Skip to content
Agentmart
Submit a tool

crew-status

Rapport lecture seule de l'état crew — batchs actifs et zones, tâches en cours, tests IA non cochés, TODO non classées.

Skill by Nakken13

IndexedMIT★ 3
Write a review

Chalk Labs

Need help deploying crew-status?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/nakken13-crew-status

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Rapport lecture seule de l'état crew — batchs actifs et zones, tâches en cours, tests IA non cochés, TODO non classées. Trigger — "/crew-status", "où en est le projet", "état des batchs".

Use cases: productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/crew-status

What's inside

Skill name
crew-status
Description
Rapport lecture seule de l'état crew — batchs actifs et zones, tâches en cours, tests IA non cochés, TODO non classées. Trigger — "/crew-status", "où en est le projet", "état des batchs".
License
MIT
Instructions
37 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • files: referenced but missing: scripts/crew_hook.py

Files (1)

  • SKILL.md

SKILL.md (first lines)

Read-only — modifies no file. The computation is done by a deterministic script;
this skill presents its result. Complements the `Stop` hook (discreet stderr
output) with an on-demand view.

1. Run (plugin: the plugin's `scripts/crew_hook.py`; manual clone:
   `crew/crew_hook.py`):

   ```bash
ROOT="$(git rev-parse --show-toplevel)"; HOOK="${CLAUDE_PLUGIN_ROOT:+$CLAUDE_PLUGIN_ROOT/scripts}"; HOOK="${HOOK:-$ROOT/crew}/crew_hook.py"
CLAUDE_PROJECT_DIR="$ROOT" python "$HOOK" status
```

2. Report, from the JSON:
   - `active_batches` + `zone`; any `zone_overlaps` = **violated invariant**, to
     flag explicitly (batches + paths), not just list;
   - `current`: `done/total` ratio per task;
   - `paused`: tasks waiting for visual/dev validation — flag by name, not
     counted as normal work in progress;
   - `tests_ia_unchecked`: files with unticked boxes (what remains to validate);
   - `todo_orphans`: in `TODO/` but absent from `CLAUDE_BATCH.md` (neither batch
     nor `Unsorted`, the to-be-sorted section) → suggest `/crew-new-task` /
     `manager`;
   - `bootstrap_pending` true: run `python check_placeholders.py` and include its
     result (`<...>` placeholders = scaffold not initialized → `/crew-init`);
   - **Never-ticked checklists guard** (suggestion only): read the `Level:`
     line (legacy projects: `Niveau :`) of `crew/CLAUDE_CONTEXT/TESTS_POLICY.md` (`grep`, without reading the
     file). Only if the level is `full`, or the file is missing or unreadable
     (historical `full` behavior): if the `- [ ]` in `crew/TESTS/{IA,DEV}`
     (excluding `TESTS_DONE`) clearly dominate the `- [x]` (totals via
     `grep -rhF … | wc -l`), suggest "N boxes never ticked: switch to `light` in
     `TESTS_POLICY.md`?". Never at `light`/`none`, never modify the file.
   - `orphan_worktrees`: a `*-batch-*` worktree on disk with no session carrying
     it (crash, or `/crew-close-task` never run) — flag it for manual cleanup
     (`git worktree remove` / `git branch -d` by the user), **never** delete it
     yourself (possible uncommitted work).

## What this skill does not do

- Writes, moves, ticks nothing — pure reporting.
- Does not replace `/crew-new-task` / `/crew-close-task` to act.

From Nakken13/claude-crew, MIT.

More from Nakken13/claude-crew

Signals

Stars
3
Forks
1
Open issues
0
Last commit (this folder)
Oct 15, 2026 (26 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Same skill elsewhere

Copies of this SKILL.md published by others; search shows only one of them.

More from Nakken13

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get crew-status running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying crew-status?

CallGet help
Cite this page

crew-status skill. Agent Mart. https://agentmart.dev/skills/nakken13-crew-status (last updated 2026-10-24)