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/automatelab-tech/agency-os/startgit clone --depth 1 https://github.com/AutomateLab-tech/agency-osWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/automatelab-tech/agency-os/start)<a href="https://agentmods.dev/commands/automatelab-tech/agency-os/start"><img src="https://agentmods.dev/badge/commands/automatelab-tech/agency-os/start.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00000 | $0.00362 |
| Opus 5 | $0.00000 | $0.00181 |
| Sonnet 5 | $0.00000 | $0.00072 |
| Haiku 4.5 | $0.00000 | $0.00036 |
Grade A, and why
start 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 4d 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
Command: start <id> (alias: launch)
Move To-Do -> In Progress and emit the kickoff brief.
-
Sync preflight.
-
Resolve
<id>(UUID, URL, or substring against To-Do rows). -
Verify status is
To-Do. IfSuggestion-> refuse withdiscuss it first. IfDiscussion-> refuse withapprove it first. IfIn Progress-> soft-allow (re-emits brief). -
notion-update-pageStatus -> In Progress. -
Assemble the kickoff brief, in this exact order:
## Task [<title>](<notion-url>) [<corpus> / <priority> / type=<type>{ cadence=<cadence>}{ last_done=<date>} / effort=<effort>] ## Description <Description toggle body> ## Subtasks (N) - [Status] <subtask title> -> /agency-os start <subtask-id> - ... ## Latest discussion entry (of <K> total) <most-recent entry verbatim> (For older entries: /agency-os show <id> --section discussion --entry <date>) ## Corpus: <name> <Goal + Local guidance from the corpus page> ## General guidance <full general guidance page body> -
End with:
Brief loaded. Proceed.
Overfeed protection. The brief never embeds:
- Older discussion entries (only the latest; the rest are referenced by date)
- Sibling tasks
- Subtask bodies (only their titles + status)
- The Done log
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.
- 4d ago First seen · 40 lines · 0 tokens per session scan A 4f0992585328
start is a command published in the GitHub repository AutomateLab-tech/agency-os (3 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 362 tokens. 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
team-status
查看当前活跃的 PUA agent/team 清单、PID、TTL。/pua:team-status。Triggers on: '/pua:team-status', '查看 agent 状态', 'pua team status', 'list agents'.
done-check
PUA Done Check — 用于没跑测试别说完成、已完成但没证据、done without proof、需要验收/回归/交付质量检查的场景。.
evidence
PUA Evidence — 用于证据呢、数据在哪、验收标准是什么、怎么证明完成、需要证据链/交付物核对的场景。.
survey
PUA 调研问卷 — 7 部分交互式问卷收集用户反馈。/pua:survey。Triggers on: '/pua:survey', 'pua survey', '调研', '问卷', 'feedback survey'.
flavor
PUA 切换味道 — 从 15 种味道中选择，包括阿里/字节/华为/腾讯/Netflix/Musk/Jobs/Microsoft/钉内钉外。.
kpi
PUA KPI 报告卡 — 生成段位和绩效报告。/pua:kpi。Triggers on: '/pua:kpi', 'pua kpi', 'kpi报告', '段位报告', 'performance report', 'generate kpi'.