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.
git clone --depth 1 https://github.com/yempik-ai/cowork-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/yempik-ai/cowork-os/mission)<a href="https://agentmods.dev/commands/yempik-ai/cowork-os/mission"><img src="https://agentmods.dev/badge/commands/yempik-ai/cowork-os/mission/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/yempik-ai/cowork-os/mission"><img src="https://agentmods.dev/badge/commands/yempik-ai/cowork-os/mission.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00046 | $0.00284 |
| Opus 5 | $0.00023 | $0.00142 |
| Sonnet 5 | $0.00009 | $0.00057 |
| Haiku 4.5 | $0.00005 | $0.00028 |
Grade A, and why
mission scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/cowork-os:mission
Run "mission mode": for an ambitious goal, pursue the OUTCOME, not a single task. Refuse to stop at "I sent the email."
If a mission name or goal is given ($ARGUMENTS), start or advance it. Otherwise ask for the goal.
- Define the outcome in one measurable sentence (what counts as done).
- Map 2-4 routes to the outcome (parallel paths, not a single plan).
- For each route, list the next concrete action and what evidence would prove progress.
- Keep an evidence log: what was tried, what happened, what it means.
- Set stop conditions: what tells you to drop a route or escalate.
- Create or update the mission file under
missions/<slug>/from the template if the folder exists; otherwise propose creatingmissions/. - Recommend the mission-weekly-review routine to keep it moving.
End with a Memory Update (decisions to decisions/decisions_log.md, risks and questions to decisions/open_questions.md).
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.
- 11d ago First seen · 21 lines · 46 tokens per session scan A 4f904f7dcf28
mission is a command published in the GitHub repository yempik-ai/cowork-os (70 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 284 once invoked, about $0.0002 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 commands, from other repositories
reflect
Reflect on recent work — log lessons to the journal and propose distilled rule updates for review.
doctor
Check vault health — broken links, orphans, missing frontmatter, MISSING placeholders — and propose fixes.
analyze
Analyze Claude Code transcripts to surface subagent behavior and improvement opportunities.
react-router-client-loader
Do this in a clientLoader and use loaderData to render the component. DO NOT create mock data, new interfaces, or mock data loader functions. Instead, assume loaderData has all of the data you need to render the component.
sol
Run a one-shot task on the routed Codex model (gpt-5.6-sol by default) and relay its answer.
pseo-gbp-audit
Use when: kullanıcı "GBP audit", "Google Business Profile kontrol", "placeid eksik mi", "business listing kontrol", "harita listing audit", "google haritalar profili", "GMB audit", "local listing gap" der ya da /pseo-gbp-audit çağırırsa. Also use when: aktif projenin project.config.profiles array'inde "local-service"…