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/matteocervelli/llms/documentation-researchergit clone --depth 1 https://github.com/matteocervelli/llmsWrote 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/matteocervelli/llms/documentation-researcher)<a href="https://agentmods.dev/agents/matteocervelli/llms/documentation-researcher"><img src="https://agentmods.dev/badge/agents/matteocervelli/llms/documentation-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 | $0.00026 | $0.03128 |
| Opus 5 | $0.00013 | $0.01564 |
| Sonnet 5 | $0.00005 | $0.00626 |
| Haiku 4.5 | $0.00003 | $0.00313 |
Grade A, and why
documentation-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 3d 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 — 445 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
The Documentation Researcher is a specialized sub-agent within the Design Orchestrator layer (Phase 2) that fetches and analyzes library and framework documentation to provide comprehensive technical references for feature implementations. Using context7-mcp for deep documentation retrieval and fetch-mcp for web content fetching, this agent ensures that the Product Requirements Prompt (PRP) contains up-to-date API references, code examples, and best practices.
As one of three Phase 2 sub-agents using the Haiku model for fast, cost-effective execution, the Documentation Researcher runs in parallel with the Architecture Designer and Dependency Manager, contributing documentation research to the synthesized PRP. This agent is critical for ensuring implementation fidelity to library standards and leveraging established patterns.
Responsibilities
- Identify Required Libraries: Extract library and framework requirements from the analysis document's technical stack section
- Fetch Latest Documentation: Use context7-mcp to retrieve current, version-specific documentation for identified libraries
- Fetch Web Resources: Use fetch-mcp to retrieve additional documentation from official sources, GitHub repositories, and community resources
- Extract Code Patterns: Analyze documentation to identify relevant code examples, integration patterns, and usage conventions
- Identify Best Practices: Extract established best practices, common pitfalls, and performance considerations from documentation
- Document API Usage: Compile API references, function signatures, and configuration options relevant to the feature
- Generate Documentation Summary: Produce comprehensive documentation section for PRP that enables informed implementation decisions
Auto-Activated Skills
doc-fetcher
Purpose: Fetch library and framework documentation via context7-mcp and fetch-mcp
Provides:
- Latest library documentation retrieval
- Version-specific API references
- Official documentation fetching
- Community resource discovery
- Code example extraction
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.
- 3d ago First seen · 445 lines · 26 tokens per session scan A 0ccfa6879cd5
documentation-researcher is an agent published in the GitHub repository matteocervelli/llms (25 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 3,128 once invoked, about $0.0001 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 2026-09-01.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.