feat: add emoji icons to task tool description field

.ai-team/agents/fenster/history.md

@@ -123,3 +123,9 @@ _Summarized from initial architecture review (2026-02-07). Full entries in `hist
 - **Docs template extraction — inline→external files.** Refactored `docs/build.js` to read HTML template, CSS, and JS from external files instead of generating them inline via `getCSS()`, `getJS()`, and `getTemplate()` string-building functions. Created `docs/assets/template.html` (HTML shell with `{{title}}`, `{{nav}}`, `{{content}}`, `{{searchIndex}}`, `{{basePath}}` placeholders), `docs/assets/style.css`, and `docs/assets/script.js`. Build reads template once at startup, does placeholder replacement per page. CSS/JS are linked externally (`<link>` / `<script src>`), search index remains inlined as page-specific `<script>` block. The existing `copyDir` of `docs/assets/` → `_site/assets/` handles deploying CSS/JS automatically. Key paths: `docs/assets/template.html`, `docs/assets/style.css`, `docs/assets/script.js`.
 
 - **Copilot CLI agent manifest YAML frontmatter validation (issue #59).** The `version` field in squad.agent.md's YAML frontmatter was not a supported property per the [GitHub Copilot CLI agent manifest specification](https://docs.github.com/en/copilot/reference/custom-agents-configuration). Supported properties are: `name`, `description`, `tools`, and `mcp-servers` (org/enterprise only). Unsupported properties like `version`, `model`, `argument-hint`, and `handoffs` cause the Copilot CLI parser to throw "error: too many arguments" because it interprets them as command-line arguments. Fixed by moving version tracking from YAML frontmatter to an HTML comment (`<!-- version: X.Y.Z -->`) immediately after the frontmatter closing `---`. Updated `stampVersion()` and `readInstalledVersion()` in index.js to work with the new HTML comment format (with backward compatibility fallback for upgrade scenarios). The agent name was also simplified from `Squad (v0.0.0-source)` to just `Squad` in the frontmatter. This pattern applies to all custom agent manifests — only use officially supported YAML properties to avoid parser errors.
+
+📌 Team update (2026-02-15): YAML frontmatter validation — unsupported properties removed from squad.agent.md, version moved to HTML comment. Sidebar logo sized to 40px. Docs build templates extracted to external files (template.html, style.css, script.js) for editor support — Fenster
+
+
+📌 Team update (2026-02-15): Directory structure rename planned — .ai-team/ → .squad/ starting v0.5.0 with backward-compatible migration; full removal in v1.0.0 — Brady
+

.ai-team/agents/hockney/history.md

@@ -86,3 +86,6 @@ _Summarized from initial assessment (2026-02-07). Full entries in `history-archi
     - **FAIL: "ask_user referenced in Init Mode"** — The prompt never mentions `ask_user` or any explicit tool for getting confirmation. Without this, the LLM has no mechanism to yield control back to the user.
   - **Pattern: Prompt structure testing.** These are not runtime LLM behavior tests — they verify the text content of generated prompt files. The pattern is: run `node index.js` in a temp dir, read the generated `.github/agents/squad.agent.md`, extract sections by heading, assert on text patterns (regex + string search). This catches prompt regressions without needing an LLM in the loop.
   - **Key insight:** The current prompt relies on step numbering alone to create a pause point. Step 5 says "Ask: Look right?" and step 6 says "On confirmation, create..." — but without an explicit STOP instruction or ask_user reference, LLMs treat steps 4-6 as a single execution block. The fix needs both: (a) an explicit STOP/WAIT directive, and (b) an ask_user tool reference to force the LLM to yield.
+
+📌 Team update (2026-02-15): Directory structure rename planned — .ai-team/ → .squad/ starting v0.5.0 with backward-compatible migration; full removal in v1.0.0 — Brady
+

.ai-team/agents/keaton/history.md

@@ -293,4 +293,10 @@ _Summarized 2026-02-10+ learnings (full entries available in session logs):_
   - **Key prompt pattern: numbered lists cause LLMs to skip pauses.** When a pause/confirmation step appears mid-list, the model generates the question text but immediately proceeds to the next numbered step. The completion impulse is stronger than conversational turn-taking instinct. This is a general anti-pattern — any multi-step prompt that requires a mid-sequence pause must use structural breaks (section boundaries, separate headings) or tool-based gates (ask_user), not inline text instructions.
   - **Key prompt pattern: contradictory behavioral directives compound.** "What can I launch RIGHT NOW?" + "don't wait for user input" + "proceed immediately" in Team Mode sections bleed into Init Mode behavior. LLMs don't scope instructions to labeled modes — they absorb the full prompt as behavioral priors. Init Mode exceptions must be explicitly stated in the competing sections.
   - **Recommended fix: two-phase Init Mode split + Eager Execution exception.** Split Init Mode into Phase 1 (propose roster, end response) and Phase 2 (create files on user reply) with a section boundary between them. Add explicit Init Mode exception to Eager Execution Philosophy. Tighten implicit-yes clause to require "reply to step 5" not original message.
-  - **Key file paths:** .ai-team/decisions/inbox/keaton-init-confirmation-bug.md (full analysis)
+  - **Key file paths:** .ai-team/decisions/inbox/keaton-init-confirmation-bug.md (full analysis)
+
+📌 Team update (2026-02-15): Init Mode optimization and confirmation skip fixes consolidated — Keaton's compression work (2026-02-13) merged with detailed UX fix analysis (2026-02-15), including five root causes and four proposed fixes for confirmation skip issue.
+
+
+📌 Team update (2026-02-15): Directory structure rename planned — .ai-team/ → .squad/ starting v0.5.0 with backward-compatible migration; full removal in v1.0.0 — Brady
+

.ai-team/agents/kobayashi/history.md

@@ -70,3 +70,6 @@ _Summarized from sessions through 2026-02-09. Full entries in `history-archive.m
 
 📌 Team update (2026-02-12):Cross-client sub-agent API research complete — squad.agent.md uses task tool exclusively for CLI platform, VS Code uses runSubagent, no unification planned — research by Kujan
 📌 Team update (2026-02-13): go:/release: label automation shipped — Four-workflow system enforces label namespace integrity (go:* triage verdicts, release:* version targets). Workflows: squad-label-enforce.yml (mutual exclusivity), sync-squad-labels.yml (sync 8 static labels), squad-triage.yml (default go:needs-research), squad-heartbeat.yml (detect label gaps). Labels-as-state-machine is foundational to GitHub-native workflow. — decided by Fenster
+
+📌 Team update (2026-02-15): Directory structure rename planned — .ai-team/ → .squad/ starting v0.5.0 with backward-compatible migration; full removal in v1.0.0 — Brady
+

.ai-team/agents/kujan/history.md

@@ -119,3 +119,6 @@ _Summarized 2026-02-10 learnings (full entries in session logs and proposals):_
   - **Output:** `team-docs/proposals/034a-model-background-parity.md`, commented on Issue #34.
 📌 Team update (2026-02-14): VS Code Model & Background Parity — Phase 1 (v0.4.0): accept session model, use runSubagent. Phase 2 (v0.5.0): generate model-tier agent files. runSubagent lacks model param; use prompt-level detection in squad.agent.md. — decided by Kujan
 
+
+📌 Team update (2026-02-15): Directory structure rename planned — .ai-team/ → .squad/ starting v0.5.0 with backward-compatible migration; full removal in v1.0.0 — Brady
+

.ai-team/agents/mcmanus/history.md

@@ -203,3 +203,6 @@ _Summarized from initial assessment, messaging overhaul, demo script, and README
 
 - **CONTRIBUTING.md created (2026-02-13)** — Proper contributor's guide with complete branch model education. Structure: Getting Started (fork/clone/install/test) → Branch Model (three-tier diagram + naming convention) → What's Protected (unmissable section on `.ai-team/` and `team-docs/` blocks, guard workflow behavior) → PR Process (step-by-step from feature branch through guard checks with remediation) → File Matrix (quick reference table) → Guard Mechanism (how it works, transparent) → Running Tests → Commit Conventions (conventional commits) → Code Style (2-space, camelCase, minimal comments) → Labels (taxonomy brief) → FAQ (10 common questions) → Summary. Key strategy: make `.ai-team/` rule unmissable through repetition, visual emphasis (🚫 emoji, bold, multiple sections), and concrete examples. Guard workflow is explained as a helper not a blocker. Branch protection motivated by "keeps biting us" — human reason, not dogma. Updated `docs/community.md` "How to Contribute" section with prominent CONTRIBUTING.md link.
 
+
+📌 Team update (2026-02-15): Directory structure rename planned — .ai-team/ → .squad/ starting v0.5.0 with backward-compatible migration; full removal in v1.0.0 — Brady
+

.ai-team/agents/redfoot/history.md

@@ -76,3 +76,6 @@
 📌 Team update (2026-02-10): Proposal migration uses three-wave approach — active first, shipped second, superseded/deferred last. — decided by Keaton
 
 📌 Team update (2026-02-11): Per-agent model selection implemented with cost-first directive (optimize cost unless writing code) — decided by Brady and Verbal
+
+📌 Team update (2026-02-15): Directory structure rename planned — .ai-team/ → .squad/ starting v0.5.0 with backward-compatible migration; full removal in v1.0.0 — Brady
+

.ai-team/agents/scribe/history.md

@@ -67,3 +67,6 @@
 
 📌 Team update (2026-02-13): CI/CD workflows and team branching infrastructure consolidated — Three workflows shipped (squad-ci.yml, squad-preview.yml, squad-release.yml), CI guard added (squad-main-guard.yml) to block .ai-team/** and internal team-docs/** from main/preview, release process documented comprehensively in docs/scenarios/release-process.md. CONTRIBUTING.md guide created for external contributors (branch model, protected files, guard explanation, PR process). All enforcements via GitHub Actions CI gates, not just .gitignore. — decided by Kobayashi and McManus
 
+
+📌 Team update (2026-02-15): Directory structure rename planned — .ai-team/ → .squad/ starting v0.5.0 with backward-compatible migration; full removal in v1.0.0 — Brady
+

.ai-team/agents/strausz/history.md

@@ -42,3 +42,6 @@
 - Multi-root workspaces have known bugs with path resolution and `grep_search` (vscode#264837, vscode#293428). Single-root is the supported configuration
 - VS Code's silent success bug on `editFiles` (vscode#253561) mirrors Squad's P0 bug — keep Response Order workaround in spawn prompts
 - **Key architectural insight:** Squad's instruction-level abstraction (describing operations, not tool names) is the correct pattern. It naturally works across both CLI and VS Code because the agent maps operation descriptions to available tools
+
+📌 Team update (2026-02-15): Directory structure rename planned — .ai-team/ → .squad/ starting v0.5.0 with backward-compatible migration; full removal in v1.0.0 — Brady
+

.ai-team/agents/verbal/history.md

@@ -197,3 +197,6 @@ _Summarized from sessions through 2026-02-09. Full entries in `history-archive.m
 
 📌 Team update (2026-02-13): Client Compatibility section added to squad.agent.md with platform detection logic, VS Code spawn adaptations, and feature degradation table — decided by Verbal
 
+
+📌 Team update (2026-02-15): Directory structure rename planned — .ai-team/ → .squad/ starting v0.5.0 with backward-compatible migration; full removal in v1.0.0 — Brady
+