Borrowing it
Nothing to install: this file belongs to dzhng/duet-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dzhng/duet-agent/main/.agents/skills/handoff-spec/SKILL.mdgit clone --depth 1 https://github.com/dzhng/duet-agentWrote 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/dzhng/duet-agent/handoff-spec)<a href="https://agentmods.dev/skills/dzhng/duet-agent/handoff-spec"><img src="https://agentmods.dev/badge/skills/dzhng/duet-agent/handoff-spec/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/dzhng/duet-agent/handoff-spec"><img src="https://agentmods.dev/badge/skills/dzhng/duet-agent/handoff-spec.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 | $0.00319 |
| Opus 5.5 | $0.00008 | $0.00128 |
| Sonnet 5.5 | $0.00004 | $0.00064 |
| Haiku 4.5 | $0.00002 | $0.00032 |
Grade A, and why
handoff-spec 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 25d 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.
This is a copy
100% identical to handoff-spec — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Handoff Spec
I'm moving this spec's work to another machine or another agent. The next session starts cold: it has the repository and nothing else. It has none of this conversation, none of this machine's files and none of your memory. Leave the spec so that session can carry on as if it had been here.
Collect what this session knows and the spec doesn't yet say, from the discussion and from the work itself, and put it in the spec:
- what is done, what is half-done and exactly where it stopped, and what is next;
- what I decided or corrected along the way, and how I want the work done;
- calls you made where I was silent, and anything still waiting on me;
- what is known to be broken or unverified, with what you already found out about it;
- anything that lives only on this machine and the next session needs: unpushed branches, uncommitted work, scratch results worth keeping.
Write it into the spec's own handoff, in place: the spec stays one current account, not a transcript with a new note on top. Then push, so everything the spec points at exists on the remote.
Done when a fresh agent, given only the repository, would pick the same next step you would, and would not repeat a question I've already answered.
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.
- 25d ago First seen · 32 lines · 19 tokens per session scan A e902beff153a
handoff-spec is a skill published in the GitHub repository dzhng/duet-agent (52 stars, last pushed 7d ago), licensed Apache-2.0. It adds 19 tokens to every session and 319 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to handoff-spec, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
evaluator-write-qa-parallel
Internal Auto-Harness evaluator skill for parallel sprint QA and QA report writing. Use only inside the Evaluator subagent during evaluatorqaparallel.
evaluator-write-qa
Internal Auto-Harness evaluator skill for sprint QA and QA report writing. Use only inside the Evaluator subagent during qa mode.
evaluator-write-retest-parallel
Internal Auto-Harness evaluator skill for parallel sprint retest and retest report writing. Use only inside the Evaluator subagent during evaluatorretestparallel.
evaluator-write-retest
Internal Auto-Harness evaluator skill for sprint retest and retest report writing. Use only inside the Evaluator subagent during retest mode.
generator-fix-integrator
Internal Auto-Harness generator skill for worktree-merge fix integration. Use only inside the parallel Generator integrator when it is addressing named defects from QA or retest.