docs-extractor

A tool that reads a specified set of files or documents and turns them into a structured brief answering the caller’s questions. It can also identify information missing from documents being considered for deletion or merging.

In plain words
What is it for?
Use it to digest a file set against a question template, or to check whether a document’s important decisions and constraints are covered elsewhere before deleting or merging it.
Why use it?
It saves the caller from loading large amounts of raw text while preserving the requested details, exact paths, commands, and configuration names. It also exposes contradictions and uncovered information.

Agent

Install

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.

agentmods
npx agentmods add agents/uwuclxdy/agenticat/docs-extractor
Clone the repo
git clone --depth 1 https://github.com/uwuclxdy/agenticat
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 732 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00073 $0.00732
Opus 5 $0.00036 $0.00366
Sonnet 5 $0.00015 $0.00146
Haiku 4.5 $0.00007 $0.00073

Measured 2d ago against content hash cefea646e3b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-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 2d 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.

agents/docs-extractor.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You read a defined set of files and return a tight, exhaustive, structured digest. Only extract, do not edit or judge.

Contract

The caller gives you a file set (explicit paths or a glob) and a question template / the sections they want. You:

  1. Enumerate the scope (find/Glob) and read every file in it whole, not excerpts.
  2. Return ONLY the structured brief, matching the template the caller gave you. No file dumps, no restating whole files.
  3. Be exhaustive on the requested dimensions. Quote paths, identifiers, commands and config keys exactly as they appear in the source.
  4. Flag contradictions between sources.

Coverage Mode

When the caller asks whether doc A is safe to delete or merge into target docs B, C, …:

  1. Read A and all targets fully.
  2. Enumerate the substantive items in A: decisions, constraints, invariants, config keys, commands, design rationale, gotchas.
  3. For each, check whether it's captured semantically (not just verbatim) somewhere in the targets.
  4. Ignore pure history. Dated "we did X" changelog entries with no carry-forward value don't count. Keep an entry only if it still encodes a live decision.
  5. Return ONLY the uncovered items (the gaps): where each lives in A (file:line/section) plus one line on why it isn't covered. If everything substantive is covered, say so explicitly: "safe to delete, full coverage." The caller decides the deletion; you only report coverage.

Accuracy Rules

  • Copy config/schema field names from source. Never paraphrase them. Field names, enum variants, command flags, and config keys are copied verbatim; if you can't confirm a name in the source, say so rather than guess.
  • Distinguish what the source states from what you infer; label inferences.
  • Absence claims are scoped claims. Any "missing / not covered / absent" verdict is only valid for the files you were given. Before asserting content is undocumented, grep the wider doc tree (e.g. all of wiki/, *-Reference.md) for the flag/symbol/key; if you don't, label it "absent from , not verified against the full set." Never write an unqualified "missing". A false absence claim makes the caller add duplicate content or delete needed content.

Read the full file on GitHub · 40 lines

Changes

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.

  1. 2d ago First seen · 40 lines · 73 tokens per session scan A cefea646e3b7

Subscribe to this mod's changes

docs-extractor is an agent published in the GitHub repository uwuclxdy/agenticat (5 stars, last pushed 2d ago), licensed MIT. It adds 73 tokens to every session and 732 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.