📄 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/planning/security-agent-detection-gaps-remediation.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/planning/security-agent-detection-gaps-remediation.md

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

Create CI validation checks to extract and compare effort estimates across related planning documents (epics, PRDs, tasks, memory) and flag discrepancies exceeding 20%

Maintain planning artifacts for all work phases in .agents/planning/ to enable upfront scope completeness validation and gap detection

.agents/planning/**/*.md: Effort estimates for remediation phases must be consistent throughout planning documents (all mentions of Phase 1 must show same duration estimate); include analyst gap findings and test verification effort in calculations
Provide a comprehensive rollback plan that includes: trigger conditions, 5-step rollback procedure with git commands, root cause analysis commands, git revert strategy with verification, and both recovery scenarios (fixable vs. unrecoverable), plus a testing gate requiring 3 mandatory tests before re-attempt
All acceptance criteria in implementation plans must be measurable and testable with clear blocking requirements marked with warning symbols (⚠️) to indicate mandatory completion conditions

Document all acceptance criteria in markdown format with checklist format ([ ] unchecked, [x] checked) for milestone completion validation

.agents/planning/**/*.md: Standardize task prompts with absolute file paths, search patterns, action specifications, complete code blocks (no placeholders), and verification steps
Organize task dependencies by phase structure (Core → Detection → Synthesis → Dedup → Tests → Docs) to clarify execution order
Avoid location references using relative positioning (e.g., 'after Task X') in task prompts; use absolute file paths and search patterns instead
Include code blocks and concrete examples in task prompts instead of placeholders to reduce implementer ambiguity

.agents/planning/**/*.md: Documentation for agent specifications and planning must be written at a Grade 9 reading level without unexplained jargon, ensuring junior developers can understand requirements without additional questions...

Files:

• .agents/planning/security-agent-detection-gaps-remediation.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/planning/security-agent-detection-gaps-remediation.md

📄 CodeRabbit inference engine (.agents/sessions/2025-12-20-session-46-skills-index-prd.md)

Run markdown linting with --fix flag on all planning artifacts before committing

Files:

• .agents/planning/security-agent-detection-gaps-remediation.md

📄 CodeRabbit inference engine (.agents/architecture/ADR-004-pre-commit-hook-architecture.md)

Validate cross-document consistency and scope alignment for planning artifacts in the .agents/planning/ directory during pre-commit

Planning artifact files must maintain cross-document consistency with effort estimates and condition traceability across all related planning documents.

Planning documents (PRDs and task breakdowns) must be validated for effort estimate divergence, orphan specialist conditions, and missing task coverage

Files:

• .agents/planning/security-agent-detection-gaps-remediation.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/planning/security-agent-detection-gaps-remediation.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/planning/security-agent-detection-gaps-remediation.md

📄 CodeRabbit inference engine (.agents/governance/historical-reference-protocol.md)

When referencing historical items checked into source control in planning documents, documentation MUST include: Date in YYYY-MM-DD format, Git Commit SHA (full or short), and GitHub Issue number if applicable in #NNN format with date

Files:

• .agents/planning/security-agent-detection-gaps-remediation.md

📄 CodeRabbit inference engine (.agents/planning/historical-reference-compliance-plan.md)

{.agents/architecture/**/*.md,.agents/sessions/**/*.md,.serena/memories/**/*.md,.agents/analysis/**/*.md,.agents/planning/**/*.md,.agents/retrospective/**/*.md}: All historical references in documentation must include a date in YYYY-MM-DD format
All Git commit SHA references must include the commit date in (YYYY-MM-DD) format
All GitHub Issue references must include the issue number and date in #NNN (YYYY-MM-DD) format when applicable
All GitHub PR references SHOULD include the PR number and date in PR #NNN (YYYY-MM-DD) format when applicable
Avoid vague historical references such as 'was done previously', 'See ADR-XXX for details', 'The original implementation', 'As decided in the issue', or 'Per our previous discussion' without explicit commit SHA, date, or issue number references

Files:

• .agents/planning/security-agent-detection-gaps-remediation.md

📄 CodeRabbit inference engine (.agents/sessions/2026-01-01-session-123-historical-reference-compliance.md)

All external artifact references (PRs, issues, commits) in documentation must include dates in the format 'reference_identifier (YYYY-MM-DD)' to comply with the historical reference protocol

Files:

• .agents/planning/security-agent-detection-gaps-remediation.md

📄 CodeRabbit inference engine (.agents/sessions/2026-01-01-session-123-historical-reference-compliance.md)

Avoid vague historical references such as 'was done previously', 'original implementation', 'as decided in the issue', or 'per our previous discussion' without specific commit SHAs, PR numbers (with dates), or issue numbers (with dates)

Files:

• .agents/planning/security-agent-detection-gaps-remediation.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/planning/security-agent-detection-gaps-remediation.md

⚙️ CodeRabbit configuration file

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

Files:

• .agents/planning/security-agent-detection-gaps-remediation.md

Learnt from: CR
Repo: rjmurillo/ai-agents PR: 0
File: .agents/planning/security-agent-detection-gaps-remediation.md:0-0
Timestamp: 2026-01-05T02:00:57.558Z
Learning: Applies to src/claude/security.md : Expand CWE detection in security.md from 3 CWEs (CWE-78, CWE-79, CWE-89) to 30+ high-priority CWEs organized by CWE-699 Software Development View categories (Injection, Authentication, Authorization, Cryptography, Input Validation, Resource Management, Error Handling, API Abuse, Race Conditions, Code Quality). Each CWE must include category label, 1-sentence description, and OWASP Top 10:2021 mapping where applicable. Add OWASP Agentic Top 10 patterns (ASI01-ASI10) mapped to corresponding CWEs.

Applied to files:

• .agents/planning/security-agent-detection-gaps-remediation.md

Learnt from: CR
Repo: rjmurillo/ai-agents PR: 0
File: .agents/planning/security-agent-detection-gaps-remediation.md:0-0
Timestamp: 2026-01-05T02:00:57.558Z
Learning: Applies to src/claude/security.md : Maintain comprehensive CWE-699 Software Development View framework integration in src/claude/security.md organized by 11 weakness categories (Injection/Code Execution, Authentication/Session Management, Authorization/Access Control, Cryptography, Input Validation/Representation, Resource Management, Error Handling/Logging, API/Function Abuse, Race Conditions/Concurrency, Code Quality/Maintainability, plus variant/related CWEs). Each CWE category must include parent-child hierarchy relationships (e.g., CWE-99 Resource Injection → CWE-73 External Control → CWE-22 Path Traversal → CWE-23/36 variants) with one-sentence description per CWE and OWASP Top 10:2021 mapping. Ensure CWE-22 (Path Traversal) and CWE-77 (Command Injection) from PR #752 failures are explicitly prominent.

Applied to files:

• .agents/planning/security-agent-detection-gaps-remediation.md

Learnt from: rjmurillo-bot
Repo: rjmurillo/ai-agents PR: 53
File: .agents/planning/PRD-visual-studio-install-support.md:1-6
Timestamp: 2025-12-21T20:40:22.359Z
Learning: In the .agents/planning/ directory, PRD markdown files must use the lowercase 'prd-' prefix (e.g., prd-visual-studio-install-support.md, prd-agent-consolidation.md, prd-pre-pr-security-gate.md). Uppercase 'PRD-' is a legacy convention and should be renamed to 'prd-'.

Applied to files:

• .agents/planning/security-agent-detection-gaps-remediation.md