Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ao92265/claude-code-playbook/plugin install playbookWrote 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/ao92265/claude-code-playbook/skill-capture)<a href="https://agentmods.dev/skills/ao92265/claude-code-playbook/skill-capture"><img src="https://agentmods.dev/badge/skills/ao92265/claude-code-playbook/skill-capture.svg" alt="Measured on agentmods" 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 | $0.00194 | $0.02302 |
| Opus 5 | $0.00097 | $0.01151 |
| Sonnet 5 | $0.00039 | $0.00460 |
| Haiku 4.5 | $0.00019 | $0.00230 |
Grade A, and why
skill-capture 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Capture
Merges four overlapping capture workflows into one skill with four modes. Pick the mode from how the user (or the situation) invoked this skill; if ambiguous, ask.
| Trigger phrase | Mode |
|---|---|
| "learn from this session", "autoskill", "what did you learn" | corrections |
| "extract a skill", "learner" | extract |
| "skillify", "turn this into a skill" | workflow |
| "watch for skill opportunities", start of a multi-step task | observe |
Shared Quality Gate
Before capturing anything in corrections, extract, or workflow mode,
all three must be true:
- Non-Googleable — could someone find this via a 5-minute search? If yes, discard (BAD: "use try/catch for error handling"; GOOD: "the aiohttp proxy in server.py:42 crashes on ClientDisconnectedError — wrap StreamResponse in try/except").
- Specific — is it tied to this codebase, project, or team, with actual file paths, error messages, or line numbers? Generic patterns, library usage, and boilerplate belong in documentation, not here.
- Hard-won — did it take real debugging, correction, or operational effort to surface, and does it apply beyond a single file or one-off task?
If any check fails, discard the candidate and move on.
Mode: corrections (was autoskill)
Analyze the current or recent session for correction signals — places where
the user stated a team/project preference or corrected an approach — and
turn qualifying ones into skill or CLAUDE.md updates.
- Resolve project context. Extract the project name from
$CWD(e.g./Users/aoreilly/Repos/Wraith→wraith). Check whether.claude/skills/exists in the project root. - Subcommands (from
$ARGUMENTS):review= steps 3-5 only, propose without applying;history= rungit log --oneline --grep="autoskill:"and stop;apply= skip to step 5 using previously proposed learnings;global= restrict search/output to cross-project preferences; no argument = run steps 3-5 in full. - Search for signals. Query
mcp__historian__search_conversationsfor"no use instead|don't use|we always|we never|our convention|team prefers|standard practice"and separately for"Actually|Wrong|not like that|stop doing", filtered to the current project. No signals → report "No correction signals detected" and stop. - Filter each signal against the Shared Quality Gate above, plus: team-relevant? (benefits the whole project, not one person's taste). Drop anything that fails.
- Map each surviving signal to a target file:
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 · 199 lines · 194 tokens per session scan A 83e919351d02
skill-capture is a skill published in the GitHub repository ao92265/claude-code-playbook (10 stars, last pushed 20d ago), licensed MIT. It adds 194 tokens to every session and 2,302 once invoked, about $0.0010 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…