By govctl-org
Enforce governed development workflows with ADR/RFC creation, review agents, compliance audits, and git-integrated work item tracking via the govctl CLI.
Review ADR drafts for quality, completeness, and decision clarity. Use proactively after drafting or editing ADRs.
Verify code conforms to normative RFC clauses and ADR decisions. Use proactively after implementation, during code review, or before advancing RFC-governed work to stable.
Review RFC drafts for quality, completeness, and normative language correctness. Use proactively after drafting or editing RFCs.
Review work items for quality, completeness, and actionable acceptance criteria. Use proactively after creating or updating work items.
Write effective Architecture Decision Records. Use when: (1) Creating a new ADR, (2) Recording a design decision, (3) User mentions ADR, decision, trade-off, or alternatives
Commit changes with govctl integration — check work item status, update journal or notes, and run govctl check
Stress-test a design decision with premortem/backcast analysis, then produce a risk-calibrated recommendation that maps to ADR fields. Use when: (1) Multiple competing architecture options, (2) Irreversible or high-risk design choices, (3) /discuss identifies a complex trade-off
Facilitate design discussion — research context, clarify requirements, draft RFC/ADR
Execute governed implementation workflow with work items, RFC/ADR checks, phase gates, testing, and closure. Use when: (1) User invokes /gov, (2) A non-trivial change needs work item tracking, (3) Implementation may require RFC/ADR handling
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Governance-as-code for AI-assisted software development.
Enforce spec-first discipline. Every feature starts with an RFC, not a prompt.
AI-assisted coding is powerful but undisciplined:
The result: faster typing, slower thinking, unmaintainable systems.
Day 1: "Let's add caching!"
Day 2: AI generates 500 lines of Redis integration
Day 7: "Wait, did we agree on Redis or Memcached?"
Day 14: Half the team implements one, half the other
Day 30: Two incompatible caching layers, no spec, nobody knows why
Day 1: govctl rfc new "Caching Strategy"
Day 2: RFC-0015 defines: Redis, TTL policy, invalidation rules
Day 3: govctl rfc advance RFC-0015 impl
Day 7: Implementation complete, traceable to spec
Day 14: Tests pass, govctl rfc advance RFC-0015 stable
govctl enforces phase discipline on software development:
┌─────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐
│ SPEC │ ──► │ IMPL │ ──► │ TEST │ ──► │ STABLE │
└─────────┘ └──────────┘ └──────────┘ └──────────┘
│ │ │ │
▼ ▼ ▼ ▼
RFC must Code must Tests must Bug fixes
be normative match spec pass gates only
Three artifact types, one lifecycle:
All artifacts are TOML files in gov/, validated by JSON schemas, and rendered to markdown in docs/. govctl governs itself by its own rules -- this repository is the first proof.
/plugin marketplace add govctl-org/govctl
/plugin install govctl@govctl
/govctl:init
The plugin provides workflow skills, reviewer agents, and enforcement hooks out of the box.
cargo install govctl
govctl init
govctl init creates the governance structure and installs AI agent skills into .claude/.
For complete documentation, see the User Guide.
govctl is built for AI-native development. Install the Claude Code plugin or run govctl init to get workflow skills that any Claude Code / Cursor / Codex agent can invoke:
| Skill | Purpose |
|---|---|
/gov <task> | Complete governed workflow: work item, RFC/ADR, implement, test, done |
/migrate | Adopt govctl in an existing project: discover decisions, backfill ADRs, annotate source |
/discuss <topic> | Design discussion: explore options, draft RFC or ADR |
/commit | Smart commit: VCS detection, govctl checks, work item journal updates |
/quick <task> | Fast path for trivial changes (skip governance ceremony) |
/guard-writer | Create and edit verification guards |
The plugin also includes enforcement hooks: govctl status runs at session start for context, govctl check runs at session end as a gate.
Every govctl operation is a single CLI call. No MCP server needed -- the CLI is the universal interface. Every shell-capable agent already speaks it.
npx claudepluginhub govctl-org/govctl --plugin govctlComplete project development toolkit: 23 agents, 23 slash commands, 29 lifecycle hooks, and 69 reusable skills for Claude Code workflows
Graph-first governance workflow guard for Aming Claw. Bundles the core governance skill, launcher skill, Project Inbox capture skill, HN challenge/demo skills, everyday AI coding demo skills, and the project MCP server (.mcp.json) so Claude Code sessions start with backlog/MF discipline, core runtime checks, and dashboard governance context.
AI-SDLC governance framework for Claude Code — action enforcement, telemetry, quality gates, and review agents
Harness engineering for Claude Code — hook-enforced dual review, state-machine gates, and fail-closed safety where it counts.
Implementation planning, execution, and PR creation workflows with multi-agent collaboration
Corca Workflow Framework — consolidated hooks and skill orchestration for structured development sessions