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 Tx1207/hello-scholar --skill handoffgit clone --depth 1 https://github.com/Tx1207/hello-scholarWrote 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/tx1207/hello-scholar/handoff)<a href="https://agentmods.dev/skills/tx1207/hello-scholar/handoff"><img src="https://agentmods.dev/badge/skills/tx1207/hello-scholar/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/tx1207/hello-scholar/handoff"><img src="https://agentmods.dev/badge/skills/tx1207/hello-scholar/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 | $0.00027 | $0.00575 |
| Opus 5.5 | $0.00011 | $0.00230 |
| Sonnet 5.5 | $0.00005 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00057 |
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.
How it starts
The opening of the file, as written. The whole thing — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
Give the next session enough context to take the right next action without replaying the conversation. Start from that action and work backward: what must the next agent know that it cannot reliably recover from durable sources?
Preserve the missing context
Use the Spec, acceptance evidence, code, tests, Git, Records, issues, and other artifacts to distinguish recoverable facts from session-only state. Briefly orient the reader to the current objective and link the relevant owners. Preserve only additional context that changes continuation: an unresolved user choice, a local constraint not yet captured, the ownership of unfinished work, a blocker, an active job the next session must not duplicate, or Runs, caches, and checkpoints it should reuse rather than recompute.
Explain a temporary choice through its reason and consequence, not a chronology of attempts. A discarded approach matters when its evidence would prevent the next agent from repeating an unproductive action. Preserve useful negative results through their source; do not rewrite them as failure to make the handoff sound complete.
Distinguish actions already performed, observations, and proposed next steps. Link recorded verification; include a check's actual command, result, and coverage only when those facts are otherwise unavailable. For ongoing external work, record the real job or process identifier and where to inspect it, rather than guessing its eventual result. Existing authorization and unresolved limits travel with the task; a handoff grants no new authority.
Make continuation concrete
State the first useful action, its prerequisite or blocker, and the evidence it should produce. Prefer a path or precise command when one is known. The next session should be able to explain why that action is next without searching the whole history. Do not require a full recheck of unchanged evidence merely because the agent changed.
Write hello-scholar/handoffs/YYYY-MM-DD-<topic>-handoff.md under the current project root, using an unused suffix for a distinct handoff or updating the identified ongoing one. Use assets/handoff-template.md for English or assets/handoff-template.zh_CN.md for Chinese, following the requested language and otherwise the project language. Merge or omit template divisions that add no useful context.
What ships with it
4 files 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.
- 9d ago Changed · +12 lines cfdb8705a55b
- 1mo ago Changed · -10 lines · +3 tokens per session 3229e00b0e4e
- 2mo ago First seen · 23 lines · 24 tokens per session scan A 5608f4d9638d
handoff is a skill published in the GitHub repository Tx1207/hello-scholar (10 stars, last pushed 4d ago), licensed MIT. It adds 27 tokens to every session and 575 once invoked, about $0.0001 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
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…