claude

clavain

Self-improving agent rig — codifies product and engineering discipline into composable workflows from brainstorm to ship. Compounds knowledge, generates domain agents, and monitors its own docs. Orchestrates Claude, Codex, and GPT-5.2 Pro through 4 agents, 54 commands, 16 skills, 1 MCP servers. Companions: interphase, interline, interflux, interpath, interwatch, interslack, interform, intercraft, interdev, interpeer, intertest.

1 on GitHubby mistakeknotv0.6.332MITupdated 9 days ago
/

Plugin clavain from marketplace interagency-marketplace in mistakeknot/interagency-marketplace. Commands read from the repo's manifest — 9 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (28)

  • bug-reproduction-validator

    Reproduce and validate a bug report to confirm whether the reported behavior is an actual bug.

  • code-review-discipline

    Request code review, and assess received feedback from people, PR comments, or agent and cross-lab reviewers; verify findings before implementing and preserve required review gates.

  • codex-delegate
  • data-migration-expert
  • dispatching-parallel-agents
  • engineering-docs
  • executing-plans
  • file-todos
  • full-stop
  • galiana
  • gardener
  • interop-with-gsd
  • interop-with-superpowers
  • interserve-engine
  • landing-a-change
  • lane
  • plan-reviewer
  • pr-comment-resolver
  • project-onboard
  • refactor-safely
  • remontoire
  • ship
  • subagent-driven-development
  • ui-polish
  • upstream-sync-engine
  • using-clavain
  • using-tmux-for-interactive-commands
  • writing-plans

Slash commands (65)

  • /clavain:bead-sweep

    Scan open beads for stale trackers already implemented — deterministic checks then LLM verification.

  • /clavain:blast-radius

    Find what a change could break somewhere else before it ships, and prove the one fact it is safe because of by running real code

  • /clavain:brainstorm

    Collaborative brainstorm — assess clarity, research repo, explore approaches, capture design. Auto-handoff to /write-plan.

  • /clavain:campaign

    Orchestrate epic execution — read children, topo-sort by dependencies, dispatch phases sequentially with parallel features

  • /clavain:changelog

    Create engaging changelogs for recent merges to main branch

  • /clavain:clavain-doctor

    Quick health check — verifies MCP servers, external tools, beads, and plugin configuration without making changes

  • /clavain:clavain-help

    Show Clavain commands organized by daily drivers first, then by workflow stage

  • /clavain:clavain-init

    Scaffold .clavain/ agent memory directory in the current project

  • /clavain:clavain-review

    Perform exhaustive code reviews using multi-agent analysis and deep inspection

  • /clavain:clavain-status

    Unified status view across Clavain, artifact generation, doc drift, and coordination

  • /clavain:clodex-toggle

    Toggle interserve execution mode

  • /clavain:codex-bootstrap

    Bootstrap or check Clavain Codex installation health (install + wrapper sync + doctor)

  • /clavain:compound

    Document a recently solved problem to compound your team's knowledge

  • /clavain:correct

    Find the mistakes agents keep repeating in this repo and make each one impossible, at the highest level that works

  • /clavain:create-agent-skill

    Create or edit Claude Code skills with expert guidance on structure and best practices

  • /clavain:debate

    Run a structured Claude↔Codex debate before implementing a complex task

  • /clavain:deepen

    Rewrite an ask as a deeper version, not a bigger one: name the top practitioner's method, the rawest source, the real instruments and the external evidence that would prove the result

  • /clavain:describe-pr

    Generate PR title and description from current branch commits

  • /clavain:distill

    Synthesize accumulated docs into categorized solutions and generate missing SKILL-compact.md files

  • /clavain:execute-plan

    Slash-command entry that enforces the pre-execution gate, records the phase transition, then runs a written plan via the executing-plans skill. Use the executing-plans skill directly when no gate or phase tracking is wanted.

  • /clavain:fixbuild

    Run build, capture error, fix it, re-run — fast loop for type errors and build failures without heavyweight debugging

  • /clavain:freeze

    Restrict file edits to declared paths — scope-lock for parallel-session safety

  • /clavain:galiana

    Discipline analytics — view KPIs, report defects, or reset cache

  • /clavain:generate-command

    Create a new custom slash command following conventions and best practices

  • /clavain:goal-form

    Collaborative goal-formation ritual: research-first inter-elicitation → charter → stakes-routed review → mint (ic goal) → /goal handoff

  • /clavain:grill-me

    Interview the user relentlessly about a plan or design until every branch of the decision tree is settled

  • /clavain:handoff

    Generate a concise session handoff summary as a dated markdown file, grounded in intercore run state

  • /clavain:heal-skill

    Fix incorrect SKILL.md files when a skill has wrong instructions or outdated API references

  • /clavain:interserve

    Run Codex-first execution flow for larger scope work

  • /clavain:land

    Run the landing workflow for trunk-based handoff

  • /clavain:migration-safety

    Slash-command entry that fans out three parallel agents for a full pre-deploy safety assessment of a DB migration or data change. For a single-reviewer validation of migration code against production data, use the data-migration-expert skill instead.

  • /clavain:model-routing

    Toggle subagent model routing between economy (smart defaults) and quality (all opus) mode

  • /clavain:next-goal

    Generate a Next-goal block (2-4 leverage-ranked candidates + recommendation + ready-to-paste /goal text) — invoke manually after a /goal completes or whenever you want a fresh set of candidates

  • /clavain:peers

    Read-only viewer for detected peer agent rigs (superpowers, GSD, compound-engineering). Lists detection state and recommended bridge skills. Never makes changes.

  • /clavain:plan-review

    Have multiple specialized agents review a plan in parallel

  • /clavain:pr-triage

    Triage all open PRs — batch by theme, review with parallel agents, generate report, walk through decisions. With a PR reference, run one follow-up pass on your own PR after a watcher update.

  • /clavain:quality-gates

    Gate orchestrator — prepares diff, delegates review to flux-drive, enforces pass/fail gate

  • /clavain:recall

    Search across all knowledge systems — curated docs, memory files, legacy entries

  • /clavain:refactor

    Plan and execute safe refactors with explicit risk controls

  • /clavain:reflect

    Capture sprint learnings and register the reflection artifact

  • /clavain:remontoire

    Operate the Remontoire portfolio agency across hosts with explicit approval and receipt boundaries

  • /clavain:repro-first-debugging

    Disciplined bug investigation — reproduce first, then diagnose. Composes debugging agents.

  • /clavain:resolve

    Resolve findings from any source — auto-detects TODOs, PR comments, or todo files, then resolves in parallel

  • /clavain:retro

    Read a session, a PR with its session, or a week of merged PRs and propose ranked changes to the environment that would have stopped repeated mistakes

  • /clavain:review-discipline

    Run disciplined code review and feedback triage

  • /clavain:review-doc

    Quick single-pass document refinement — assess clarity, score quality, fix issues, offer iteration

  • /clavain:route

    Universal entry point — discovers work, resumes sprints, classifies tasks, and dispatches to /sprint or /work

  • /clavain:setup

    Bootstrap Clavain for the active runtime (Codex or Claude Code) and verify health

  • /clavain:show-me-your-work

    Keep a reviewable decision trail for long-running or unattended work, one TSV row per decision

  • /clavain:smoke-test

    Run smoke tests against a running app — detect dev server, walk critical user journeys, report results

  • /clavain:sprint-dag

    Visualize sprint execution as a DAG — shows phases, dispatches, and artifacts

  • /clavain:sprint-status

    Deep sprint workflow scan — session continuity, pipeline, plan, beads, recommendations.

  • /clavain:sprint

    Phase sequencer — brainstorm, strategize, plan, execute, review, ship. Use /route for smart dispatch.

  • /clavain:strategy

    Structure brainstorm output into a PRD with features, create beads for tracking, and validate before detailed planning

  • /clavain:tdd

    Run disciplined test-driven development (RED-GREEN-REFACTOR) for a task

  • /clavain:todos

    Create and maintain file-based todo tracking

  • /clavain:triage

    Triage and categorize findings for the CLI todo system

  • /clavain:unfreeze

    Lift the /freeze scope lock — restore full edit permissions

  • /clavain:update-check

    Conservative update check — reports available Sylveste/Clavain/Codex updates without changing anything

  • /clavain:upstream-sync

    Check upstream repos (beads, oracle, superpowers, compound-engineering) for updates and generate upgrade checklist

  • /clavain:verify

    Run completion verification before claiming work is done

  • /clavain:wayfind

    Chart or work a decision map in beads for an effort whose destination is known but whose route spans many sessions

  • /clavain:waymap

    Chart or work a project's Now / Next / Later roadmap in beads, as bets the coordinator commits, defers or drops

  • /clavain:work

    Execute work plans efficiently while maintaining quality and finishing features

  • /clavain:write-plan

    Create detailed implementation plan with bite-sized tasks

Subagents (7)

  • architecture
  • codex-integration
  • commands-reference
  • development
  • hooks-reference
  • interface-contracts
  • skills-reference

Hooks (22)

  • UserPromptSubmit

    ${CLAUDE_PLUGIN_ROOT}/hooks/context-gateway.sh

  • SessionStart

    ${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh

  • SessionStart

    ${CLAUDE_PLUGIN_ROOT}/hooks/peer-telemetry.sh

  • SessionStart

    ${CLAUDE_PLUGIN_ROOT}/hooks/release-canary-check.sh

  • SessionStart

    ${CLAUDE_PLUGIN_ROOT}/scripts/remontoire-attention.sh

  • SessionStart

    ${CLAUDE_PLUGIN_ROOT}/hooks/context-reset-post.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/guard-plugin-cache.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/security-triage-hook.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/gauge-gate-executor-spawn.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/context-reset-pre.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/peer-routing-telemetry.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/auto-publish.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/bead-agent-bind.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/agents-md-refresh.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/catalog-reminder.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/validate-plugin-edit.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/temple-invariant.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/context-reset-post.sh

  • Stop

    ${CLAUDE_PLUGIN_ROOT}/hooks/auto-stop-actions.sh

  • SessionEnd

    ${CLAUDE_PLUGIN_ROOT}/hooks/dotfiles-sync.sh

  • SessionEnd

    ${CLAUDE_PLUGIN_ROOT}/hooks/auto-push.sh

  • SessionEnd

    ${CLAUDE_PLUGIN_ROOT}/hooks/gate-calibration-session-end.sh

View source on GitHub

More from mistakeknot/interagency-marketplace

All 60 plugins →

interflux

claude

Multi-agent review and research with scored triage, content slicing, and intermediate finding sharing. 17 agents (12 review + 5 research), 4 commands, 1 skill, 1 MCP server. Domain detection via intersense, knowledge via interknow.

3 skills · 8 commands · 8 agents · 2 MCP servers · hooks

1

Agent performance profiler and routing optimizer. Collects evidence about flux-drive agent accuracy, proposes routing overrides for underperforming agents, and monitors canary periods. Companion plugin for Clavain.

18 commands · hooks

1

Bidirectional Notion sync for Claude Code. Three-way merge conflict resolution, beads issue tracking, and 21 MCP tools for project lifecycle and sync control.

4 skills · 3 commands · 7 agents · 1 MCP server · hooks

1

Token-efficient code reconnaissance for LLMs. Autonomous skills save 48-85% tokens via diff-context, semantic search, structural patterns, and symbol analysis. Includes MCP server for direct tool integration.

5 skills · 7 agents · 1 MCP server

1

intervox

claude

Voice engine with a closed loop: generate and edit prose in your voice, then verify it against your measured stylometric fingerprint. Register-aware profile, LLMism linter, exemplar retrieval, critique-revise apply. Successor to interfluence and intervoice.

9 skills · 1 command · 1 agent · hooks

1

interpath

claude

Product artifact generator — roadmaps, PRDs, vision docs, changelogs, and status reports from beads state, brainstorms, and project context. Companion plugin for Clavain.

1 skill · 8 commands

1

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

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

15 skills · hooks

obra/superpowers 316,836

5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.

5 skills · 16 commands · 4 agents · hooks

Imbad0202/academic-research-skills 56,698

Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.

2 commands

alibaba/open-code-review 50,068

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 agents

wshobson/agents 42,461

Long-term semantic memory for Claude Code, powered by OpenViking

5 skills · 1 command · 1 MCP server · hooks

volcengine/OpenViking 42,126

Maintain clavain?

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 plugins60 plugins