Skip to content

feat(agents): add activation profiles for improved agent routing#56

Merged
rjmurillo merged 2 commits into
mainfrom
feat/improve-agent-descriptions
Dec 18, 2025
Merged

feat(agents): add activation profiles for improved agent routing#56
rjmurillo merged 2 commits into
mainfrom
feat/improve-agent-descriptions

Conversation

@rjmurillo

@rjmurillo rjmurillo commented Dec 18, 2025

Copy link
Copy Markdown
Owner

Pull Request

Summary

Add activation vocabulary and summoning prompts to all 18 agents across all platforms to improve the model's ability to select the right specialist agent immediately.

Changes

  • Updated description field with activation-focused language in YAML frontmatter
  • Added ## Activation Profile section to each agent with:
    • Keywords: 20-word activation vocabulary cluster unique to each agent's specialty
    • Summon: 4-6-sentence character description for invoking the specialist
  • Updated 18 shared templates in templates/agents/
  • Regenerated 18 VSCode agents and 18 Copilot CLI agents using Generate-Agents.ps1
  • Updated 18 Claude agents directly

Type of Change

  • Bug fix (non-breaking change fixing an issue)
  • New feature (non-breaking change adding functionality)
  • Breaking change (fix or feature causing existing functionality to change)
  • Documentation update
  • Infrastructure/CI change
  • Refactoring (no functional changes)

Testing

  • Tests added/updated
  • Manual testing completed
  • No testing required (documentation only)

Agent Review

Security Review

Required for: Authentication, authorization, CI/CD, git hooks, secrets, infrastructure

  • No security-critical changes in this PR
  • Security agent reviewed infrastructure changes
  • Security agent reviewed authentication/authorization changes
  • Security patterns applied (see .agents/security/)

Other Agent Reviews

  • Architect reviewed design changes
  • Critic validated implementation plan
  • QA verified test coverage

Checklist

  • Code follows project style guidelines
  • Self-review completed
  • Comments added for complex logic
  • Documentation updated (if applicable)
  • No new warnings introduced

Related Issues


🤖 Generated with Claude Code


Note

Adds activation profiles across all agents/templates, mandates Serena MCP initialization in docs, removes the auto-generated header utility, and persists retrospective learnings to Serena memory.

  • Agents & Templates:
    • Add activation-focused description and new ## Activation Profile (Keywords + Summon) across all agent definitions in src/claude/*, src/copilot-cli/*, src/vs-code-agents/*, and templates/agents/*.
  • Docs:
    • Require Serena initialization at session start in AGENTS.md, CLAUDE.md, and .github/copilot-instructions.md.
  • Build:
    • Remove dead code Get-AutoGeneratedHeader and its export from build/Generate-Agents.Common.psm1.
  • Retrospective & Memory:
    • Add detailed session failure retrospective in .agents/retrospective/.
    • Persist skills, preferences, and outcomes under .serena/memories/* (session failures, new skills, and user preference: no auto-generated headers).

Written by Cursor Bugbot for commit 4ca9397. This will update automatically on new commits. Configure here.

Copilot AI review requested due to automatic review settings December 18, 2025 01:19

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This PR enhances agent discoverability by adding activation profiles to all 18 agents across three platforms (VSCode, Copilot CLI, and Claude). The changes improve how AI models select the appropriate specialist agent by providing keyword-based activation vocabulary and conversational summoning prompts. Each agent now has an "Activation Profile" section with 20 domain-specific keywords and a persona-driven description that helps models understand when and how to invoke each specialist.

Key Changes

  • Updated description fields in YAML frontmatter with more activation-focused language that emphasizes agent capabilities and use cases
  • Added "Activation Profile" sections to all agents containing Keywords (20-word vocabulary cluster) and Summon (conversational invocation prompt)
  • Maintained consistency across all 54 agent files (18 agents × 3 platforms) through template-based regeneration

Reviewed changes

Copilot reviewed 72 out of 72 changed files in this pull request and generated 1 comment.

File Description
templates/agents/*.shared.md (18 files) Source templates with new activation profiles that propagate to all platforms
src/vs-code-agents/*.agent.md (18 files) VSCode agent definitions regenerated from templates with platform-specific tool configurations
src/copilot-cli/*.agent.md (18 files) Copilot CLI agent definitions regenerated with name field and shell tools
src/claude/*.md (18 files) Claude Code agent definitions regenerated with model specifications and Claude-specific tool references

Comment thread templates/agents/high-level-advisor.shared.md
@coderabbitai

coderabbitai Bot commented Dec 18, 2025

Copy link
Copy Markdown

Caution

Review failed

The pull request is closed.

Note

Other AI code review bot(s) detected

CodeRabbit has detected other AI code review bot(s) in this pull request and will avoid duplicating their findings in the review comments. This may lead to a less comprehensive review.

📝 Walkthrough

Walkthrough

Adds standardized "Activation Profile" sections (Keywords + Summon) across agent/profile markdowns, expands many agent descriptions and templates, introduces Serena initialization and several .serena memory/policy artifacts, and removes the Get-AutoGeneratedHeader function/export from the build module. No runtime logic besides the module export change.

Changes

Cohort / File(s) Summary
Agent profiles (all platforms & templates)
src/claude/*.md, src/copilot-cli/*.md, src/vs-code-agents/*.md, templates/agents/*.md
Inserted standardized Activation Profile blocks (Keywords + Summon) and rewrote front-matter descriptions across many agents (analyst, architect, critic, devops, explainer, high-level-advisor, implementer, independent-thinker, memory, orchestrator, planner, pr-comment-responder, qa, retrospective, roadmap, security, skillbook, task-generator). Some agent docs gained richer subsections (Responsibilities, Protocols, Analysis templates, Memory references). These are documentation/content changes.
Build module (code change)
build/Generate-Agents.Common.psm1
Removed Get-AutoGeneratedHeader implementation and removed it from Export-ModuleMember exports (public API change).
Serena memories & skill artifacts
.serena/memories/*.md
Added multiple memory/policy/skill docs: session retrospective, Skill-Init-001 (mandatory Serena init + session protocol), Skill-Verify-001 (script audit), Skill-Memory-001 (feedback retrieval), Skill-Audit-001 (dead code detection), and two user-preference policy files (no-auto-generated-headers).
Top-level agent runbooks & instructions
AGENTS.md, CLAUDE.md, .github/copilot-instructions.md
Prepended mandatory Serena initialization instructions to AGENTS.md and CLAUDE.md and added Serena init block to Copilot instructions; added a clarified "Typical Workflow" sequence in AGENTS.md.
Templates / shared agent scaffolding
templates/agents/*.md (already included above)
Mirrors Activation Profile additions and description rewrites so generated agents inherit new activation wording and keywords.

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~25 minutes

Points needing special attention:

  • build/Generate-Agents.Common.psm1 — removal of Get-AutoGeneratedHeader is a breaking export change; verify callers, templates, and build scripts no longer rely on it.
  • New mandatory Serena initialization (AGENTS.md, CLAUDE.md, .github/copilot-instructions.md, .serena skills) — confirm activation sequence is implementable and documented tooling hooks exist.
  • Consistency checks between Activation Profile keywords/summons and any tooling that parses agent front-matter or templates (templates/agents/*).
  • PR-comment-responder and Independent-thinker docs include larger procedural expansions; validate internal consistency and cross-references to orchestrator/memory skills.

Possibly related PRs

Pre-merge checks and finishing touches

✅ Passed checks (3 passed)
Check name Status Explanation
Title check ✅ Passed Title follows conventional commit format with type 'feat' and scope 'agents', clearly describing the main change: adding activation profiles to agents.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Description check ✅ Passed The PR description clearly relates to the changeset: it adds activation profiles and summoning prompts to all agents across platforms, which matches the raw_summary showing consistent updates to Activation Profile sections across 18+ agent files.

📜 Recent review details

Configuration used: Repository YAML (base), Organization UI (inherited)

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 96e36b6 and 4ca9397.

📒 Files selected for processing (85)
  • .agents/retrospective/2025-12-17-session-failures.md (1 hunks)
  • .github/copilot-instructions.md (1 hunks)
  • .serena/memories/retrospective-2025-12-17-session-failures.md (1 hunks)
  • .serena/memories/skill-audit-001-dead-code-detection.md (1 hunks)
  • .serena/memories/skill-init-001-serena-mandatory.md (1 hunks)
  • .serena/memories/skill-init-001-session-initialization.md (1 hunks)
  • .serena/memories/skill-memory-001-feedback-retrieval.md (1 hunks)
  • .serena/memories/skill-verify-001-script-audit.md (1 hunks)
  • .serena/memories/user-preference-no-auto-generated-headers.md (1 hunks)
  • .serena/memories/user-preference-no-auto-headers.md (1 hunks)
  • AGENTS.md (1 hunks)
  • CLAUDE.md (1 hunks)
  • build/Generate-Agents.Common.psm1 (0 hunks)
  • src/claude/analyst.md (2 hunks)
  • src/claude/architect.md (2 hunks)
  • src/claude/critic.md (2 hunks)
  • src/claude/devops.md (2 hunks)
  • src/claude/explainer.md (2 hunks)
  • src/claude/high-level-advisor.md (2 hunks)
  • src/claude/implementer.md (2 hunks)
  • src/claude/independent-thinker.md (2 hunks)
  • src/claude/memory.md (2 hunks)
  • src/claude/orchestrator.md (2 hunks)
  • src/claude/planner.md (2 hunks)
  • src/claude/pr-comment-responder.md (2 hunks)
  • src/claude/qa.md (2 hunks)
  • src/claude/retrospective.md (2 hunks)
  • src/claude/roadmap.md (2 hunks)
  • src/claude/security.md (2 hunks)
  • src/claude/skillbook.md (2 hunks)
  • src/claude/task-generator.md (2 hunks)
  • src/copilot-cli/analyst.agent.md (2 hunks)
  • src/copilot-cli/architect.agent.md (2 hunks)
  • src/copilot-cli/critic.agent.md (2 hunks)
  • src/copilot-cli/devops.agent.md (2 hunks)
  • src/copilot-cli/explainer.agent.md (2 hunks)
  • src/copilot-cli/high-level-advisor.agent.md (2 hunks)
  • src/copilot-cli/implementer.agent.md (2 hunks)
  • src/copilot-cli/independent-thinker.agent.md (2 hunks)
  • src/copilot-cli/memory.agent.md (2 hunks)
  • src/copilot-cli/orchestrator.agent.md (2 hunks)
  • src/copilot-cli/planner.agent.md (2 hunks)
  • src/copilot-cli/pr-comment-responder.agent.md (2 hunks)
  • src/copilot-cli/qa.agent.md (2 hunks)
  • src/copilot-cli/retrospective.agent.md (2 hunks)
  • src/copilot-cli/roadmap.agent.md (2 hunks)
  • src/copilot-cli/security.agent.md (2 hunks)
  • src/copilot-cli/skillbook.agent.md (2 hunks)
  • src/copilot-cli/task-generator.agent.md (2 hunks)
  • src/vs-code-agents/analyst.agent.md (2 hunks)
  • src/vs-code-agents/architect.agent.md (2 hunks)
  • src/vs-code-agents/critic.agent.md (2 hunks)
  • src/vs-code-agents/devops.agent.md (2 hunks)
  • src/vs-code-agents/explainer.agent.md (2 hunks)
  • src/vs-code-agents/high-level-advisor.agent.md (2 hunks)
  • src/vs-code-agents/implementer.agent.md (2 hunks)
  • src/vs-code-agents/independent-thinker.agent.md (2 hunks)
  • src/vs-code-agents/memory.agent.md (2 hunks)
  • src/vs-code-agents/orchestrator.agent.md (2 hunks)
  • src/vs-code-agents/planner.agent.md (2 hunks)
  • src/vs-code-agents/pr-comment-responder.agent.md (2 hunks)
  • src/vs-code-agents/qa.agent.md (2 hunks)
  • src/vs-code-agents/retrospective.agent.md (2 hunks)
  • src/vs-code-agents/roadmap.agent.md (2 hunks)
  • src/vs-code-agents/security.agent.md (2 hunks)
  • src/vs-code-agents/skillbook.agent.md (2 hunks)
  • src/vs-code-agents/task-generator.agent.md (2 hunks)
  • templates/agents/analyst.shared.md (2 hunks)
  • templates/agents/architect.shared.md (2 hunks)
  • templates/agents/critic.shared.md (2 hunks)
  • templates/agents/devops.shared.md (2 hunks)
  • templates/agents/explainer.shared.md (2 hunks)
  • templates/agents/high-level-advisor.shared.md (2 hunks)
  • templates/agents/implementer.shared.md (2 hunks)
  • templates/agents/independent-thinker.shared.md (2 hunks)
  • templates/agents/memory.shared.md (2 hunks)
  • templates/agents/orchestrator.shared.md (2 hunks)
  • templates/agents/planner.shared.md (2 hunks)
  • templates/agents/pr-comment-responder.shared.md (2 hunks)
  • templates/agents/qa.shared.md (2 hunks)
  • templates/agents/retrospective.shared.md (2 hunks)
  • templates/agents/roadmap.shared.md (2 hunks)
  • templates/agents/security.shared.md (2 hunks)
  • templates/agents/skillbook.shared.md (2 hunks)
  • templates/agents/task-generator.shared.md (2 hunks)

Comment @coderabbitai help to get the list of available commands and usage tips.

@coderabbitai coderabbitai Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 0

Caution

Some comments are outside the diff and can’t be posted inline due to platform limitations.

⚠️ Outside diff range comments (12)
src/vs-code-agents/memory.agent.md (1)

1-6: Add AUTO-GENERATED FILE header comment—file lacks required safety marker.

File was regenerated via Generate-Agents.ps1 and content is consistent with template. However, both src/vs-code-agents/memory.agent.md and src/copilot-cli/memory.agent.md are missing the AUTO-GENERATED FILE header comment required by coding guidelines.

Add this header to both files:

  • Format: # AUTO-GENERATED FILE - DO NOT EDIT DIRECTLY
  • Include source template reference and generator script name
  • Place before the YAML frontmatter
src/copilot-cli/planner.agent.md (1)

2-17: Add missing AUTO-GENERATED FILE header comment.

File is missing the required # AUTO-GENERATED FILE - DO NOT EDIT DIRECTLY header comment before YAML frontmatter. Per coding guidelines, generated agent files in src/copilot-cli/ must include this header with source template and regeneration command reference to prevent accidental manual edits.

src/copilot-cli/devops.agent.md (1)

2-17: Add AUTO-GENERATED FILE header to generated agent file.

Generated Copilot CLI agent files must include a header comment at the top (before YAML frontmatter) indicating they are auto-generated and should not be edited directly. Missing from lines 1-2. Add:

<!-- AUTO-GENERATED FILE - DO NOT EDIT DIRECTLY
Source: templates/agents/devops.shared.md
Generator: build/Generate-Agents.ps1
-->
src/vs-code-agents/task-generator.agent.md (1)

2-17: Add required AUTO-GENERATED FILE header to generated file.

This file is generated from templates/agents/task-generator.shared.md and must include a header comment per coding guidelines. Add the following header comment at the top of the file before the YAML frontmatter:

# AUTO-GENERATED FILE - DO NOT EDIT DIRECTLY
# Source: templates/agents/task-generator.shared.md
# Generator: build/Generate-Agents.ps1

Generated agent files in src/vs-code-agents/ must never be edited manually. Regenerate by running the build script, which should automatically add this header.

src/vs-code-agents/planner.agent.md (1)

2-17: VS Code agent has incorrect model field.

The template (templates/agents/planner.shared.md) does not specify a model, and src/copilot-cli/planner.agent.md correctly has no model field. However, src/vs-code-agents/planner.agent.md line 5 specifies model: Claude Opus 4.5 (anthropic) while src/claude/planner.md line 4 uses model: sonnet. Remove the model field from the VS Code agent to match the template structure, or change it to model: sonnet to align with the Claude source.

templates/agents/explainer.shared.md (1)

90-110: Replace absolute path examples with placeholder syntax in anti-pattern section.

Lines 96, 99–100 contain literal absolute paths that violate coding guidelines. Use placeholder syntax instead:

  • [DRIVE]:\Users\[username]\repo\docs\guide.md for Windows
  • /Users/[username]/repo/docs/guide.md for macOS
  • /home/[username]/repo/docs/guide.md for Linux

This preserves the anti-pattern examples while passing validation.

src/claude/explainer.md (1)

95-101: Replace absolute paths in anti-pattern examples with placeholder syntax.

Lines 107-110 show forbidden absolute paths (Windows C:, macOS /Users/, Linux /home/) as examples of what not to do. Coding guidelines prohibit absolute paths in documentation without exception. Replace with placeholders to demonstrate the anti-pattern without violating the requirement.

Use syntax like [WINDOWS_DRIVE]:\Users\[USERNAME]\repo\docs\guide.md and /Users/[USERNAME]/repo/docs/guide.md to preserve the teaching value while complying with the relative path requirement.

src/vs-code-agents/explainer.agent.md (1)

94-101: Replace absolute paths in anti-pattern examples with placeholder syntax.

The Path Normalization Protocol section shows forbidden absolute paths. Coding guidelines prohibit absolute paths in documentation—including in anti-pattern examples. Use placeholder syntax to demonstrate the anti-pattern without breaking the rule.

Fix the source template templates/agents/explainer.shared.md, then regenerate all derived files. Replace paths with placeholders:

  • Windows: [WINDOWS_DRIVE]:\Users\[USERNAME]\repo\docs\guide.md
  • macOS: /Users/[USERNAME]/repo/docs/guide.md
  • Linux: /home/[USERNAME]/repo/docs/guide.md
src/claude/pr-comment-responder.md (1)

638-643: Missing formal Execution Mindset section. Other agent templates (analyst, critic, roadmap, etc.) include an explicit "Execution Mindset" section with Think/Act pattern. PR Comment Responder should include this for consistency and clarity of operational behavior.

Consider adding:

## Execution Mindset

**Think:** "Every comment deserves acknowledgment and systematic resolution"

**Act:** Triage by actionability, track conversations, delegate appropriately

**Verify:** No comment left unaddressed, no reviewer ignored

Suggested location: Between "Communication Guidelines" and "Bot-Specific Handling" sections.

src/copilot-cli/explainer.agent.md (1)

92-110: Pipeline failure: Path normalization violations in anti-pattern examples need resolution.

Lines 96, 99, 100 show absolute paths marked as "FORBIDDEN" examples. Pipeline validation correctly flags these as violations, but they're presented as demonstrative anti-patterns. Two options: (1) convert anti-pattern paths to [example-path] placeholders, or (2) move anti-patterns to a separate callout where linting is suppressed. Verify the approach with your CI configuration.

templates/agents/pr-comment-responder.shared.md (1)

656-682: Duplicate Handoff sections must be removed.

Lines 656–663 ("## Handoff") and lines 675–682 ("## Handoff Protocol") contain identical content. Per coding guidelines, keep only one Handoff Options section in agent templates.

🔎 Remove the duplicate section:
 ## Handoff
 
 This agent primarily delegates to **orchestrator**. Direct handoffs:
 
 | Target | When | Purpose |
 |--------|------|---------|
 | **orchestrator** | Each comment analysis | Full workflow determination |
 | **orchestrator** | Each implementation | Code changes |

-## Handoff Protocol
-
-This agent primarily delegates to **orchestrator**. Direct handoffs:
-
-| Target | When | Purpose |
-|--------|------|---------|  
-| **orchestrator** | Each comment analysis | Full workflow determination |
-| **orchestrator** | Each implementation | Code changes |
src/vs-code-agents/pr-comment-responder.agent.md (1)

656-682: Duplicate Handoff sections inherited from template.

Lines 656–663 and 675–682 duplicate the Handoff content. This issue originates in the template (templates/agents/pr-comment-responder.shared.md). Fix the template, then regenerate this file with .\build\Generate-Agents.ps1.

🔎 Fix the template and regenerate:

Edit templates/agents/pr-comment-responder.shared.md to remove lines 675–682 (the duplicate "## Handoff Protocol" section), then run:

.\build\Generate-Agents.ps1

This will regenerate src/vs-code-agents/pr-comment-responder.agent.md with the corrected content.

🧹 Nitpick comments (1)
src/claude/implementer.md (1)

17-17: Minor wording suggestion for Summon statement.

Line 17 uses "hard to test" twice in close proximity: "If it's hard to test, flag it—that reveals deeper design problems." Consider rephrasing the second clause to strengthen specificity, e.g., "that signals deeper design flaws" or "that uncovers structural issues."

coderabbitai[bot]
coderabbitai Bot previously approved these changes Dec 18, 2025
Add activation vocabulary and summoning prompts to all 18 agents across
all platforms (Claude, VSCode, Copilot CLI) to improve model's ability
to select the right specialist agent immediately.

Changes per agent:
- Updated description field with activation-focused language
- Added Activation Profile section with:
  - Keywords: 20-word activation vocabulary cluster
  - Summon: 4-sentence character description for invoking specialist

Files modified:
- 18 Claude agents (src/claude/)
- 18 VSCode agents (src/vs-code-agents/)
- 18 Copilot CLI agents (src/copilot-cli/)
- 18 shared templates (templates/agents/)

Also removed dead code:
- Removed Get-AutoGeneratedHeader function from Generate-Agents.Common.psm1
  (unused function that could accidentally add unwanted headers to files)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
BREAKING: All Claude Code, VS Code, and Copilot sessions MUST initialize
Serena before any other work.

Changes:
- CLAUDE.md: Added mandatory Serena init section at top
- AGENTS.md: Added mandatory Serena init section at top
- .github/copilot-instructions.md: Added mandatory Serena init section

Also includes:
- Retrospective analysis of session failures (.agents/retrospective/)
- Skills and user preferences in Serena memory (.serena/memories/)

Root cause: Not initializing Serena led to missing project context,
repeated mistakes, and ignoring user preferences stored in memory.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Copilot AI review requested due to automatic review settings December 18, 2025 02:15

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 85 out of 85 changed files in this pull request and generated no new comments.

@rjmurillo rjmurillo merged commit 0f4a47a into main Dec 18, 2025
10 of 13 checks passed
@rjmurillo rjmurillo deleted the feat/improve-agent-descriptions branch December 18, 2025 02:18
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants