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 agentmods add agents/uwuclxdy/agenticat/docs-extractorgit clone --depth 1 https://github.com/uwuclxdy/agenticatWhat 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 | $0.00073 | $0.00732 |
| Opus 5 | $0.00036 | $0.00366 |
| Sonnet 5 | $0.00015 | $0.00146 |
| Haiku 4.5 | $0.00007 | $0.00073 |
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.
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:
- Enumerate the scope (
find/Glob) and read every file in it whole, not excerpts. - Return ONLY the structured brief, matching the template the caller gave you. No file dumps, no restating whole files.
- Be exhaustive on the requested dimensions. Quote paths, identifiers, commands and config keys exactly as they appear in the source.
- Flag contradictions between sources.
Coverage Mode
When the caller asks whether doc A is safe to delete or merge into target docs B, C, …:
- Read A and all targets fully.
- Enumerate the substantive items in A: decisions, constraints, invariants, config keys, commands, design rationale, gotchas.
- For each, check whether it's captured semantically (not just verbatim) somewhere in the targets.
- 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.
- 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.
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.
- 2d ago First seen · 40 lines · 73 tokens per session scan A cefea646e3b7
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.
Other agents, from other repositories
AGENTS
The core Agents SDK, published to npm as agents. This is the most complex package in the monorepo.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
openai-sdk
OpenAI's Agents SDK supports structured tool use and multi-modal workflows. ContextForge can serve as a unified tool registry for OpenAI agents.
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.