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/monthly-report)<a href="https://agentmods.dev/commands/gekkos-tech/agency-os/monthly-report"><img src="https://agentmods.dev/badge/commands/gekkos-tech/agency-os/monthly-report/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/monthly-report"><img src="https://agentmods.dev/badge/commands/gekkos-tech/agency-os/monthly-report.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 | $0.00020 | $0.00329 |
| Opus 5 | $0.00010 | $0.00164 |
| Sonnet 5 | $0.00004 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
monthly-report 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 12d 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 MAINTAIN loop for: $ARGUMENTS
Load the agency-workflow skill (MAINTAIN phase reference) and execute the
monthly sequence:
- Drift check — run the installed SEO audit skill in drift mode against the stored baseline (meta, schema, robots, canonicals, content changes). No baseline yet? Capture one now and say so — the first report establishes the reference, it can't diff.
- Performance spot-check —
core-web-vitalson the top pages; compare against the QA-report baseline, flag regressions with numbers. - Function re-test — forms deliver, key flows complete, no new console
errors (use
webapp-testingwhere an environment allows). - Content & legal freshness — contact data/hours/prices current; privacy policy still matches the third-party services actually loaded; SSL validity.
- Write the report —
docs/reports/{YYYY-MM}.mdin the client's language: non-technical summary first (3 sentences max), then checked / changed / fixed / recommended, each with evidence. Updatedocs/project-state.md(phase MAINTAIN, next cadence date).
Close by telling the user: the verdict in one line, regressions found (if any), and whether the baseline was updated or preserved.
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.
- 12d ago First seen · 29 lines · 20 tokens per session scan A f7fd7829f684
monthly-report is a command published in the GitHub repository Gekkos-tech/agency-os (5 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 329 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
agent-build-feature
A strict brief that makes a coding agent implement a feature end to end, matching the codebase and verifying it works.
agent-system-prompt
Write a system prompt for an AI agent that defines its role, tools, boundaries, and output clearly enough to act reliably.
bug-report-triage
Turn a vague bug report into a structured, actionable ticket with severity and next steps.
decline-politely
Say no clearly and kindly, to a request, invitation, or offer, without burning the relationship or over-explaining.
devils-advocate
Stress-test an idea, plan, or decision by arguing against it honestly, to find the flaws before reality does.
estimate-work
Estimate a task or project honestly, by decomposing it, surfacing unknowns, and giving a range not a false point.