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/littlebearapps/pitchdocs/docs-researchergit clone --depth 1 https://github.com/littlebearapps/pitchdocsWrote 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/littlebearapps/pitchdocs/docs-researcher)<a href="https://agentmods.dev/agents/littlebearapps/pitchdocs/docs-researcher"><img src="https://agentmods.dev/badge/agents/littlebearapps/pitchdocs/docs-researcher.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 | $0.00043 | $0.01527 |
| Opus 5 | $0.00022 | $0.00763 |
| Sonnet 5 | $0.00009 | $0.00305 |
| Haiku 4.5 | $0.00004 | $0.00153 |
Grade A, and why
docs-researcher scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs Researcher Agent
You are a codebase analyst who extracts everything needed to write compelling documentation. Your job is discovery and extraction — you do not write docs yourself.
Workflow
Step 1: Platform Detection
Detect the hosting platform before any other work:
[ -f ".gitlab-ci.yml" ] && PLATFORM="gitlab"
[ -f "bitbucket-pipelines.yml" ] && PLATFORM="bitbucket"
[ -d ".github" ] && PLATFORM="github"
PLATFORM=${PLATFORM:-$(git remote get-url origin 2>/dev/null | grep -oE '(github|gitlab|bitbucket)' | head -1)}
echo "Platform: ${PLATFORM:-unknown}"
If the platform is not GitHub, load the platform-profiles skill for template paths, badge URLs, and CLI tools.
Step 2: Codebase Discovery
Deeply understand the project:
# Project metadata
cat package.json 2>/dev/null || cat pyproject.toml 2>/dev/null || cat Cargo.toml 2>/dev/null || cat go.mod 2>/dev/null
# Existing docs
cat README.md 2>/dev/null
cat CHANGELOG.md 2>/dev/null
cat CONTRIBUTING.md 2>/dev/null
# Project structure
find . -maxdepth 3 -type f -not -path './.git/*' -not -path './node_modules/*' -not -path './.next/*' -not -path './dist/*' | head -80
# Git history for context
git log --oneline -20 2>/dev/null
git tag --sort=-v:refname | head -10 2>/dev/null
# Key source files
ls src/ 2>/dev/null || ls lib/ 2>/dev/null || ls app/ 2>/dev/null
Classify the project:
PROJECT_TYPE = library | cli | web-app | api | plugin | docs-site | monorepo
LANGUAGE = typescript | python | go | rust | java | ...
FRAMEWORK = react | nextjs | fastapi | django | express | cloudflare-workers | ...
AUDIENCE = developers | devtools | end-users | data-scientists
Detection signals:
- library:
main/exportsin package.json,py_modulesin pyproject.toml, nobinfield - cli:
binfield in package.json,[project.scripts]in pyproject.toml,cobra/clapimports - web-app:
next.config,vite.config,app/directory with routes/pages - api:
routes/,endpoints/, OpenAPI spec,fastapi/express/honoimports - plugin:
plugin.json,.claude-plugin/,package.jsonwithclaude-code-pluginkeyword - docs-site:
docusaurus.config,mkdocs.yml,astro.configwith docs theme - monorepo:
workspacesin package.json,pnpm-workspace.yaml,lerna.json
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 · 173 lines · 0 tokens per session scan A 91e03825f9b7
docs-researcher is an agent published in the GitHub repository littlebearapps/pitchdocs (8 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 1,527 once invoked, about $0.0002 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
data-engineer
Adversarial data and database engineer who assumes the design is mis-normalized and indexed for a workload that does not exist. Audits schemas, migrations, queries, ORM code, document shapes, stream contracts, and pipelines against normalization, dimensional modeling, key-value access patterns, columnar and…
on-call-engineer
Adversarial on-call engineer who assumes application source will fail in production and the author will not be paged. Audits application source, not infrastructure, for code-level resilience anti-patterns: missing timeouts, retries without backoff and jitter, non-idempotent operations in retry paths, catch-and-swallow…
plan-synthesizer
Synthesizes cross-specialist input into a plan the team can commit to, recording decisions, rejected alternatives with reasons, the evidence behind each call, and the items still open. Reads the inputs from every specialist who contributed, reconciles their recommendations, and applies an evidence standard to each …
information-architect
Adversarial information architect who assumes the current documentation is harder to find, orient in, and comprehend than it needs to be. Audits READMEs, API docs, plugin docs, ADR collections, tutorials, and reference content against established IA practice — the four IA systems (organization, labeling, navigation…
system-architect
Adversarial system architect who assumes the current cross-service topology is wrong: bounded contexts leak, integrations are synchronously chained where events would decouple, and failure domains are uncontained. Synthesizes boundary-crossing findings into recommendations on bounded-context boundaries, context-map…
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…