claude

coordinator

Coordinator plugin: plan-enrich-chunk-review pipeline, named reviewer personas (the Staff Engineer, the Director of Engineering, the Game Dev Reviewer, the Data Science Reviewer, the UX Reviewer, the Front-End Reviewer), fan-out dispatch, session continuity via handoffs and flight recorders, and workflow skills (/plan, /review, /execute-plan, /workday-start, /workstream-complete).

5 on GitHubby Dónal O'Duffy & Claudev4.6.18updated 7 days ago
/

Plugin coordinator from marketplace coordinator-claude in dbc-oduffy/coordinator-claude. Commands read from the repo's manifest — 7 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 (47)

  • app-session

    Census/launch/teardown/validate for a repo's declared app.

  • architecture-audit

    Rotational arch audit: score systems, audit the top. No code edits.

  • artifact-investigation

    Opaque binary or artifact investigation: structure first, script second, agent last.

  • box-onboarding

    Admit a new macOS box to the multibox fleet: Homebrew python3, Remote Login, install, engine, keys, Unimatrix, home repo, verify.

  • brainstorming

    Shape vague or multi-subsystem asks into requirements. Size first if unsized.

  • bug-sweep

    Codebase bug hunt: fix AI-fixable bugs, defer the rest.

  • cloud-channel
  • cloud-spawn
  • code-health
  • consolidate-git
  • coordinator-update
  • debt-triage
  • design-canvas
  • dogfood
  • enrich-and-review
  • eval-output
  • execute-plan
  • finishing-a-development-branch
  • goal-blitz
  • goal-setting
  • group-em
  • handoff
  • learn-lessons
  • merging-to-main
  • new-project
  • parallel-code-review
  • pickup
  • plan-blitz
  • plan-delivery-audit
  • plan
  • quick-wrap
  • repo-setup
  • review
  • roadmap-blitz
  • roadmap-planning
  • setup
  • shape
  • sizing
  • spike
  • spinoff
  • staff-session
  • strategic-self-description-refresh
  • systematic-debugging
  • uhura
  • validate
  • workstream-complete
  • workstream-start

Slash commands (18)

  • /coordinator:architecture-survey

    Build or refresh the architecture atlas.

  • /coordinator:autonomous

    Toggle autonomous mode — the PM-away premise for what counts as a legitimate stop.

  • /coordinator:bug-blitz

    Submit a bug-blitz as one coordinator:bug-blitz Workflow call.

  • /coordinator:cruft-sweep

    Find reclaimable scratch and orphans; apply only if confirmed.

  • /coordinator:distill

    Distill session artifacts to wiki and decisions; archive specs, drop scratch.

  • /coordinator:fire-and-forget

    \"fire and forget\" / \"fire and forget\": a raw ask or sizing to a reviewed commit in one fire.

  • /coordinator:install

    Installs the coordinator plugin: prereqs, project config.

  • /coordinator:mise-en-place

    Autonomous backlog run — flight-recorder prep, then run-through.

  • /coordinator:mise-prep

    Certify approved plans; route residue to plan-author-residue.

  • /coordinator:notebooklm-research

    PM-GATED, never from a subagent. NotebookLM research for video/audio sources.

  • /coordinator:research

    Research by value class: scouts, corpus, deep, or spike. EM-fired, never from a subagent.

  • /coordinator:review-code

    Review a code diff/PR, or apply landed findings — findings land on the artifact.

  • /coordinator:uninstall

    Reverses the coordinator install, fully or back to marketplace.

  • /coordinator:update-docs

    Sync all documentation artifacts to the current codebase state.

  • /coordinator:workday-complete

    End-of-day wrap — validate, consolidate, review, changelog.

  • /coordinator:workday-start

    Morning orient — triage handoffs, staleness, priorities.

  • /coordinator:workweek-complete

    Weekly release ceremony — validate, docs, release notes, merge.

  • /coordinator:workweek-start

    Weekly orient — review last week, set this week's priorities.

Subagents (56)

  • apm

    Personas are Opus-only. Angelique, adversarial junior-PM: ELI5 a plan's choice, then challenge it.

  • atlas-clarity-reviewer

    Clarity verdict for one atlas page: followability, ambiguity. Never accuracy.

  • blitz-em

    Personas are Opus-only. EM judgment in a plan-blitz wave: interrogates sizings.

  • code-reviewer-weekly

    Static weekly-gate chunk reviewer, compaction-safe. Only via parallel-code-review.

  • code-reviewer

    Static Sonnet code reviewer: nits, weak tests, security. Sidecar + OK/WARN/BLOCKED.

  • coverage-auditor

    Fresh-eyes check of specialist claims against a finished synthesis: present/absent.

  • delivery-verifier

    Checks executor delivery claims against the frozen diff. Read-only.

  • dep-cve-auditor

    Audits dependency manifests for CVEs; source is security-audit-worker's.

  • distill-writer

    Lean batch writer for distill-harvest: synthesizes a batch of topic clusters into staged files.

  • doc-link-checker

    Validates doc links and anchors; external URLs only on opt-in. Returns a status table.

  • docs-checker

    Verifies external API claims against authoritative docs before Opus review. A table.

  • eng-director

    Personas are Opus-only. The Director of Engineering, Director of Engineering: staff rigor, cross-repo boundaries.

  • enricher

    Enriches plan stubs and live plan bodies pre-execution. Verifies facts, never decides.

  • executor

    Delivers one chunk of an enriched, reviewed plan; validates at chunk boundaries.

  • exit-criterion-falsifier

    Authors and runs the baseline falsifier for a plan's prime exit criterion.

  • exit-criterion-judge

    Terminal judge: is a run's prime exit criterion met or not_met.

  • external-pattern-checker

    Opt-in web research on plan claims prior-art-checker left Silent.

  • external-reviewer

    Opt-in non-Anthropic review lens: runs the codex CLI out of process, applies findings, owns the ledger.

  • falsifier-integrity-reviewer

    Static review of an exit-criterion falsifier: can it report red at all.

  • git-commit-agent

    Commits a supplied pathspec via the scoped route when the EM can't run the ceremony.

  • group-em-assistant

    Sonnet aide to a Group EM: memo inbox, park-spool triage. Read-and-report.

  • notebooklm-research-scout

    Haiku NotebookLM scout: finds sources per notebook topic, writes sources.md.

  • objective-reacher

    Writes a delta plan whose rows target only the failing falsifier axes of a run objective; never declares done.

  • op-relay

    Relays one coordinator-invoke op verbatim.

  • overengineering-reviewer

    Personas are Opus-only. Kira: final whole-diff pass; cuts waste, may change code, checks the target. Not plans.

  • parallel-review-synthesizer

    Folds chunk reviews and specialists into one verdict; parallel-code-review only.

  • plan-author-residue

    Amends plans in place with /mise-prep capabilities and appends; never authors one.

  • plan-author

    Authors one plan doc against a finalised size/route; never sizes, routes, or executes.

  • plan-coverage-checker

    Mechanical plan check: slate vs oracle, deferral ratification, task-spine. No fixes.

  • plan-reviewer

    Sonnet plan-body reviewer: assumes gaps, runs the coverage checklist; edits only as XS/S reviewer.

  • premise-checker

    Resolves a plan's load-bearing citations against the tree before review.

  • prior-art-checker

    Recall pre-flight: plan vs wikis, decisions, lessons. Conflicts/Compatible/Silent.

  • queue-grind-op-runner

    Runs one queue-grind op verify via coordinator-invoke; relays exit code and JSON.

  • repo-scout

    Haiku repo-research scout: inventories assigned repo chunks. Mechanical only.

  • repo-specialist

    Sonnet repo-research specialist: deep-reads a scout inventory, writes claims.json.

  • research-brief-author

    Sonnet research-brief author: after the haiku source survey, writes the expert brief specialists read.

  • research-scout

    Haiku web-research scout: runs scope.md queries, writes the source corpus.

  • research-specialist

    Sonnet web-research specialist: deep-reads scout sources, writes claims.json.

  • research-sweep

    Opus NotebookLM sweep after workers: coverage check, gap fill, final framing.

  • research-synthesizer

    Opus web-research sweep after specialists: adversarial coverage, gaps, summary.

  • research-worker

    Sonnet NotebookLM worker: ingests scout sources, queries, writes {letter}-claims.json.

  • residue-author

    Authors /mise-prep residue: capabilities, appends, census rewrites; never decides scope.

  • roadmap-planner

    Authors a roadmap's inventory, clusters, overview, stubs; never sizes, approves, executes.

  • security-audit-worker

    Sonnet static-security scan of a diff: traversal, injection, secrets.

  • senior-front-end

    Personas are Opus-only. The Front-End Reviewer: front-end review for design-system adherence.

  • sizing-scout

    Sizes one ask by engineering depth, not breadth; in engine-ask it also writes and gates it.

  • spike-worker

    Sonnet spike worker: web research plus scratch-dir probes to a binary viable/not-viable verdict record.

  • staff-data-sci

    Personas are Opus-only. The Data Science Reviewer: data science, ML, and statistics review.

  • staff-eng

    Personas are Opus-only. The Staff Engineer: generalist staff-engineer review of code, plans, docs.

  • staff-ux

    Personas are Opus-only. The UX Reviewer: user-facing flow review for clarity and trust.

  • structured-synthesizer

    Opus structured-research synthesizer: verifier findings to schema YAML/JSON.

  • subtractive-adjudicator

    Personas are Opus-only. Terminal subtractive pass: what comes OUT of reviewer additions.

  • test-evidence-parser

    Classifies captured test failures (real/flake/env/timeout/skip). Mechanical.

  • test-runner

    Runs a diff's scoped tests and execute-review prep. Never the fast/full suite.

  • vp-product

    Personas are Opus-only. The VP-Product Reviewer, VP Product: stress-tests choices before they ship.

  • workflow-maker

    Emits a plan's spine as a Workflow script; returns path and wave map for the EM to fire.

Hooks (30)

  • SessionStart

    python3

  • SessionStart

    python3

  • SessionStart

    python3

  • SessionStart

    python3

  • Stop

    python3

  • Stop

    COORDINATOR_DOOR_STDIN_MODE=hook "${COORDINATOR_SETTINGS_HOME:-$HOME/.coordinator-claude-settings}/bin/hook-run" hooks.guard_manufactured_blocker 2>/dev/null; rc=$?; [ $rc -eq 2 ] && rc=0; exit $rc

  • Stop

    COORDINATOR_DOOR_STDIN_MODE=hook "${COORDINATOR_SETTINGS_HOME:-$HOME/.coordinator-claude-settings}/bin/hook-run" hooks.guard_turn_intent 2>/dev/null; rc=$?; [ $rc -eq 2 ] && rc=0; exit $rc

  • SessionEnd

    COORDINATOR_DOOR_STDIN_MODE=hook "${COORDINATOR_SETTINGS_HOME:-$HOME/.coordinator-claude-settings}/bin/hook-run" --advisory hooks.sessionend_archive_session 2>/dev/null; rc=$?; [ $rc -eq 2 ] && rc=0;

  • SubagentStart

    python3

  • SubagentStart

    python3

  • SubagentStart

    COORDINATOR_DOOR_STDIN_MODE=hook "${COORDINATOR_SETTINGS_HOME:-$HOME/.coordinator-claude-settings}/bin/hook-run" --advisory hooks.workflow_step_dispatch 2>/dev/null; rc=$?; [ $rc -eq 2 ] && rc=0; exit

  • SubagentStop

    python3

  • SubagentStop

    COORDINATOR_DOOR_STDIN_MODE=hook "${COORDINATOR_SETTINGS_HOME:-$HOME/.coordinator-claude-settings}/bin/hook-run" --advisory hooks.workflow_step_dispatch 2>/dev/null; rc=$?; [ $rc -eq 2 ] && rc=0; exit

  • UserPromptExpansion

    python3

  • UserPromptSubmit

    python3

  • PreToolUse

    COORDINATOR_DOOR_STDIN_MODE=hook "${COORDINATOR_SETTINGS_HOME:-$HOME/.coordinator-claude-settings}/bin/hook-run" hooks.preuse_bash_dispatch

  • PreToolUse

    python3

  • PreToolUse

    python3

  • PreToolUse

    COORDINATOR_DOOR_STDIN_MODE=hook "${COORDINATOR_SETTINGS_HOME:-$HOME/.coordinator-claude-settings}/bin/hook-run" hooks.guard_agent_route_admission

  • PreToolUse

    COORDINATOR_DOOR_STDIN_MODE=hook "${COORDINATOR_SETTINGS_HOME:-$HOME/.coordinator-claude-settings}/bin/hook-run" --advisory hooks.guard_ue_specialist_advisory

  • PreToolUse

    COORDINATOR_DOOR_STDIN_MODE=hook "${COORDINATOR_SETTINGS_HOME:-$HOME/.coordinator-claude-settings}/bin/hook-run" hooks.guard_brief_prescribed_method

  • PreToolUse

    COORDINATOR_DOOR_STDIN_MODE=hook "${COORDINATOR_SETTINGS_HOME:-$HOME/.coordinator-claude-settings}/bin/hook-run" hooks.guard_editor_python_direct

  • PreToolUse

    COORDINATOR_DOOR_STDIN_MODE=hook "${COORDINATOR_SETTINGS_HOME:-$HOME/.coordinator-claude-settings}/bin/hook-run" --advisory hooks.preuse_search_dispatch 2>/dev/null; rc=$?; [ $rc -eq 2 ] && rc=0; exit

  • PreToolUse

    python3

  • PreToolUse

    python3

  • PreToolUse

    python3

  • PreToolUse

    COORDINATOR_DOOR_STDIN_MODE=hook "${COORDINATOR_SETTINGS_HOME:-$HOME/.coordinator-claude-settings}/bin/hook-run" --advisory hooks.block_group_em_agent_cap_grant 2>/dev/null; rc=$?; [ $rc -eq 2 ] && rc

  • PreToolUse

    COORDINATOR_DOOR_STDIN_MODE=hook "${COORDINATOR_SETTINGS_HOME:-$HOME/.coordinator-claude-settings}/bin/hook-run" --advisory hooks.rewrite_sendmessage_peer_name 2>/dev/null; rc=$?; [ $rc -eq 2 ] && rc=

  • PreToolUse

    python3

  • PreToolUse

    python3

View source on GitHub

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

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

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

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

12 skills

vercel-labs/agent-browser 50,373

Maintain coordinator?

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 pluginslisted