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/pre-launch)<a href="https://agentmods.dev/commands/gekkos-tech/agency-os/pre-launch"><img src="https://agentmods.dev/badge/commands/gekkos-tech/agency-os/pre-launch/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/pre-launch"><img src="https://agentmods.dev/badge/commands/gekkos-tech/agency-os/pre-launch.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 | $0.00027 | $0.00229 |
| Opus 5 | $0.00014 | $0.00114 |
| Sonnet 5 | $0.00005 | $0.00046 |
| Haiku 4.5 | $0.00003 | $0.00023 |
Grade A, and why
pre-launch 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
Run the pre-launch gate on: $ARGUMENTS
Delegate to the qa-auditor agent with the pre-launch-checklist skill as
its rulebook. The agent must:
- Work through section A (legal — DACH/EU) and section B (technical) of the checklist against the actual site/code, collecting evidence per item — no checkbox theater: verify third-party requests in the code, test the consent gate both ways, send a real test form submission where possible.
- Produce
docs/launch-checklist.mdin the client's language with the GO / NO-GO result table.
Then report back: the verdict (GO / NO-GO), every legal blocker verbatim, and the top technical items. Legal blockers are non-negotiable — if any exist, state plainly that launch is not recommended until they are fixed.
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 · 21 lines · 27 tokens per session scan A 6d1dbb64b0ce
pre-launch is a command published in the GitHub repository Gekkos-tech/agency-os (5 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 229 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
contract-review-checklist
Extract the terms that matter from an agreement and flag deviations for a lawyer, without giving legal advice.
review-data-privacy
Review a feature for privacy: what is collected, where it goes, how long it stays, and whether deletion works.
estimate-work
Estimate a task or project honestly, by decomposing it, surfacing unknowns, and giving a range not a false point.
eli-expert
Explain a topic at an expert level, assuming deep background and going straight to the substance.
run-company-standup
Produce a daily operating brief across every function, ranked by what needs a decision today.
preflight
Audit a build against App Review rejection triggers by app type before submitting.