MCP server for AI coding agents — persistent engineering memory, knowledge compounding, and spec-driven development workflows. Part of TRW Framework.
Skill Claude CodeCodex
Adversarial spec-vs-code audit. Verifies implementation against PRD acceptance criteria, runs mandatory NFR checklist, assesses test quality. Independent from the implementer to break confirmation bias. Use: /trw-audit PRD-CORE-055.
Skill Claude CodeCodex
Load the full TRW ceremony reference: tool lifecycle table, execution phases, and example flows. Use when you need to know which tool to call and when. Invoke: /trw-ceremony-guide.
Skill Claude CodeCodex
Concurrency-safe conventional commit with scoped staging, cached-diff review, repository-native branch policy, and optional PRD/run provenance. Use only when the user explicitly asks Codex to commit current work; never auto-trigger.
Skill Claude CodeCodex
Dispatch an isolated, read-only second-opinion review to another coding-agent CLI. Use an explicit client or model when provider diversity matters; defaults may select the same client as the host.
Skill Claude CodeCodex
Persist the session's work with validation evidence, durable learnings, and client instruction sync. Use: /trw-deliver.
Skill Claude CodeCodex
Scan files for duplicated code blocks and classify consolidation candidates. Read-only analysis — reports evidence without modifying code. Use: /trw-dry-check [file-patterns...].
Skill Claude CodeCodex
Convert an approved PRD into a repository-grounded execution plan with behavior-sized tasks, verified paths/interfaces, proof, dependencies, ownership, migration concerns, and exact project-native verification. Internal phase used by trw-prd-ready and trw-prd-new.
Skill Claude CodeCodex
File a TRW bug, install issue, feature request, feedback note, or question through the authenticated POST /v1/submissions channel. Prompts for the category and a one-line summary, optionally attaches recent learnings + the last error trace, and returns a submissionid the operator can quote on follow-up. Use…
Skill Claude CodeCodex
Check TRW framework compliance. Reports ceremony adherence, phase gate status, and active run health. Use when unsure if framework obligations are being met. Use: /trw-framework-check.
Skill Claude CodeCodex
Record, update, or retire durable learnings. Use when the user asks for learning management or a workflow explicitly surfaces a non-obvious reusable discovery; never use for routine status. Invoke: /trw-learn ["summary" | resolve L-id | obsolete L-id].
Skill Claude CodeCodex
Audit learning memory health. Shows tag distribution, impact spread, staleness, duplicate candidates, and recommendations. Read-only. Use: /trw-memory-audit.
Skill Claude CodeCodex
Optimize learning memory. Prunes stale entries, consolidates duplicates, rebalances tags. Interactive — confirms before deleting. Use: /trw-memory-optimize.
Skill Claude CodeCodex
Internal phase: Groom a PRD to sprint-ready quality. Researches codebase, drafts missing sections, iterates until validation passes. Called automatically by /trw-prd-ready and /trw-prd-new. Not intended for direct user invocation.
Skill Claude CodeCodex
Create a new PRD from a feature description, then automatically run the full readiness pipeline (groom → review → execution plan) so the user gets a sprint-ready PRD with micro-tasks in one command. Use: /trw-prd-new "Add rate limiting to the API".
Skill Claude CodeCodex
Full PRD lifecycle in one command: create (or pick up existing) → groom → review → refine → execution plan. Accepts a feature description ("Add rate limiting") or a PRD ID (PRD-CORE-020). Use: /trw-prd-ready "Add rate limiting to the API" or /trw-prd-ready PRD-CORE-020.
Skill Claude CodeCodex
Internal phase: Review a PRD for quality, returning a structured READY/NEEDS WORK/BLOCK verdict with per-dimension scores. Read-only — never modifies files. Called automatically by /trw-prd-ready and /trw-prd-new. Not intended for direct user invocation.
Skill Claude CodeCodex
Audit TRW health in the current or target project. Summarizes tool usage, ceremony compliance, hook enforcement, active runs, learnings, and issues. Use: /trw-project-health [path].
Skill Claude CodeCodex
End-of-session reflection: examine the session's actual signals (events, diffs, build results, corrections), identify process/organization/tooling/agent improvement opportunities, get approval, then route each one to implementation (inline quick-fix, PRD pipeline, learning, or backlog) with a follow-through ledger.…
Skill Claude CodeCodex
OWASP-focused, language-aware security audit of a target repository. Checks command injection, unsafe deserialization, path traversal, secrets, dependency risk, and input validation. Read-only. Use: /trw-security-check [module or 'all'].
Skill Claude CodeCodex
Complete a sprint. Validates deliverables, runs build gate, validates PRD lifecycle, archives sprint doc, runs delivery ceremony. Use only when the user explicitly requests sprint completion: /trw-sprint-finish. Never auto-trigger.
Skill Claude CodeCodex
Initialize a new sprint. Lists draft PRDs, creates sprint doc, bootstraps run directory, sets up tracking. Use: /trw-sprint-init "Sprint 16: Skills Architecture".
Skill Claude CodeCodex
Plan sprint-scale coordination from a sprint document. Produces a simple file-ownership and helper-assignment plan that works with any client or harness; does not assume beta peer-team features. Use: /trw-sprint-team [sprint-doc-path].
Skill Claude CodeCodex
Generate portable coordination playbooks with file ownership and interface contracts for sprint workstreams. Works for local sequential work, human handoff, or any client-supported helper. Use: /trw-team-playbook [sprint-doc-path].
Skill Claude CodeCodex
Audit test coverage and strategy. Identifies untested modules, coverage gaps, and suggests test improvements. Use before or during IMPLEMENT phase. Use: /trw-test-strategy [module or 'all'].
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: