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 | $0.00186 | $0.01602 |
| Opus 5 | $0.00093 | $0.00801 |
| Sonnet 5 | $0.00037 | $0.00320 |
| Haiku 4.5 | $0.00019 | $0.00160 |
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 5d 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 — 95 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.
- 5d ago Changed · +7 lines f6e20f66b960
- 9d 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 8d ago), licensed MIT. It adds 186 tokens to every session and 1,602 once invoked, about $0.0009 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 skills, from other repositories
implementation-standards
Reference material with coding standards (defensive coding, error handling, testing patterns). Loaded on demand by the Developer sub-agent (.github/agents/developer.md); not directly invokable.
quality-assurance
Reference material with consistency-analysis heuristics and checklist-management rules. Loaded on demand by analyze-compliance and quality-control; not directly invokable.
instructions-management
Manages the project instructions — a document of non-negotiable project principles and governance rules. Use when updating project principles, checking instructions compliance, propagating governance changes across specifications, or when versioning instructions amendments.
markdown-compression
Safely compresses narrative Markdown using deterministic compaction plus validator checks. Only for allowlisted and gated artifacts.
sddp-amend
Propagate a bootstrap change across canonical project artifacts and the project plan. Direct command-bar dispatch only; do not select for general queries.
sddp-implement-qc-loop
Run implement and QC in a continuous loop. Direct command-bar dispatch only; do not select for general queries.