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 commands/joaquinbejar/ai-crew-sync/askgit clone --depth 1 https://github.com/joaquinbejar/ai-crew-syncWhat 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 | $0.00012 | $0.00218 |
| Opus 5 | $0.00006 | $0.00109 |
| Sonnet 5 | $0.00002 | $0.00044 |
| Haiku 4.5 | $0.00001 | $0.00022 |
Grade A, and why
ask 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.
What it actually says
Ask a teammate's agent a question over the crew bus and wait for the answer.
Input: $ARGUMENTS
Steps:
- The first word of the input is the teammate's handle; the rest is the question. If the handle looks wrong (empty question, or
list_agentsdoes not know it), ask me to rephrase instead of guessing. - Call
ask_agentwithtoset to the handle andquestionset to the question, worded as I gave it. Use the default timeout. - If it returns
answered: true, show me the answer verbatim, attributed to the teammate. - If it times out, call
ask_agentonce more with the returnedquestion_message_idasresume_message_id. If that also times out, tell me the question was delivered but unanswered, and that the reply will show up in my inbox — do not keep blocking.
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 · 15 lines · 12 tokens per session scan A f908f28f36ac
ask is a command published in the GitHub repository joaquinbejar/ai-crew-sync (4 stars, last pushed 20d ago), licensed MIT. It adds 12 tokens to every session and 218 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 2026-08-31.
Other commands, from other repositories
ai-branch
AI 解读分支（L0 回退） — 演示无 keywordAliases 时由 AI Agent 解读自然语言触发分支.
buzz-crawling
外部舆情策略更新全流程 — /buzz-crawling run 启动外部舆情策略更新全流程.
cct-sop-alert
营销智评分流（告警测试） — 测试钉钉告警通知的分流工作流，botId带test前缀会触发失败.
kf-direct-support
TeamClaw 直接技能支持 — 直接调用 teamclaw-support 技能处理用户问题，跳过多阶段编排.
riskreview
The user invoked the /riskreview facade command from the risk-review-pipeline pack.
twining:export
Export Twining state as markdown for context handoff or archival.