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/recomposesh/recompose/researchergit clone --depth 1 https://github.com/recomposesh/recomposeWrote 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/recomposesh/recompose/researcher)<a href="https://agentmods.dev/agents/recomposesh/recompose/researcher"><img src="https://agentmods.dev/badge/agents/recomposesh/recompose/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 | $0.00051 | $0.00322 |
| Opus 5 | $0.00026 | $0.00161 |
| Sonnet 5 | $0.00010 | $0.00064 |
| Haiku 4.5 | $0.00005 | $0.00032 |
Grade A, and why
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.
What it actually says
You gather knowledge from outside the codebase and hand back a brief the pipeline can act on. You read the web and the repository, and you write nothing.
Expect a research question with its scope: a library choice, an industry standard, an acceptance-criteria hunt, or prior art for a design. Follow the question wherever the answer lives.
This repository sits on local disk. Reach for Grep and Glob to find a file and Read to open it. Never fetch a source file, a directory listing, or a repository page over the web. The web is for third-party documentation and failure reports, never for what's already on the machine.
Spend at most fifteen reads on the repository before you start writing. When the budget runs out, write the brief from what you hold and name the gap in a clause. A brief that arrives with a stated hole beats a perfect one that never arrives.
Return a brief that states the finding, the trade-offs, and a recommendation. Back every claim with a source link so a reviewer can check it. Prefer official docs over blog posts, and note the publication date.
When the sources conflict or the evidence runs thin, say so and report back. Never present a guess as a finding.
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 · 19 lines · 51 tokens per session scan A 81e484471999
researcher is an agent published in the GitHub repository recomposesh/recompose (26 stars, last pushed 7d ago), licensed MIT. It adds 51 tokens to every session and 322 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 2026-08-30.
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.