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.
npx skills add hams-ollo/zen-agent-skills --skill agent-handoffgit clone --depth 1 https://github.com/hams-ollo/zen-agent-skillsWrote 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/skills/hams-ollo/zen-agent-skills/agent-handoff)<a href="https://agentmods.dev/skills/hams-ollo/zen-agent-skills/agent-handoff"><img src="https://agentmods.dev/badge/skills/hams-ollo/zen-agent-skills/agent-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/skills/hams-ollo/zen-agent-skills/agent-handoff"><img src="https://agentmods.dev/badge/skills/hams-ollo/zen-agent-skills/agent-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 | $0.00128 | $0.01540 |
| Opus 5.5 | $0.00051 | $0.00616 |
| Sonnet 5.5 | $0.00026 | $0.00308 |
| Haiku 4.5 | $0.00013 | $0.00154 |
Grade A, and why
agent-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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent handoff
Write a brief that a downstream agent session or subagent can execute on its own, with no access to the current conversation. The reader is a machine that will act on what you write, so the brief has to be self-contained, unambiguous about what not to touch, and precise about what is already true. When the handoff target is a person rather than an agent, use human-handoff instead.
Why this shape
A fresh session starts cold. It cannot see what was decided here, what was already tried, or which files matter. Most bad handoffs fail in one of three ways: the agent re-does work that is already done, the agent wanders into files or decisions it should have left alone, or the agent acts on a stale assumption because the brief never pinned down what was actually proven and when. The five sections below exist to close those three gaps. Keep the whole thing tight; a brief the reader will not finish is worse than a short one.
Before writing: gather the real state
Do not write the brief from memory of the conversation alone. Ground it in the repository as it actually is right now, because that is what the downstream agent will see.
- If the repo has an
AGENTS.mdorCLAUDE.md, read it. Inherit its reading protocol, task lifecycle, and conventions rather than restating them. If it defines a task system (for example.tasks/), the brief should point the agent at the relevant task file instead of duplicating its content. - Check
git statusand recent changes so the "what is proven" section reflects the working tree, not your recollection. - Identify the exact files the work touches. Name them by path. If you are unsure a file is relevant, it probably is not; a shorter reading list is better than a padded one.
Output structure
Produce one contiguous block the user can copy in a single action. Use this order. The section labels can be light; the content is what matters.
1. Role and mode
State who the agent is for this task and, critically, what mode it is in. The sharpest handoffs name the mode as a boundary: an analysis and recommendation task is not an implementation task, and saying so up front prevents the agent from writing code when you wanted a written plan. Example framing: "You are doing an architectural deep-dive, not implementation. The deliverable is a written analysis, nothing more."
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.
- 7d ago Changed · -3 lines · -58 tokens per session 37e1dae3896a
- 1mo ago Changed · +7 lines f6e20f66b960
- 2mo ago First seen · 88 lines · 186 tokens per session scan A a0f7ac9cbe71
agent-handoff is a skill published in the GitHub repository hams-ollo/zen-agent-skills (2 stars, last pushed 7d ago), licensed MIT. It adds 128 tokens to every session and 1,540 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
review
Use when explicitly invoked to review a branch diff (or any diff or files pointed at) with a find-only subagent covering rubric and conventions, change conformance against the AC-N and their runtime-verification evidence, and documentation consistency — one plain-text verdict that reaches lgtm only when no dimension…
implement
Use when explicitly invoked to execute a change's tasks.md from the first unticked step: implement each task, run its validation, commit, then run the quality gate and verify every acceptance criterion by observed behavior. Needs no conversation context — the change folder is the whole input. Trigger on…
archive
Use when explicitly invoked to close out a change whose branch has already merged: confirm the merge from git alone, then move the change folder under changes/archive/ with its ship date. Trigger on '/sw:archive', '$sw:archive', 'archive this change', or a request to close out a merged change.
ship
Use when explicitly invoked to run the whole change ladder without stopping — ticket, plan, implementation, quality gate, runtime verification, review to lgtm — deciding every open question autonomously and recording each decision in proposal.md. Trigger on '/sw:ship', '$sw:ship', or a request to take something from…
gsd-audit-milestone
Audit milestone completion against original intent before archiving.
spec-kitty-charter-doctrine
Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…