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 MintoTsukino/cathub-nyaanes --skill nyaanes-handoffgit clone --depth 1 https://github.com/MintoTsukino/cathub-nyaanesWrote 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/mintotsukino/cathub-nyaanes/nyaanes-handoff)<a href="https://agentmods.dev/skills/mintotsukino/cathub-nyaanes/nyaanes-handoff"><img src="https://agentmods.dev/badge/skills/mintotsukino/cathub-nyaanes/nyaanes-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/mintotsukino/cathub-nyaanes/nyaanes-handoff"><img src="https://agentmods.dev/badge/skills/mintotsukino/cathub-nyaanes/nyaanes-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 | $0.00083 | $0.00603 |
| Opus 5 | $0.00042 | $0.00302 |
| Sonnet 5 | $0.00017 | $0.00121 |
| Haiku 4.5 | $0.00008 | $0.00060 |
Grade A, and why
nyaanes-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 11d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nyaanes Handoff
Use CatHub's MCP tools as the shared handoff lane. Do not edit board Markdown or read-state files directly.
Identity
Use the fixed provider ID, not the customizable display name:
- Claude:
claude - Codex:
codex - Grok:
grok
Check in
- Call
check_inonce when beginning or resuming a work session, or when the user asks for unread updates. - Pass the current provider ID as
reader. - Briefly report new decisions, blockers, handoffs, and next steps. Do not repeat the full board response unless asked.
- If there are no unread posts, continue without ceremony.
- If CatHub is unavailable, mention it once and continue the user's work. Do not retry in a loop.
Check out
Call check_out only when the user performs an explicit declaration that the current work session is ending.
Valid examples:
- 「今日はここまで」
- 「この作業は終わり」
- 「作業終了。引き継ぎを残して」
- 「もう閉じるから報告して」
These are not end declarations:
- Hypothetical or instructional wording such as 「終えるときは報告して」
- Questions such as 「終了報告はどうする？」
- Completion of one job, test, build, or response
- 「ありがとう」「了解」だけ
- Silence, inactivity, app closure, timeout, or session disconnect
If the wording is ambiguous, do not call check_out.
When the declaration is valid:
- Use verified conversation and workspace facts to prepare
completed,decisions,blockers,nextStep, andrelatedPaths. - Set
userDeclaredEndtotrue. - Copy the user's actual declaration verbatim into
declaration. Never invent or paraphrase it as evidence. - Call
check_outonce with the current provider ID asauthor. - Confirm the saved handoff briefly. Do not start a new task afterward unless the user asks.
Safety invariants
- Never check out merely because an agent job completed.
- Never check out automatically at the end of an assistant response.
- Never turn a policy discussion about ending work into an actual end declaration.
- Never fabricate completed work, decisions, blockers, paths, or the user's declaration.
- Keep check-out reports concise enough for the next agent to scan quickly.
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.
- 11d ago First seen · 62 lines · 83 tokens per session scan A 8c557dd882cf
nyaanes-handoff is a skill published in the GitHub repository MintoTsukino/cathub-nyaanes (0 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 603 once invoked, about $0.0004 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
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…
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…