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 motlin/claude-code-plugins --skill recapgit clone --depth 1 https://github.com/motlin/claude-code-pluginsWrote 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/motlin/claude-code-plugins/recap)<a href="https://agentmods.dev/skills/motlin/claude-code-plugins/recap"><img src="https://agentmods.dev/badge/skills/motlin/claude-code-plugins/recap/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/motlin/claude-code-plugins/recap"><img src="https://agentmods.dev/badge/skills/motlin/claude-code-plugins/recap.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 | $0.00020 | $0.00536 |
| Opus 5.5 | $0.00008 | $0.00214 |
| Sonnet 5.5 | $0.00004 | $0.00107 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
recap 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recap Footer
End every message that returns control to the user with these two lines, after a blank line, as the last thing in the message:
📌 You asked: Make Claude end every turn with a recap and a link.
🔗 [PR #42](https://github.com/motlin/claude-code-plugins/pull/42)
The user multitasks. When they come back to the terminal they have forgotten what the session was about and have not scrolled up. The footer replaces the context they lost.
The recap line
One sentence restating the user's original request in their framing — not a summary of what you did.
- Good:
📌 You asked: Find out why the nightly build times out. - Bad:
📌 You asked: I added a timeout flag and reran the suite.
When a session covers several requests, recap the one currently being worked. When the current request is a follow-up, recap the thread it belongs to rather than the last message alone.
The link line
The URL the user is most likely to want next: pull request, issue, CI run, deployed site, dev server, documentation page, dashboard.
Always Markdown link syntax — 🔗 [short label](URL). A bare URL, with or without angle brackets, is not reliably turned into a link by every renderer, so it can arrive as text the user cannot click.
🔗 [CI run](https://github.com/motlin/claude-code-plugins/actions/runs/1234567890)
🔗 [Dev server](http://localhost:5173/)
🔗 None
- Prefer something created or discussed this session, even far earlier in the conversation — that is the case this footer exists for.
- Keep the label short and recognizable:
PR #42,CI run,Dev server. - Repeat a URL from earlier turns rather than dropping the line. The user has not scrolled up.
- Write
🔗 None, with no brackets, only when nothing applies.
Always both lines
Emit the footer on every turn: trivial answers, questions back to the user, refusals, and turns that changed nothing. Both lines are always present, even when the recap is short and the link is None.
The footer is the whole ending — do not follow it with more prose. A closing question to the user, or an AskUserQuestion call, comes before the footer.
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 510c17c2b2c3
- 22d ago Changed 40be4e763cbe
- 1mo ago First seen · 48 lines · 20 tokens per session scan A 79f65e7ca436
recap is a skill published in the GitHub repository motlin/claude-code-plugins (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 20 tokens to every session and 536 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 2026-09-04.
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…
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…