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/Gekkos-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/gekkos-tech/agency-os/status)<a href="https://agentmods.dev/commands/gekkos-tech/agency-os/status"><img src="https://agentmods.dev/badge/commands/gekkos-tech/agency-os/status/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/gekkos-tech/agency-os/status"><img src="https://agentmods.dev/badge/commands/gekkos-tech/agency-os/status.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 | $0.00019 | $0.00298 |
| Opus 5 | $0.00010 | $0.00149 |
| Sonnet 5 | $0.00004 | $0.00060 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
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 8d 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
Report the project status for: $ARGUMENTS (default: the current project)
- Read
docs/project-state.md. If it exists, verify it against reality with quick spot-checks (does the phase's key artifact actually exist — brief, concept, design/ handoff, code, QA report, live URL?). Fix discrepancies in the file first. - If no state file exists, load the
agency-workflowskill, classify the phase from project signals, and CREATEdocs/project-state.mdfrom the template in its references — this command is the recovery path for projects started before state tracking existed. - Report to the user, compact:
- Phase + health (on track / blocked / at risk, with the reason)
- Gate status — what's passed, what's open in the current phase
- Blockers with owners and age (flag anything older than 7 days)
- Client owes / we owe — the two lists, with dates
- The single next step — and offer to execute it now
Do not start any phase work in this command beyond the spot-checks — /status reports; the workflow executes.
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.
- 8d ago First seen · 25 lines · 19 tokens per session scan A 292e0e2bf1ac
status is a command published in the GitHub repository Gekkos-tech/agency-os (5 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 298 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
estimate-work
Estimate a task or project honestly, by decomposing it, surfacing unknowns, and giving a range not a false point.
meeting-request-email
Write an email requesting a meeting that states the purpose, respects their time, and makes scheduling easy.
pre-mortem
Run a pre-mortem: imagine the project already failed, work backward to the causes, and prevent them now.
promotion-packet
Write a promotion packet or self-review that frames your work as impact at the next level, with evidence.
exec-one-pager
Write a one-page brief for executives that leads with the ask and the bottom line, backed by just enough evidence.
job-description
Write a clear, honest job description that attracts the right candidates and screens out the wrong ones.