claude

mz-gov

Development governance pipeline — generates, discusses, enforces, and reviews ADRs, RFCs/RFDs, design docs, and AI-decision provenance, gated by a human sign-off

3 on GitHubby Stanislav Gonorovskiiv0.57.0MITupdated 4 days agodevelopment
/

Plugin mz-gov from marketplace mozg-pipelines in DoctorMozg/claude-pipelines. Commands read from the repo's manifest — 4 days ago.

What it installs

Skills (3)

  • gov-init

    Installs, updates or removes the governance policy in CLAUDE.md. Use when the user wants governance set up ("gov init", "install governance policy", "set up governance"). Not for running a decision (use govern) or auditing records (use gov-review).

  • gov-review

    Audits ADRs, RFDs and design docs into a read-only findings report. Use when the user wants existing decision records checked ("review our ADRs", "audit decision records", "check governance docs"). Not for reviewing code changes (use review-branch).

  • govern

    Runs a substantial design decision through review and sign-off into an ADR, RFD or design doc. Use when the user wants a choice made and recorded ("should I X or Y", "ADR for X", "decide between A and B"). Not for auditing records (use gov-review).

Subagents (10)

  • gov-artifact-writer

    Pipeline-only, dispatched by the mz-gov govern skill during its record phase, after human sign-off. Writes the approved decision as a durable, sequentially-numbered artifact under docs/decisions, docs/rfcs, or docs/design, embeds the AI-provenance fence in the header, and initializes its status from

  • gov-audit-reviewer

    Pipeline-only, dispatched by the mz-gov gov-review skill. Scores one existing governance artifact (ADR, RFD, or design doc) against the six-axis review rubric — missing alternatives, unstated assumptions, reversibility, blast radius, considered-options completeness, and status/provenance hygiene — a

  • gov-critic-alternatives

    Pipeline-only. Dispatched by /govern. Considered-options critic for the governance discuss phase. Reviews a draft ADR/RFD/design-doc for whether the option space is complete, whether at least two real alternatives carry honest trade-offs, and whether the chosen option is actually best rather than me

  • gov-critic-assumptions

    Pipeline-only. Dispatched by /govern. Unstated-assumptions critic for the governance discuss phase. Reviews a draft ADR/RFD/design-doc for the premises it silently rests on — what must be true for the decision to work, whether those premises are stated and warranted, and what the failure mode is if

  • gov-critic-blast-radius

    Pipeline-only. Dispatched by /govern. Blast-radius critic for the governance discuss phase. Reviews a draft ADR/RFD/design-doc for downstream impact — what breaks, who and what depends on the thing being changed, and whether the artifact states its own blast radius instead of leaving it for the read

  • gov-critic-quick

    Pipeline-only. Dispatched by /govern. Light-path consolidated governance critic for simple ADRs. Reviews a draft decision artifact across all four governance lenses — alternatives, reversibility, blast radius, and assumptions — in a single pass, and its output is the final verdict with no separate s

  • gov-critic-reversibility

    Pipeline-only. Dispatched by /govern. One-way-door critic for the governance discuss phase. Reviews a draft ADR/RFD/design-doc to classify the decision as reversible (two-way door) or irreversible (one-way door), and checks that any irreversibility is justified and met with a proportionally high dec

  • gov-discussion-synthesizer

    Pipeline-only, dispatched by the mz-gov govern skill after the heavy critic panel runs. Merges the four governance critics (reversibility, alternatives, blast-radius, assumptions) from one discuss iteration into discussion_<N>.md with a single aggregate verdict, resolving conflicts by lane ownership

  • gov-provenance-recorder

    Pipeline-only, dispatched by the mz-gov govern skill. Formats the AI-decision provenance (AgDR) block for the current run and writes it to the task's provenance.md, recording the authoring agent, model, timestamp, and trigger, with the human sign-off left pending until a human approves. Do not dispa

  • gov-router

    Pipeline-only, dispatched by the mz-gov govern skill. Decides whether a proposed change needs a governance artifact and which one, by running the two-gate artifact-selection algorithm and emitting a routing decision (none | adr | rfd | design) plus a light/heavy weight label. Do not dispatch standal

View source on GitHub sgon.ai

More from DoctorMozg/claude-pipelines

All 14 plugins →

Multi-perspective AI panels and creative writing tools — brainstorming, Delphi-style expert consultation, technical documentation, AI-text naturalization, and copywriting

5 skills · 22 agents

3

Personal Obsidian knowledge base skills and agents — vault bootstrap (init), vault maintenance, note processing, multimodal capture (voice/image/PDF/YouTube), vault triage, research ingestion, schema validation, safe refactoring, epistemic provenance, grounded Q&A, review, link suggestions, and Obsidian syntax reference

15 skills · 11 agents · hooks

3

Business outreach intelligence — /outreach-brief captures the outreach brief via an iterative clarification loop then researches local industry climate (economic, regulatory, deals, pain points) per target market, feeding the other skills via a `brief:` arg; /outreach-research runs the full company-discovery pipeline (sources, scout, reputation, enrichment, scoring, dossiers, output in `.mz/outreach/<run>/companies/`); /outreach-enrich-company fans out 5 specialist subagents to deepen the card beyond the base research and then drafts naturalized LinkedIn/email letters into it; /outreach-update-card logs a dated interaction entry. Both writer skills relocate the card to `.mz/outreach/active/<YYYY-MM-DD>_<slug>.md` with the last interaction date as prefix

4 skills · 14 agents

3

Full development pipeline — autonomous coding, reviewing, testing, and research agents with orchestrating skills

5 skills · 13 agents

3

Job and freelance hunt intelligence — /job-search and /freelance-search run full CV-to-listings pipelines for salaried roles and freelance gigs; /job-recruiter-info does one-shot recruiter discovery; /freelance-pitch drafts a grounded proposal for one gig (≤350 words, milestones/pricing cited verbatim from the gig)

4 skills · 12 agents

3

Git workflow review pipelines — branch-level deep review with multi-lens fan-out (bugs, security, architecture, performance, maintainability, over-engineering), GitHub PR review, and daily PR triage

3 skills · 11 agents

3

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

Maintain mz-gov?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins14 plugins