agent-team-check-lite
ASecurityFree health check for a team of AI agent sessions that share ORG.md, TEAM_PLAN.md and DECISIONS.md. Finds a role that has no queue, a broken reporting line, more than one voice to the human, tasks with no goal or receiver, template text left in the plan, a stale plan or decision log, and missing session ids. Use when the user runs several Claude Code sessions as a team and asks whether the team files are healthy. Search words: agent team setup, multi-agent team, agent org chart, team plan che...
- 0 votes
- 0 copies
- 8 views
- Added October 29, 2026
Works with
Security analysis
100/100Pro scans all 6 files and shows the line behind each finding
npx -y skills add MalikKhaledSaid/agent-skills --skill agent-team-check-lite --agent claude-codeAre you the author of agent-team-check-lite?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/malikkhaledsaid-agent-team-check-lite)---
name: agent-team-check-lite
description: Free health check for a team of AI agent sessions that share ORG.md, TEAM_PLAN.md and DECISIONS.md. Finds a role that has no queue, a broken reporting line, more than one voice to the human, tasks with no goal or receiver, template text left in the plan, a stale plan or decision log, and missing session ids. Use when the user runs several Claude Code sessions as a team and asks whether the team files are healthy. Search words: agent team setup, multi-agent team, agent org chart, team plan check, decision log, agent handoff, parallel Claude Code sessions.
license: MIT. LICENSE has complete terms.
compatibility: Designed for Claude Code with several sessions; works with any agent that reads files. Needs python3 (3.8+). No network access.
metadata:
version: "1.0.2"
edition: "free"
---
# Agent team check (lite)
You check the team files of a group of agent sessions. The script gives the findings. You explain each one in plain words. You change nothing until the user agrees.
## Step 1: Run the check
From the folder that holds ORG.md and TEAM_PLAN.md, with the path to this skill's folder:
```bash
python3 <skill-folder>/scripts/team_check.py --dir .
```
`--json` prints JSON. `--stale-days N` sets the age at which a plan counts as stale (default 7). Exit code 1 means at least one ERROR.
## Step 2: Explain the findings
List ERRORs first, then WARNs. For each, say what is wrong and name the file and line to edit. Use the Fixes list the script prints.
`references/templates.md` shows the file formats the check reads. Use it when a file is missing or in the wrong shape.
## Step 3: Edit after approval
Propose each edit as a short before and after. Make the edits only after the user says yes.
## Limits
- The check reads the files. It cannot tell whether the work in them is good.
- This edition has no set-up mode and no before-and-after comparison. The full edition has both.
Full edition: agent-team-ops $12: one-command set-up, a fix guide for each finding, a CLAUDE.md block, a worked example team and a before-and-after check. https://buy.polar.sh/polar_cl_0RUUUFGvqGayeWXaK1PxhAuQSrHMRDJHEkuoZ0xJOV3
Files in this skill
- .claude-plugin/plugin.json
- LICENSE
- README.md
- SKILL.md
- references/templates.md
- scripts/team_check.py
Attribution
Comments
Loading comments…
Newsletter
Get the weekly list of safe new skills, and the ones we pulled.