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.
git clone --depth 1 https://github.com/ikotelkin/claude-skillsWrote 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/agents/ikotelkin/claude-skills/extractor)<a href="https://agentmods.dev/agents/ikotelkin/claude-skills/extractor"><img src="https://agentmods.dev/badge/agents/ikotelkin/claude-skills/extractor/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/agents/ikotelkin/claude-skills/extractor"><img src="https://agentmods.dev/badge/agents/ikotelkin/claude-skills/extractor.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 | $0.00060 | $0.00327 |
| Opus 5 | $0.00030 | $0.00163 |
| Sonnet 5 | $0.00012 | $0.00065 |
| Haiku 4.5 | $0.00006 | $0.00033 |
Grade A, and why
extractor 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 4d 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.
What it actually says
You are an extractor. You transform files into the shape the brief asks for and change nothing else.
- Read only the files the brief points to (or the glob it gives). Do not go looking for more context.
- Produce exactly the output the brief specifies — a table, a JSON array, a deduplicated list, a normalised file. When the brief leaves the shape open, use the simplest shape that holds every field you found.
- Never invent a value. A missing field stays empty and is counted in your digest.
- Write the result to the path in the brief; if none is given, write next to the source with a
-extractedsuffix and say so. - Ambiguity is reported, not resolved: list the cases you were unsure about with the input that caused them.
Your final message is short: what you read, what you wrote (path), row/item counts, and the list of unsure cases. No content echo — the file is the deliverable.
You cannot spawn agents. If the job is too large for your turn budget, process as much as you can, write it, and say precisely where you stopped so the caller can continue.
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.
- 4d ago First seen · 20 lines · 60 tokens per session scan A b71fe205031e
extractor is an agent published in the GitHub repository ikotelkin/claude-skills (3 stars, last pushed 5d ago), licensed MIT. It adds 60 tokens to every session and 327 once invoked, about $0.0003 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 2026-09-08.
Other agents, from other repositories
doc-keeper
Repairs docs already in the corpus — single-file upsert/delete, metadata and staleness fixes, and edits driven by a drift report. Use for targeted edits to existing docs; bulk ingest or crawl is corpus-sync, and finding drift is doc-reviewer.
remediation-agent
Applies verified documentation findings to one file with the smallest safe change set, then re-runs native validators and the STE lint.
technical-writer
Use when: creating or improving technical documentation — API reference, user guides, tutorials, architecture docs. Do NOT use for: designing the API contract itself (use api-designer) or writing implementation code.
docs-manager
Use this agent when you need to manage technical documentation, establish implementation standards, analyze and update existing documentation based on code changes, write or update Product Development Requirements (PDRs), organize documentation for developer productivity, or produce documentation summary reports. This…
web-researcher
Searches the web for a specific research query and returns a compressed finding with cohort-diverse citations and source-type annotations. Use when the parent recipe needs current-web information — especially fast-moving landscape/tooling topics where model priors can't be trusted.
researcher
Use this agent when you need to conduct comprehensive research on software development topics, including investigating new technologies, finding documentation, exploring best practices, or gathering information about plugins, packages, and open source projects. This agent excels at synthesizing information from…