, supervisor orchestration, and companion subagent spawning. aidevops is also available in the Claude marketplace. | ||
|
|
||
| **Mission**: Maximise dev-ops efficiency and ROI — maximum value for the user's time and money. Self-heal, self-improve, and grow capabilities through highest-leverage tooling. See `prompts/build.txt` for the full mission statement. |
There was a problem hiding this comment.
For consistency with other parts of the document and standard industry terminology, 'dev-ops' should be capitalized as 'DevOps'. For example, 'AI DevOps agent' is used on line 12.
| **Mission**: Maximise dev-ops efficiency and ROI — maximum value for the user's time and money. Self-heal, self-improve, and grow capabilities through highest-leverage tooling. See `prompts/build.txt` for the full mission statement. | |
| **Mission**: Maximise DevOps efficiency and ROI — maximum value for the user's time and money. Self-heal, self-improve, and grow capabilities through highest-leverage tooling. See `prompts/build.txt` for the full mission statement. |
| ## Quick Reference | ||
|
|
||
| - **Purpose**: DevOps automation across multiple services | ||
| - **Purpose**: Maximise dev-ops efficiency — self-healing, self-improving automation |
There was a problem hiding this comment.
For consistency and to adhere to the standard industry term, please capitalize 'dev-ops' to 'DevOps'.
| - **Purpose**: Maximise dev-ops efficiency — self-healing, self-improving automation | |
| - **Purpose**: Maximise DevOps efficiency — self-healing, self-improving automation |
| # Overrides: file discovery, code search, git workflow, security, agent framework | ||
|
|
||
| # Mission | ||
| Your purpose is to maximise dev-ops efficiency and ROI for the user — maximum value for their time and money. You achieve this by: |
There was a problem hiding this comment.
For consistency with the term 'DevOps' used later in this file (line 14) and standard industry usage, 'dev-ops' should be capitalized.
Your purpose is to maximise DevOps efficiency and ROI for the user — maximum value for their time and money. You achieve this by:
| # Mission | ||
| Your purpose is to maximise dev-ops efficiency and ROI for the user — maximum value for their time and money. You achieve this by: | ||
| - Maximising leverage: use the highest-impact tools and models available; prefer approaches that multiply output per unit of cost and time | ||
| - Cost and time awareness: choose efficient models, batch work, parallelise where possible, and avoid waste (tokens, compute, human attention) |
There was a problem hiding this comment.
To improve grammatical parallelism in the list of directives, consider rephrasing this item to be more action-oriented, similar to 'Maximising leverage' and 'Growing capabilities'. 'Cost and time awareness' is a state, whereas the others are actions. A more parallel phrasing would improve the clarity of the mission statement.
- Optimising for cost and time: choose efficient models, batch work, parallelise where possible, and avoid waste (tokens, compute, human attention)
![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 @.agents/prompts/build.txt:
- Around line 4-12: The Mission block at the top of the prompt duplicates
canonical guidance and should be removed or collapsed; replace the multi-line
"Mission" section (the block beginning with "# Mission" and the subsequent
bullet list) with a single-line pointer or minimal one-liner that references the
authoritative AGENTS.md mission section (e.g., "See AGENTS.md — Mission") and,
if desired, keep a tiny one-sentence summary, ensuring no substantive
operational rules are duplicated in this file.
🧹 Nitpick comments (1)
.agents/AGENTS.md (1)
10-10: Keep the Mission line as a minimal pointer to preserve the root instruction budget.
Root AGENTS.md is intended to stay within a ~50–100 instruction budget and use progressive disclosure; adding a full mission sentence here pushes the root file further from that target. Consider reducing this to a brief pointer only (e.g., “Mission: see prompts/build.txt”) and keep the full wording elsewhere.Based on learnings: “Organize agent documentation with instructions budget of ~50-100 max in root AGENTS.md, using progressive disclosure with pointers to subagents.”🔧 Suggested tightening
-**Mission**: Maximise dev-ops efficiency and ROI — maximum value for the user's time and money. Self-heal, self-improve, and grow capabilities through highest-leverage tooling. See `prompts/build.txt` for the full mission statement. +**Mission**: See `prompts/build.txt` for the full mission statement.
| # Mission | ||
| Your purpose is to maximise dev-ops efficiency and ROI for the user — maximum value for their time and money. You achieve this by: | ||
| - Maximising leverage: use the highest-impact tools and models available; prefer approaches that multiply output per unit of cost and time | ||
| - Cost and time awareness: choose efficient models, batch work, parallelise where possible, and avoid waste (tokens, compute, human attention) | ||
| - Self-healing: when something breaks, diagnose the root cause, create tasks, and fix it | ||
| - Self-improving: when patterns of failure or inefficiency emerge, improve the framework itself | ||
| - Growing capabilities: discover, evaluate, and adopt new tools and approaches that increase impact | ||
| - Requesting resources: when better tools, higher model tiers, or more compute would serve the mission, ask for them | ||
| Everything you do serves the user's goals and projects. The operational rules below exist to support this mission. |
There was a problem hiding this comment.
Avoid duplicating mission instructions outside AGENTS.md.
The mission block here duplicates instruction content that should live in AGENTS.md as the single source of truth. To prevent drift, consider replacing this block with a short pointer to the AGENTS.md mission section (or keep a minimal one-liner and link to the authoritative text).
🔧 Suggested consolidation
-# Mission
-Your purpose is to maximise dev-ops efficiency and ROI for the user — maximum value for their time and money. You achieve this by:
-- Maximising leverage: use the highest-impact tools and models available; prefer approaches that multiply output per unit of cost and time
-- Cost and time awareness: choose efficient models, batch work, parallelise where possible, and avoid waste (tokens, compute, human attention)
-- Self-healing: when something breaks, diagnose the root cause, create tasks, and fix it
-- Self-improving: when patterns of failure or inefficiency emerge, improve the framework itself
-- Growing capabilities: discover, evaluate, and adopt new tools and approaches that increase impact
-- Requesting resources: when better tools, higher model tiers, or more compute would serve the mission, ask for them
-Everything you do serves the user's goals and projects. The operational rules below exist to support this mission.
+# Mission
+See `.agents/AGENTS.md` (Mission section) for the authoritative mission statement.🤖 Prompt for AI Agents
In @.agents/prompts/build.txt around lines 4 - 12, The Mission block at the top
of the prompt duplicates canonical guidance and should be removed or collapsed;
replace the multi-line "Mission" section (the block beginning with "# Mission"
and the subsequent bullet list) with a single-line pointer or minimal one-liner
that references the authoritative AGENTS.md mission section (e.g., "See
AGENTS.md — Mission") and, if desired, keep a tiny one-sentence summary,
ensuring no substantive operational rules are duplicated in this file.
1 participant
Summary
prompts/build.txt(the system prompt root, loaded every session) establishing purpose, cost/time awareness, self-healing, self-improvement, and capability growthAGENTS.mdheader with mission summary and pointer to full statementChanges
.agents/prompts/build.txt(+10 lines, ~95 tokens)# Missionblock before the identity line.agents/AGENTS.md(+3 lines)**Mission**line in header with compact summary + pointer toprompts/build.txtDesign Decisions
Testing
Summary by CodeRabbit
Documentation
Chores