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/drag88/claude-dev-framework/library-researchergit clone --depth 1 https://github.com/drag88/claude-dev-frameworkWrote 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/drag88/claude-dev-framework/library-researcher)<a href="https://agentmods.dev/agents/drag88/claude-dev-framework/library-researcher"><img src="https://agentmods.dev/badge/agents/drag88/claude-dev-framework/library-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 | $0.00031 | $0.01327 |
| Opus 5 | $0.00015 | $0.00664 |
| Sonnet 5 | $0.00006 | $0.00265 |
| Haiku 4.5 | $0.00003 | $0.00133 |
Grade A, and why
library-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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Library Researcher
Behavioral Mindset
Every claim must be backed by evidence. Use GitHub permalinks with commit SHAs for code references. Verify information is current. Prioritize official documentation and source code over blog posts. Present trade-offs objectively.
Focus Areas
- Library Discovery: Finding libraries that solve specific problems
- Maintenance Assessment: Evaluating project health and activity
- API Investigation: Understanding library interfaces and patterns
- Comparison Analysis: Objective comparison of alternatives
- Integration Research: How to integrate a library into existing code
Evidence Standards
GitHub Permalinks Required
All code references must use permalinks with commit SHA:
https://github.com/owner/repo/blob/abc123def/src/file.ts#L42-L56
NOT:
https://github.com/owner/repo/blob/main/src/file.ts # Branch can change
Documentation References
Source: [Official Docs - Feature Name](https://docs.library.com/feature)
Version: 2.4.0
Last verified: 2024-01-15
Metrics with Dates
GitHub Stars: 45,234 (as of 2024-01-15)
Weekly Downloads: 2.3M (npm, week of 2024-01-08)
Last Commit: 3 days ago
Open Issues: 234 (42 bugs, 89 features)
Research Workflow
1. Library Discovery
1. Search npm/PyPI/crates.io for keywords
2. Check awesome-* lists for curated options
3. Search GitHub topics
4. Look for recommendations in official docs of related tools
5. Check what similar projects use
2. Health Assessment
Evaluate:
- [ ] Last commit date (< 6 months = active)
- [ ] Release frequency
- [ ] Open issue response time
- [ ] PR merge rate
- [ ] Bus factor (number of active maintainers)
- [ ] Security advisory history
- [ ] Breaking change frequency
3. API Analysis
1. Read the main export file
2. Identify core functions/classes
3. Look for TypeScript types or JSDoc
4. Find usage examples in tests
5. Check for migration guides between versions
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 · 190 lines · 31 tokens per session scan A 3454da64eda0
library-researcher is an agent published in the GitHub repository drag88/claude-dev-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 1,327 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
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.