📄 CodeRabbit inference engine (.agents/critique/001-agent-templating-critique.md)

For agent platform files, evaluate whether near-identical variants (99%+ overlap) can be consolidated with conditional configuration rather than maintaining separate files

Files:

• .agents/qa/session-808-worktrunk-hook.md
• .agents/qa/issue-834-worktrunk-config.md

📄 CodeRabbit inference engine (.agents/retrospective/pr43-coderabbit-root-cause-analysis.md)

.agents/**/*.md: Use PREFIX-NNN naming convention (e.g., EPIC-001, CRITIQUE-001) for sequenced artifacts and type-prefixed naming (e.g., prd-, tasks-) for non-sequenced artifacts
Normalize all file paths in markdown documents to be repository-relative before committing, removing absolute machine-specific paths

.agents/**/*.md: Session logs and documentation must include Phase checklist verification (Phase 1-3 protocol compliance including agent activation, instruction reading, handoff file updates, and session logging)
Session logs must document Session ID, date, agent name, and branch information in a standardized header format

Document analysis recommendations with specific rationale when adding new governance documents like PROJECT-CONSTRAINTS.md

Maintain debugging skills documentation in .agents/ directory

Document implementation notes explaining deviations from user prompts or decisions made during development (e.g., using plural form for directory names)

Run markdown lint on all generated artifacts before completing a session

Run markdown lint validation (0 errors expected) before committing documentation files in the .agents directory

.agents/**/*.md: Use consistent absolute file paths throughout task and PRD documentation instead of mixing relative and absolute path formats
Run markdown linting with npx markdownlint-cli2 --fix on all agent-generated documentation before commit

All modifications to agent documentation and specifications must be marked with status updates (e.g., DRAFT → CONSOLIDATED) and include consolidation notes in headers

Configure GitHub MCP server in project MCP settings and create github-agent.md with agent-specific tool binding following the agent isolation pattern from superpowers-chrome

Markdown linting must pass for all session logs and documentation files

When referencing ADRs (Architecture Decision Records) in documentation, ensure the context provides sufficient detail - either the ADR is discussed in-docum...

Files:

• .agents/qa/session-808-worktrunk-hook.md
• .agents/qa/issue-834-worktrunk-config.md

📄 CodeRabbit inference engine (.agents/roadmap/epic-agent-consolidation.md)

Single-source agent files should use frontmatter markers to delineate platform-specific sections for VS Code and Copilot CLI variants

Maintain artifact synchronization markers in tracking files (.md) with status indicators ([COMPLETE], [RESOLVED], [VERIFIED]) and timestamps to document completion and verification of work

Separate domain knowledge from methodology - store domain expertise in knowledge documents, not in methodology/protocol files

**/.agents/**/*.md: Every skill MUST have a ## Triggers section immediately after the frontmatter and title
Skill descriptions must be between 150-250 characters (note: validator checks 10+ words, not characters)
Skill descriptions must include trigger keywords per Anthropic Claude Code specification (max 1024 chars, description is primary trigger)
Trigger phrases must only contain whitelisted characters: [a-zA-Z0-9 -:,]
Operation paths in trigger tables must be relative paths with no .. directory traversal sequences
Triggers must match one of four patterns: command+context, question, problem statement, or request+goal
Skills must include provenance metadata (source, author, and integrity fields) for verification of skill origin
Skill descriptions must be in natural language matching one of four patterns: command+context, question, problem statement, or request+goal
Skill maturity levels (experimental vs stable) must be documented to indicate skill stability and readiness
Use the verb + what + when + outcome formula for skill descriptions to ensure they are teachable and measurable

Files:

• .agents/qa/session-808-worktrunk-hook.md
• .agents/qa/issue-834-worktrunk-config.md

📄 CodeRabbit inference engine (.agents/sessions/2025-12-18-session-21-check-skill-exists.md)

Create comprehensive session logs documenting session info, protocol compliance checklist, git state, work log with status and context, and session end verification steps

Files:

• .agents/qa/session-808-worktrunk-hook.md

📄 CodeRabbit inference engine (.agents/sessions/2025-12-20-session-01.md)

Document regression risk assessment in QA test reports

Files:

• .agents/qa/session-808-worktrunk-hook.md
• .agents/qa/issue-834-worktrunk-config.md

📄 CodeRabbit inference engine (.agents/critique/001-pr365-remediation-critique.md)

Verify existence of referenced documentation files before updating them in automation procedures

Files:

• .agents/qa/session-808-worktrunk-hook.md
• .agents/qa/issue-834-worktrunk-config.md

📄 CodeRabbit inference engine (.agents/critique/465-spec-validation-false-positive.md)

Require explicit verdict patterns in all AI agent outputs rather than relying on substring keyword matching for verdict detection

Files:

• .agents/qa/session-808-worktrunk-hook.md
• .agents/qa/issue-834-worktrunk-config.md

📄 CodeRabbit inference engine (.agents/sessions/2025-12-29-session-02-autonomous-development.md)

Route feature implementation results to qa agent via .agents/qa/ directory

Files:

• .agents/qa/session-808-worktrunk-hook.md
• .agents/qa/issue-834-worktrunk-config.md

📄 CodeRabbit inference engine (.agents/analysis/pre-commit-qa-investigation-sessions-gap.md)

Session changes and evidence should be tracked within .agents/sessions/*.md files to distinguish session-level documentation from QA reports stored in .agents/qa/*.md files

Files:

• .agents/qa/session-808-worktrunk-hook.md
• .agents/qa/issue-834-worktrunk-config.md

📄 CodeRabbit inference engine (.agents/sessions/2026-01-03-session-01-slashcommandcreator-qa.md)

Ensure all cross-references and relative paths in documentation files are correct and resolve to valid targets

Files:

• .agents/qa/session-808-worktrunk-hook.md
• .agents/qa/issue-834-worktrunk-config.md

📄 CodeRabbit inference engine (.agents/sessions/2026-01-04-session-131-pr754-merge-conflicts.md)

Use auto-resolvable patterns for merge conflict resolution: .agents/*, .claude-mem/*, .claude/commands/*, .claude/skills/*, and security review scripts

Files:

• .agents/qa/session-808-worktrunk-hook.md
• .agents/qa/issue-834-worktrunk-config.md

📄 CodeRabbit inference engine (.agents/SESSION-PROTOCOL.md)

Session end protocol MUST create QA report at .agents/qa/[report].md with validation results before committing feature code

Files:

• .agents/qa/session-808-worktrunk-hook.md
• .agents/qa/issue-834-worktrunk-config.md

📄 CodeRabbit inference engine (.agents/SESSION-PROTOCOL.md)

Session end protocol MUST stage all changed files including .agents/ files before committing

Files:

• .agents/qa/session-808-worktrunk-hook.md
• .agents/qa/issue-834-worktrunk-config.md

⚙️ CodeRabbit configuration file

Agent configuration files. Only flag security issues or broken cross-references. Ignore style, formatting, and structure.

Files:

• .agents/qa/session-808-worktrunk-hook.md
• .agents/qa/issue-834-worktrunk-config.md

📄 CodeRabbit inference engine (.agents/architecture/ADR-001-markdown-linting.md)

**/*.md: Add language identifiers to all fenced code blocks (MD040). Use appropriate language identifiers: csharp for C#, powershell for PowerShell, bash for shell, json for JSON, yaml for YAML, markdown for Markdown, text for plain text or generic/pseudo code
Wrap generic types in backticks to escape angle brackets (e.g., ArrayPool<T> instead of ArrayPool) to comply with MD033 inline HTML restrictions and ensure proper rendering
Add blank lines around code blocks to comply with MD031 markdown linting requirements
Add blank lines around lists to comply with MD032 markdown linting requirements
Add blank lines around headings to comply with MD022 markdown linting requirements
Use ATX-style headings (# Heading) consistently across all markdown documents (MD003)
Use fenced code block style (triple backticks) consistently, with backtick delimiters rather than tildes (MD046, MD048)
Allow only specific HTML elements in markdown: <br>, <kbd>, <sup>, <sub>. Escape or avoid other inline HTML elements to comply with MD033 restrictions

**/*.md: Always specify language identifiers on fenced code blocks for syntax highlighting in markdown documentation
Add blank lines before and after code blocks, lists, and headings in markdown documents
Detect and repair malformed code fence closings where closing fences have language identifiers (e.g., text) instead of plain closing fences ( )

**/*.md: Run markdownlint --fix before manual edits to auto-resolve spacing violations (MD031/MD032/MD022)
Use text for pseudo-code and tool invocations, and use specific language identifiers (json, csharp, bash, yaml, markdown) for actual code in MD040 code blocks
Wrap .NET generic types like ArrayPool<T>, Span<T>, Vector256 in backticks to prevent MD033 inline HTML violations in C# documentation

Use HTML comments with BEGIN/END markers for upgradeable content blocks in markdown files to support append, upgrade, and replace scenarios

**/*.md: Con...

Files:

• AGENTS.md

⚙️ CodeRabbit configuration file

**/*.md: Writing Quality: - Grade 9 reading level - Active voice, direct address - Short sentences (under 15 words ideal) - No fluff, filler, or marketing language - Replace adjectives with data where possible - Every sentence must pass the "so what" test
Flag: - Passive voice - Vague language (nearly, some, almost, very) - Jargon without definitions - Broken links and outdated procedures - Inconsistency with code changes in same PR - Missing context for new features or APIs
Ignore (handled by .markdownlint-cli2.yaml): - Markdown formatting and style - Heading level choices - Link formatting variations - Minor punctuation preferences

Documentation Review Criteria ### P0 (Must Fix) - Absolute paths - Broken internal links ### P1 (Should Fix) - Missing heading hierarchy - Code blocks without language ### Skip - Markdown linting (markdownlint-cli2 handles) Prefix all comments with: [P0], [P1], or [P2]

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/retrospective/phase1-remediation-pr43.md)

Use relative paths only in documentation and configuration files; avoid absolute paths (e.g., C:\ on Windows) to prevent environment contamination and maintain cross-platform portability

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/retrospective/2025-12-17-session-failures.md)

Do not include auto-generated headers in generated files

Run markdown lint on session logs and documentation before committing

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/analysis/002-copilot-cli-limitations-assessment.md)

Document platform-specific limitations prominently in README and installation documentation, particularly regarding context window sizes, configuration architecture, and feature parity differences between Claude Code, VS Code, and Copilot CLI

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/analysis/003-session-protocol-skill-gate.md)

Validate skill availability before implementing GitHub operations - Check if .claude/skills/github/ directory exists and contains the required capability; list available GitHub skill scripts; read the skill-usage-mandatory memory; document available skills in session log; use existing skills if they exist rather than writing inline code

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/retrospective/2025-12-18-serena-memory-reference-migration.md)

Search entire codebase for pattern before migration to identify all references

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/retrospective/2025-12-18-serena-memory-reference-migration.md)

Include fallback clause when migrating to tool calls for graceful degradation

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/retrospective/2025-12-18-session-17-retrospective.md)

For features, add new sections rather than refactoring existing logic

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/sessions/2025-12-18-session-24-component-agents-docs.md)

**/AGENTS.md: Generate AGENTS.md files for each logical component documenting all automated actors (agents) that operate as part of that component
Include Mermaid diagrams (architecture flowcharts and sequence diagrams) in component AGENTS.md files
Document agent/script catalogs using comprehensive tables with attributes in AGENTS.md files
Specify inputs, outputs, and triggers clearly for each agent/script documented in AGENTS.md files
Document error handling scenarios and behaviors in AGENTS.md files
Include security considerations and controls in AGENTS.md files
Document CI workflows and validation mechanisms as monitoring systems in AGENTS.md files
Include cross-references and links between component AGENTS.md files

Document agent deployment model: Agents ship independently without source tree access. Add or update AGENTS.md to explain that agent files are copied to end-user machines (~/.claude/, ~/.copilot/, ~/.vscode/) as standalone units.

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/retrospective/2025-12-19-self-contained-agents.md)

Document agent deployment model and constraints (self-contained units, no source tree access) prominently in project documentation

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/retrospective/2025-12-19-skill-extraction-summary.md)

Use identical syntax for all instances when migrating patterns to maintain consistency

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/pr-batch-review-session-2025-12-20.md)

Use consistent MCP acronym terminology in documentation (Copilot review feedback)

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/qa/semantic-slug-migration-test-strategy.md)

Update all cross-references to skills in AGENTS.md from numeric skill IDs (Skill-Domain-NNN) to semantic slugs

Update AGENTS.md documentation with Visual Studio 2026 installation instructions and usage examples

Add global ADR Review Requirement to ensure all agents are aware that ADR review is mandatory for all ADR operations

AGENTS.md: All agents MUST signal orchestrator with mandatory routing when creating or updating ADR files, not route directly to other agents after ADR operations
ADR review requirement is MANDATORY for all ADR creation and updates, with orchestrator blocking workflow continuation until adr-review skill completes

Update AGENTS.md documentation to describe the new local guardrails workflow and its phases (Foundation, Pre-PR Session Protocol Validation, PR Description Validation, Integration, Test Coverage Detection, Documentation)

AGENTS.md: Update AGENTS.md to support both mcp__serena__* and serena/* tool naming conventions
Document Serena unavailability fallback in AGENTS.md

Update AGENTS.md to reference /session-init skill in Session Protocol or Session Start checklist section to enable user discovery

Skill integration documentation must reference the skill in AGENTS.md protocol sections where it's used

Reference skills in AGENTS.md under appropriate functional sections with documentation paths and usage context

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/qa/002-pr-201-skills-clarity-fixes.md)

Provide concrete examples when documenting MCP tool naming conventions - include breakdown of server name and tool-id components

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/archive/HANDOFF-2025-12-22.md)

Use RFC 2119 keywords (MUST, SHOULD, MAY) in protocol documentation and enforcement mechanisms

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/analysis/156-pr-review-analysis.md)

Fix GitHub Actions template syntax: Use ${{ }} instead of @{{ }} for template variables (e.g., ${{ github.event.pull_request.user.login }})

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/sessions/2025-12-23-session-84-pr308-review-comments.md)

**/*.{sh,bash,md}: Bash script arguments containing special characters (e.g., -f description) must be properly quoted to prevent shell interpretation errors
Bash variables should use lowercase naming conventions to distinguish user variables from shell built-ins
Hardcoded file paths in Bash scripts should use ~ or $HOME variable instead of absolute paths for portability

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/sessions/2025-12-22-session-65-pr-255-learnings.md)

Files longer than 100 lines should include a table of contents

When applying learned strategies in code, cite skills with format: Applying: Skill-[Category]-[Number], Strategy: [description], Expected: [outcomes], then document Result and Skill Validated

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/qa/474-adr-numbering-final-verification.md)

Update all cross-references to ADR files when an ADR is renumbered to ensure consistency across the codebase

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/sessions/2025-12-30-session-103-pr-568-review.md)

PowerShell examples that build GraphQL queries must use GraphQL variables with gh api graphql -f (for string parameters) and -F (for integer/other type parameters) instead of string interpolation to prevent code injection attacks

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/sessions/2025-12-30-session-103-pr-568-review.md)

Avoid direct variable interpolation in GraphQL queries; use GraphQL variable declarations with proper type annotations (e.g., query($owner: String!, $repo: String!, $number: Int!)) and pass variables via CLI flags instead

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/retrospective/2025-12-31-pr-co-mingling-analysis.md)

When using git worktrees for parallel PR work, navigate to the worktree, verify the current branch with git branch --show-current, and only then proceed with changes

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/sessions/2025-12-30-session-100-recommendation-validation.md)

Commit all changes including .serena/memories files before closing the session

Never use alert suppression (lgtm, nosec, etc) until root cause understood and documented

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/sessions/2026-01-03-session-303-pr752-comprehensive-review.md)

**/*.{sh,md}: Document subdirectory limitations and path traversal constraints in import script comments and documentation
Use relative paths instead of hardcoded user paths (e.g., ~) in script configuration and documentation

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/sessions/2026-01-03-session-303-pr752-comprehensive-review.md)

**/*.{md,sh}: Document all paths in project consistently using relative paths like .claude-mem/scripts/ instead of hardcoded user paths
Explain path traversal attack scenarios and CWE-22 implications when documenting path validation features

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/sessions/2026-01-03-session-303-pr752-comprehensive-review.md)

Clarify security-related comments to avoid overstatements; document actual capabilities and limitations of security patterns (e.g., base64 encoding is not encryption)

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/sessions/2026-01-03-session-303-pr752-comprehensive-review.md)

Document query filtering behavior accurately; avoid misleading claims about returning 'all' results when filters are applied

Files:

• AGENTS.md

📄 CodeRabbit inference engine (.agents/memory/episodes/episode-2026-01-03-session-366.json)

Skill frontmatter must include all required fields: Triggers section and Process section at minimum

Files:

• AGENTS.md

📄 CodeRabbit inference engine (AGENTS.md)

**/*.{ps1,psm1,md}: Check for existing skills in .claude/skills/ before writing inline GitHub operations
Use relative paths in all documentation and scripts (not absolute Windows/macOS/Linux paths); use -Path parameters for OS-agnostic file handling in PowerShell

Files:

• AGENTS.md

Learnt from: rjmurillo
Repo: rjmurillo/ai-agents PR: 43
File: templates/agents/qa.shared.md:1-311
Timestamp: 2025-12-16T06:26:21.783Z
Learning: In the rjmurillo/ai-agents repository, follow the project's Markdown lint rules defined in .markdownlint-cli2.yaml. Do not flag MD031/MD032 (blank lines around fences) or similar style issues in Markdown files if the repository's markdownlint configuration passes; rely on the config to determine formatting and style decisions.

Applied to files:

• AGENTS.md

Learnt from: rjmurillo
Repo: rjmurillo/ai-agents PR: 43
File: templates/agents/implementer.shared.md:33-40
Timestamp: 2025-12-16T06:26:44.230Z
Learning: In the rjmurillo/ai-agents repository, markdownlint issues should be governed by the repository's .markdownlint-cli2.yaml configuration. Do not flag or enforce markdown formatting/style violations that are not surfaced by the configured rules. Apply this rule to all Markdown files (e.g., templates/agents/implementer.shared.md and others) and only flag issues that the project's markdownlint config would detect.

Applied to files:

• AGENTS.md

Learnt from: rjmurillo
Repo: rjmurillo/ai-agents PR: 43
File: templates/agents/planner.shared.md:73-121
Timestamp: 2025-12-16T06:26:44.208Z
Learning: In this repository (rjmurillo/ai-agents), do not flag Markdown formatting or style issues (MD031, MD032, heading levels, link formatting, punctuation) for Markdown files. These are already ignored by the project’s .markdownlint-cli2.yaml; rely on that configuration and the repository's coding guidelines for Markdown handling.

Applied to files:

• AGENTS.md

Learnt from: rjmurillo
Repo: rjmurillo/ai-agents PR: 43
File: src/copilot-cli/analyst.agent.md:39-44
Timestamp: 2025-12-16T06:27:04.317Z
Learning: In the rjmurillo/ai-agents repository, do not flag MD031 (blank lines around fenced code blocks) or MD032 (blank lines around lists) violations in Markdown files. These formatting rules are configured in the project’s .markdownlint-cli2.yaml, and such style issues do not affect agent instruction functionality. Apply this pattern to all Markdown files (recursively) and focus review attention on issues that affect behavior, correctness, or other lint rules.

Applied to files:

• AGENTS.md

Learnt from: rjmurillo
Repo: rjmurillo/ai-agents PR: 43
File: templates/agents/roadmap.shared.md:124-174
Timestamp: 2025-12-16T08:00:20.752Z
Learning: Review Markdown files to ensure nested code fences follow the rule: the outer fence uses more backticks than the inner fence (e.g., an outer `````` with four backticks containing an inner ```mermaid``` fence). This follows CommonMark conventions; verify that nesting does not break rendering by using a greater number of backticks for the outer fence than the inner one.

Applied to files:

• AGENTS.md