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 alphabravo-oss/guild --skill extractiongit clone --depth 1 https://github.com/alphabravo-oss/guildWrote 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/alphabravo-oss/guild/extraction)<a href="https://agentmods.dev/skills/alphabravo-oss/guild/extraction"><img src="https://agentmods.dev/badge/skills/alphabravo-oss/guild/extraction/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/alphabravo-oss/guild/extraction"><img src="https://agentmods.dev/badge/skills/alphabravo-oss/guild/extraction.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 | $0.00035 | $0.00638 |
| Opus 5.5 | $0.00014 | $0.00255 |
| Sonnet 5.5 | $0.00007 | $0.00128 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
extraction 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 1mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extraction
The rule
A reference page is extracted, not written.
A model writing an API reference from a code read produces a table that is correct on the day and wrong by the next commit, because nothing regenerates it. An extractor cannot drift, because it is re-run against the source of truth.
What a person adds around the extracted output is the part worth writing by hand: why this endpoint exists, what it refuses to do, what the reader should reach for instead. That is explanation, and it belongs on a different page from the reference.
What comes from where
| Reference material | Source of truth | Tool |
|---|---|---|
| Exported TypeScript types | The types | typedoc |
| Public API surface of a package | The types | @microsoft/api-extractor, which also reports surface changes between versions |
| HTTP endpoints, with an OpenAPI spec | The spec | @scalar/api-reference to render, redocly lint to govern |
| HTTP endpoints, no spec | The route files | scripts/survey.py, which enumerates them with anchors |
| Environment and config | .env.example and the loader |
scripts/survey.py |
| Python API | Docstrings | mkdocstrings |
| Go packages | The source | go doc |
| Changelog | Commits and tags | The changelog skill |
Run scripts/survey.py first. Its tooling block names the extractors that fit this repo and
the exact command for each.
When there is no spec and no extractor
This is the common case for an app rather than a library, and it is where invention happens.
- Take the surface from
scripts/survey.py. Every entry carries afile:lineanchor. - Read each handler. Do not summarise from the route name.
- Request and response shapes come from the types or the validation code, quoted with anchors.
If neither exists, the shape is
[?]and says so. - Status codes come from the code paths that return them, not from convention. A
429that is documented but never returned is worse than an undocumented one. - Never document a field you cannot point at.
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.
- 1mo ago First seen · 60 lines · 35 tokens per session scan A 10cd80e40412
extraction is a skill published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 15d ago), licensed MIT. It adds 35 tokens to every session and 638 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…