jason21wc

jason21wc/ai-governance-mcp

Agent Claude Code

Fresh-context code review specialist. Invoke after writing or modifying code to get independent quality assessment against explicit criteria.

jason21wc/ai-governance-mcp

Agent Claude Code

Documentation drift detector. Systematically checks documents for staleness, cross-file contradictions, and volatile metric accuracy per meta-methods Part 4.3.

jason21wc/ai-governance-mcp

Agent Claude Code

Narrative consistency verifier. Checks Story Bible against manuscript for character drift, timeline conflicts, world rule violations, and knowledge-state errors.

jason21wc/ai-governance-mcp

Agent Claude Code

Devil's advocate for high-stakes decisions. Challenges assumptions, surfaces blind spots, and identifies overlooked risks before commitment.

jason21wc/ai-governance-mcp

Agent Claude Code

Documentation specialist for README files, docstrings, and technical writing. Invoke when documentation needs creation or updates.

jason21wc/ai-governance-mcp

Agent Claude Code

Governance-first coordinator. Ensures evaluategovernance() is called before any action unless it is a read-only operation, non-sensitive question, or trivial formatting change.

jason21wc/ai-governance-mcp

Agent Claude Code

Security-focused code auditor specializing in vulnerability detection. Invoke for security reviews, especially before releases or when handling sensitive data/auth.

jason21wc/ai-governance-mcp

Agent Claude Code

Test creation specialist focused on coverage and behavior validation. Invoke when you need tests written for existing code or new functionality.

jason21wc/ai-governance-mcp

Agent Claude Code

Criteria-based quality validator for any artifact. Fresh context, explicit checklist, artifact-agnostic.

jason21wc/ai-governance-mcp

Agent Claude Code

Character voice analyst. Compares dialogue against Character Voice Profiles to detect voice convergence, undifferentiated speech patterns, and drift from established character voices.

jason21wc/ai-governance-mcp

Instructions file CodexOpenCode

AGENTS.md instructions for jason21wc/ai-governance-mcp, covering ai governance mcp server, memory files, on session start, disposition (applies to every session) and key commands.

jason21wc/ai-governance-mcp

Instructions file

Claude Code instructions for jason21wc/ai-governance-mcp, covering ai governance mcp server, disposition — reasoning posture, governance — enforced by hook and reference library.

jason21wc/ai-governance-mcp

Skill Claude CodeCodex

Fleet-level close-out check across every worktree and branch — is all work committed, durable on a remote, landed in the default branch, and are the finished worktrees removed? Read-only; it prints commands and never runs them. Invoke when the user says "all clear", "are we clear", "close everything out", "session…

jason21wc/ai-governance-mcp

Skill Claude CodeCodex

Assess a codebase or module's structural organization and health. Maps entry points, module responsibilities, dependency directions, and layering patterns, then evaluates coupling hotspots, cohesion gaps, and growth capacity. Invoke when the user says "architecture review", "architecture overview", "assess the…

jason21wc/ai-governance-mcp

Skill Claude CodeCodex

Run a multi-pass code review on staged changes, a branch diff, or specific files. Dispatches three specialized reviewers (correctness, security, architecture) in parallel, then reconciles findings into a severity-gated report. Invoke when the user says "code review", "review my code", "review this PR", "review these…

jason21wc/ai-governance-mcp

Skill Claude CodeCodex

Run post-change validation and finish a branch safely, including concurrent worktree refresh, optimistic fast-forward publication, retry, checkpoint, PR, or discard paths. Use after changes and before pushing, merging, handing off, or cleaning up a worktree.

jason21wc/ai-governance-mcp

Skill Claude CodeCodex

Transform raw content (transcripts, articles, lectures, informal posts) into enhanced reference documents — removes noise, restructures for clarity, fills knowledge gaps with researched best practices, preserves the author's voice. Invoke when the user provides source content to enhance, clean up, or transform into a…

jason21wc/ai-governance-mcp

Skill Claude CodeCodex

Generate or update documentation for a target file, module, API, or project. Works in three phases — classify and generate a draft, verify every claim against actual code using tool-assisted verification (grep/read as oracle), and revise any failures. Auto-detects doc frameworks. Invoke when the user says "generate…

jason21wc/ai-governance-mcp

Skill Claude CodeCodex

Run DOE calibration chunks for model/effort routing (BACKLOG.

jason21wc/ai-governance-mcp

Skill Claude CodeCodex

Mine completed session transcripts for unpersisted decisions, lessons, and context. Enriches and fact-checks memory files with HITL review. Use between sessions or when memory files feel stale relative to recent work. Triggers: "dream", "mine transcripts", "memory enrichment", "harvest sessions", "what did we miss".…

jason21wc/ai-governance-mcp

Skill Claude CodeCodex

Build an eval suite for a probabilistic / LLM-powered feature whose output has no single correct answer (generation, extraction, estimation, summarization, classification over natural-language input). Defines golden cases across three categories (control / edge / capability-limit), a scored rubric with deterministic…

jason21wc/ai-governance-mcp

Skill Claude CodeCodex

Scan the current session for unpersisted decisions, constraints, and lessons, then propose memory file updates. Use when you want to capture what was discussed but not yet written to memory files. Triggers: "journal", "capture memory", "update memory", "what did we discuss", "persist session state". Does NOT activate…

jason21wc/ai-governance-mcp

Skill Claude CodeCodex

Subagent model and effort routing table. Use when dispatching subagents via the Agent tool or Workflow scripts to select the right model and effort level. Triggers: "route this subagent", "which model for", "model routing", "effort level", "subagent model". Does NOT apply to: session model selection (that's /model)…

jason21wc/ai-governance-mcp

Skill Claude CodeCodex

Apply the Purpose-Method-Outcomes (PMO) lens to a project that turns inputs into outputs — either BUILD a project's PMO charter (who it serves, the mechanisms that deliver value, the artifacts + how you verify the purpose was actually delivered) or REVIEW an existing project against that lens (trace…