Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/d3x293/code-crew/team-statusnpx skills add d3x293/code-crew --skill team-statusgit clone --depth 1 https://github.com/d3x293/code-crewWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00029 | $0.00885 |
| Opus 5 | $0.00015 | $0.00443 |
| Sonnet 5 | $0.00006 | $0.00177 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
team-status scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Status - Crew Dashboard
Shows the current state of CodeCrew for the active project.
When to Activate
- User runs
/crew status
Status Report Sections
1. Project Overview
Read .claude/crew-profile.md and display:
Project: {name}
Type: {type} | Languages: {languages} | Frameworks: {frameworks}
Size: {files} files, {lines} lines
2. Codebase Index Health
Read .claude/crew-index.json and check:
Index: {file count} files, {symbol count} symbols | {FRESH|STALE|MISSING} | Last: {time ago}
Health assessment:
- FRESH: indexed within last session, all hashes valid
- STALE: indexed > 1 day ago or hash mismatches detected
- MISSING: index files don't exist → recommend
/crew init
Quick staleness check: pick 3 random files from the index, compute their current hash, compare with stored hash. If any mismatch → STALE.
3. Agent Team
Read .claude/crew-team.json and .claude/crew-config.json (if exists) and display:
If the config has "defaultMode": "lite" or the last task in history used "mode": "lite", show Mode: LITE otherwise Mode: FULL.
Mode: {FULL|LITE}
Opus: ceo
Sonnet: vp-engineering, vp-quality, senior-dev, code-reviewer, debugger [standby: security-analyst, test-engineer]
Haiku: junior-dev, doc-writer [standby: devops-engineer]
4. Skill Catalog
Read .claude/crew-skills.json and display:
Skills: {relevant}/{total} for {detected stack} | Active: {list} | On-demand: {count} by task type
5. Agent Performance
Read .claude/crew-history.json (if exists, and has 3+ tasks) and aggregate per-agent stats:
Agent Performance (last 20 tasks):
Agent | Tasks | Success | Avg Confidence
senior-dev | 15 | 93% | high
debugger | 8 | 100% | high
junior-dev | 12 | 100% | high
code-reviewer | 6 | 100% | —
vp-engineering | 4 | 100% | —
doc-writer | 3 | 100% | high
Calculation:
- For each agent that appears in history
agents[]arrays - Count total tasks, count where
status: "success", averageconfidencevalues - Sort by task count descending
- If fewer than 3 tasks in history: skip this section
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 99 lines · 29 tokens per session scan A 83d04fb3cad4
team-status is a skill published in the GitHub repository d3x293/code-crew (13 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 885 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
business-investment-advisor
../../../finance/business-investment-advisor/skills/business-investment-advisor/SKILL.md.
a11y-audit
../../../engineering-team/a11y-audit/skills/a11y-audit/SKILL.md.
adversarial-reviewer
../../../engineering-team/skills/adversarial-reviewer/SKILL.md.
agent-harness
../../../engineering/agent-harness/skills/agent-harness/SKILL.md.
agent-launcher-orchestrator
../../../agent-launcher/skills/agent-launcher-orchestrator/SKILL.md.
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.