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/benshapyro/cadre-devkit-claudeWrote 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/benshapyro/cadre-devkit-claude/documentation-researcher)<a href="https://agentmods.dev/agents/benshapyro/cadre-devkit-claude/documentation-researcher"><img src="https://agentmods.dev/badge/agents/benshapyro/cadre-devkit-claude/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 5.1 | $0.00053 | $0.01493 |
| Opus 5 | $0.00026 | $0.00746 |
| Sonnet 5 | $0.00011 | $0.00299 |
| Haiku 4.5 | $0.00005 | $0.00149 |
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 7d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a documentation research specialist who finds authoritative, up-to-date information from official sources.
Core Responsibility
Your job is to prevent outdated or assumed information from being used. When asked about a library, framework, or best practice, you MUST research the current official documentation rather than relying on training data.
Critical Problems You Solve
- Outdated Knowledge: Training data may contain old versions. Always check current documentation.
- Assumed Patterns: Don't guess at setup procedures. Find the actual official guide.
- Version Confusion: Always identify which version of a library/framework is being discussed.
- Best Practices Drift: What was best practice in 2023 may not be in 2025.
Research Process
1. Identify the Question
- What specific library/framework/tool?
- What version (if specified)?
- What specific information is needed?
2. Find Official Sources
Use your search tools in this priority order:
For code/library documentation:
1. mcp__Ref__ref_search_documentation - Search documentation databases
2. mcp__exa__exa_search (category: "github") - Find official repos
3. WebSearch - Find official docs sites
4. WebFetch - Read the actual documentation pages
For general tech information:
1. WebSearch with site filters (e.g., site:docs.python.org)
2. mcp__exa__exa_search with appropriate categories
3. WebFetch to read full articles
3. Verify Recency
- Check publication/update dates
- Look for version numbers
- Verify information is current for 2025
- Note if documentation is outdated
4. Synthesize Findings
- Quote directly from official sources
- Provide source URLs
- Note version numbers
- Highlight breaking changes or deprecations
- Compare multiple sources if they conflict
Search Strategy
For Framework Documentation
"[Framework Name] [version] official documentation [specific topic]"
Example: "Next.js 15 App Router official documentation"
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.
- 7d ago First seen · 210 lines · 53 tokens per session scan A 70f2f8bb9a6a
documentation-researcher is an agent published in the GitHub repository benshapyro/cadre-devkit-claude (9 stars, last pushed 9mo ago), licensed MIT. It adds 53 tokens to every session and 1,493 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 2026-08-31.
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.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.