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/campaign)<a href="https://agentmods.dev/commands/gekkos-tech/agency-os/campaign"><img src="https://agentmods.dev/badge/commands/gekkos-tech/agency-os/campaign/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/campaign"><img src="https://agentmods.dev/badge/commands/gekkos-tech/agency-os/campaign.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 | $0.00207 |
| Opus 5 | $0.00010 | $0.00103 |
| Sonnet 5 | $0.00004 | $0.00041 |
| Haiku 4.5 | $0.00002 | $0.00021 |
Grade A, and why
campaign 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 10d 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
Ideate a campaign for: $ARGUMENTS
Load the ad-concepts skill and follow its process:
- Audience-insight step first (pain, desire, objection, trigger moment) — state it in 4 lines before any ideas.
- Deliver exactly 3 campaign routes with different emotional registers,
each with: working title, core claim, hook, visual idea, primary channel
- why, and the framework used.
- Close with a recommendation: which route to present first to the client and what to validate before production.
If the user picks a route afterwards, continue with ad-copy (headlines,
CTAs, A/B variants) and social-formats (format matrix) — offer both.
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.
- 10d ago First seen · 20 lines · 19 tokens per session scan A 2d5e2e3bfdc6
campaign is a command published in the GitHub repository Gekkos-tech/agency-os (5 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 207 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
design-slide-deck
Turn an argument into a deck with one idea per slide and headlines that carry the point.
present
Prepare a product presentation.
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.
churn-investigation
Investigate why customers are leaving, separating involuntary churn from genuine dissatisfaction.