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 OutlineDriven/odin-claude-plugin --skill handoff-promptgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/handoff-prompt)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/handoff-prompt"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/handoff-prompt/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/outlinedriven/odin-claude-plugin/handoff-prompt"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/handoff-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00062 | $0.01570 |
| Opus 5 | $0.00031 | $0.00785 |
| Sonnet 5 | $0.00012 | $0.00314 |
| Haiku 4.5 | $0.00006 | $0.00157 |
Grade A, and why
handoff-prompt 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 6d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff prompt
Contract
| Field | Bound contract |
|---|---|
| Trigger | User says handoff , write a handoff, delegate this, or wants a clipboard-ready prompt for another agent |
| Authority | Write only the assembled prompt text and the local clipboard; no repository, VCS, credential, paid, published, or remote mutation |
| Side effect | A standalone, path-free prompt is copied to the clipboard and the user gets a terse confirmation |
| Done | Prompt is on the clipboard, contains no filesystem paths, no invented facts, and gives the receiving agent enough context to orient and decide whether to proceed |
Inputs
Required: the task the user names or clearly implies.
Optional, gathered only to make the prompt useful: repo or product identity, relevant issue/PR/branch names or URLs, likely modules, constraints, known symptoms, and the desired output shape. Infer these from the current repo, recent discussion, branch name, linked issue/PR, docs, and obvious nearby context when the user gives only a short label. Do not perform the receiving agent's full independent review or decide its final technical direction.
Procedure
- Identify the task from the user text. When the user gives only a short label, infer the boundary from the current repo, recent discussion, branch name, linked issue/PR, docs, and obvious nearby context. Done when: the task is named in one sentence, and when inferred, the source of the inference (repo, branch, issue/PR, or discussion) is recorded.
- Gather enough context to orient a fresh agent: repo/product identity, relevant issue/PR/branch names or URLs, likely modules, constraints, known symptoms, and the desired output shape. Stop short of doing the receiving agent's review or picking its technical direction. Done when: repo identity, issue/PR references, likely modules, constraints, symptoms, and output shape are gathered or marked absent, and no receiving-agent review was performed.
- Assemble a standalone prompt using portable anchors only — repo owner/name, product or module names, issue/PR URLs, branch names, package or plugin names, public symbols, command names, config keys, exact error text, docs titles, and search terms. Include no absolute paths, home-directory paths, checkout names, or repo-relative file paths unless the user explicitly requests them. Done when: every anchor in the prompt is portable (repo owner/name, URLs, branch names, public symbols, command names, config keys, error text, docs titles, or search terms), and no filesystem path appears unless the user explicitly requested it.
- The first real instruction to the receiving agent must be to review, discuss, and assess — not a command-only work order. Make clear the receiving agent owns that review; the handoff gives only starting context and known constraints, and the agent should decide whether the task is still real, stale, already solved, over-scoped, or better handled differently. Done when: the first instruction to the receiving agent is to review, discuss, and assess, and the prompt states the agent owns that review.
- Include constraints, non-goals, validation expectations, the desired output shape, and an instruction to re-check live repo/GitHub/CI state where relevant. Tell the receiving agent not to push, merge, close issues/PRs, label, or post public comments unless the handoff explicitly asks for it. Done when: the prompt includes constraints, non-goals, validation expectations, output shape, and an instruction to re-check live state, plus an explicit ban on pushing, merging, closing, labeling, or posting without explicit request.
- Use this shape by default, filling each bracketed field from gathered context: Done when: every bracketed field in the template shape is filled from gathered context or marked as needing user input, and no field is left as a placeholder.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 77 lines · 62 tokens per session scan A 842cc400b4b0
handoff-prompt is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 62 tokens to every session and 1,570 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…