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/handoff)<a href="https://agentmods.dev/commands/gekkos-tech/agency-os/handoff"><img src="https://agentmods.dev/badge/commands/gekkos-tech/agency-os/handoff/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/handoff"><img src="https://agentmods.dev/badge/commands/gekkos-tech/agency-os/handoff.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 | $0.00023 | $0.00256 |
| Opus 5 | $0.00012 | $0.00128 |
| Sonnet 5 | $0.00005 | $0.00051 |
| Haiku 4.5 | $0.00002 | $0.00026 |
Grade A, and why
handoff 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 9d 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
Design handoff task: $ARGUMENTS
Load the agency-workflow skill (DESIGN phase reference) and:
- If design assets exist (generated section images, supplied designs,
a style guide): assemble the binding handoff structure —
design/tokens.md— palette hex, type scale, spacing, radius, shadows, motion rules (extract from the assets; do not invent)design/sections/— reference images named{page}-{nn}-{section}design/notes.md— breakpoints, interaction behavior, animation intent
- If the argument is "verify": audit the existing
design/folder for completeness — could a developer who never saw the concept build the site from it alone? List gaps. - If nothing exists yet: state that DESIGN must run first and route to
the
style-systems+imagegen-webskills.
Close with the DESIGN exit-gate checklist status.
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.
- 9d ago First seen · 23 lines · 23 tokens per session scan A b6752430f22c
handoff is a command published in the GitHub repository Gekkos-tech/agency-os (5 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 256 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
audit-accessibility
Audit a product against real assistive technology use, prioritised by who is blocked.
build-website
Build a small site with the simplest stack that fits, fast by default and editable afterwards.
onboarding-flow
Design an onboarding flow that gets a user to first value quickly, cutting everything that delays it.
review-accessibility
Review an interface for accessibility barriers, prioritised by who is blocked rather than by rule count.
dashboard
Design a product dashboard.
accessibility
Audit product accessibility.