claude

team-workflow

Triage + orchestrator agents, pipeline skills (/task, /worktree, /commit, /review, /pr, /ship, /sync-docs) and enforcement hooks.

0 on GitHubby Julian Buitragov2.4.0MITupdated 1 month agoworkflow
/

Plugin team-workflow from marketplace ia-tools in julianjab/ia-tools. Commands read from the repo's manifest — 1 month 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 (13)

  • ask-user

    Use when a lead or worker agent needs to send a status update or ask a question to the user, and the destination depends on how the session was launched (Slack topic vs local terminal). Centralizes the routing decision so agent prompts stay clean of "if Slack else AskUserQuestion" branches.

  • commit

    Stage and commit changes with conventional commit format. Runs formatting, quick test validation, and creates atomic conventional commits. Examples: `/commit`, `/commit --type feat --scope notification --message "add port"`, `/commit --type fix --scope calendar`.

  • ipc-answer

    Use to send an answer back to a child lead session that asked a question via parent IPC. The router-Claude sees inbound questions injected as `[ipc id=<uuid> from=<session>] <text>` lines; replying through this skill delivers the answer to the waiting child over the Unix socket the router boots with

  • pr-review

    Review the current branch's changes against project standards. Loads the project's review checklist + stack-specific rules, reads the diff, and produces a fixed-format report with issues classified by severity and references to file:line.

  • pr

    Push branch and create or update a Pull Request with architecture diagrams. Runs /review automatically before pushing (mandatory quality gate). Resolves merge conflicts, generates component diagrams, and monitors CI. Examples: `/pr`, `/pr --base main`, `/pr --skip-ci`.

  • review

    Code quality validation: formatting, tests, coverage, and coding standards. Run standalone to validate current work, or invoked automatically by `/pr` before push. Supports: `fmt` (format & lint), `test` (run tests), `coverage` (validate thresholds), `rules` (check coding standards), or no sub-comma

  • router

    Spawn the main `router` agent in a detached tmux session. Topic is optional — omit it to start without a subscription and subscribe later with subscribe_slack. Hides the `--dangerously-load-development-channels` flag in the wrapper script so the operator doesn't type it on every boot. Use this once

  • security-audit

    Scan the codebase (or a worktree diff) for hardcoded secrets, exposed config, common injection patterns, and missing input validation. Produces a fixed-format report with severity-classified findings and file:line references. Invoked by `team-lead` when no repo-local security agent exists, or standa

  • send-session-message

    Forward a message to a running lead session (tmux or iTerm2) and submit it. Auto-detects the host: tmux first (`tmux has-session`), then iTerm2 (osascript lookup by session name). Pastes the text literally, then fires a SEPARATE submit keystroke so Claude Code's TUI actually processes the message. C

  • session

    Spawn a Claude orchestrator sub-session in tmux (default) or iTerm2 (via osascript, when IA_TW_TERMINAL=iterm or as fallback if tmux is missing). Defaults to the `lead` agent (`team-workflow:lead`) with worktree provisioning. `--provision clone` switches `lead` to clone-mode (it shallow-clones `--re

  • sync-docs

    Audit and auto-update CLAUDE.md files to match the current state of the codebase. Detects drift between documentation and actual code: new services, removed files, changed patterns, outdated commands, stale references. Applies fixes automatically and shows the diff. Use when you want to ensure CLAUD

  • team-review

    Request team review for an existing PR. Loads channel + reviewer config from settings.local.json env (or CLAUDE.md fallback), runs a quick standards preflight on the PR, blocks until CI is green, posts a review-request message in Slack mentioning the configured users/groups, and subscribes to the re

  • worktree

    Git worktree management for parallel development. Create isolated worktrees for features, reviews, and hotfixes without switching branches. Supports: `init` (create), `list` (show active), `switch` (change context), `cleanup` (remove merged/stale), `status` (overview). `init` accepts `--repo <path>`

Subagents (3)

  • implementer

    Implements feature code inside a worktree when the touched repo does not ship its own implementer agent. Loads the worktree's CLAUDE.md and stack manifests before editing so the work matches the repo's conventions, follows tests-first if qa already wrote a RED test, and runs the repo's linters/tests

  • lead

    Per-feature orchestrator. Boots inside the consumer repo (single or multi), provisions a worktree per touched repo, reads the discovery results spliced into state.md by the detect-repo-capabilities hook, builds the full task list with `owner` resolved at planning time, then dispatches the graph unti

  • router

    Main-session dispatcher AND inline conversational agent. Classifies each inbound (answer / ask / dispatch) and handles it directly. Delegates heavy reads to `Agent(Explore)` and unknown-repo discovery to `Agent(general-purpose)`; never spawns a persistent worker. Load with `--agent team-workflow:rou

Hooks (30)

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/enforcement/enforce-worktree.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/enforcement/tool-guard.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/enforcement/enforce-code-change-task.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/intelligence/redirect-ask-user.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/intelligence/agent-routing-pretool-edit.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/intelligence/agent-routing-pretool-bash.sh"

  • TaskCreated

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/bookkeeping/task-created.sh"

  • TaskCreated

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/intelligence/detect-task-replaced.sh"

  • TaskCompleted

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/enforcement/enforce-task-invariants.sh"

  • TaskCompleted

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/bookkeeping/record-state-event.sh"

  • TaskCompleted

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/enforcement/ci-poller.sh"

  • TeammateIdle

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/enforcement/teammate-idle.sh"

  • PreCompact

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/bookkeeping/pre-compact.sh"

  • SessionStart

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/bookkeeping/session-start.sh"

  • SessionStart

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/bookkeeping/sync-agents.sh"

  • SessionStart

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/intelligence/agent-routing-session-start.sh"

  • SessionEnd

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/intelligence/session-end.sh"

  • SessionEnd

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/intelligence/extract-memory-signal.sh"

  • SessionEnd

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/bookkeeping/archive-on-merge.sh"

  • UserPromptSubmit

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/intelligence/detect-user-correction.sh"

  • UserPromptSubmit

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/bookkeeping/append-message.sh" user-prompt

  • UserPromptSubmit

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/intelligence/agent-routing-prompt.sh"

  • Stop

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/bookkeeping/append-message.sh" agent-stop

  • PostToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/intelligence/detect-retract.sh"

  • PostToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/intelligence/detect-plan-edited.sh"

  • PostToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/intelligence/detect-repo-capabilities.sh"

  • PostToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/intelligence/detect-coverage-gate.sh"

  • PostToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/bookkeeping/append-message.sh" tool-use

  • SubagentStop

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/bookkeeping/subagent-stop.sh"

  • SubagentStop

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/bookkeeping/append-message.sh" subagent-stop

View source on GitHub

More from julianjab/ia-tools

All 5 plugins →

scaffold

claude

Scaffolding, validation, and editing for Claude Code agents, skills, and MCP servers. Ships /new-agent, /new-skill, /new-mcp generators; /audit-agent, /audit-skill, /audit-mcp validators; and /edit-agent, /edit-skill, /edit-mcp for audit-bracketed focused edits. Backed by canonical best-practice references.

12 skills · 4 agents · hooks

0

Captures Claude Code session events (sessions, prompts, tool usage) into a local SQLite store so future versions can detect patterns and forge skills/agents/hooks automatically. PR1 is capture-only; ships the /insights skill as a smoke-test reader.

2 skills · hooks

0

Composable pipeline (intake → repo-detect → repo-fetch → worktree → agent-scan → task-plan → dispatch) connected by a single state.yaml contract, with a per-session harness-events.log feeding the harness-engineering improvement loop. Workflow-agnostic: no role taxonomy, no ordering invariants, no Slack/tmux coupling.

1 skill · 1 agent

0

Slack bridge MCP server: subscribe to channels, claim and reply to messages, read threads, receive channel thread replies without @mention, and react with emoji (✅/❌) as approval signals via daemon + MCP architecture.

1 MCP server

0

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

nextjs

claude

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

6 skills

vercel/next.js 143,495

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

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

Maintain team-workflow?

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 plugins5 plugins