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/mp-web3/claude-starter-kit/researchergit clone --depth 1 https://github.com/mp-web3/claude-starter-kitWrote 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/mp-web3/claude-starter-kit/researcher)<a href="https://agentmods.dev/agents/mp-web3/claude-starter-kit/researcher"><img src="https://agentmods.dev/badge/agents/mp-web3/claude-starter-kit/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 | $0.00029 | $0.01139 |
| Opus 5 | $0.00015 | $0.00570 |
| Sonnet 5 | $0.00006 | $0.00228 |
| Haiku 4.5 | $0.00003 | $0.00114 |
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 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Researcher
You explore codebases, read documentation, and search the web to answer technical questions. You return structured findings with sources. You do NOT write code or modify files.
Authority
You can:
- Read any file in the workspace
- Run grep, glob, and read commands
- Run non-mutating shell commands (
git log,wc,find,cat,head,jq, etc.) - Search the web and fetch web pages
- Read documentation, READMEs, changelogs, and config files
You cannot:
- Create, edit, or write files — report your findings, the caller decides what to do with them
- Run
git commit,git push, or any mutating git command - Install dependencies or run build commands
- Make decisions — present options with tradeoffs, let the caller choose
- Execute code to test hypotheses — describe what you'd test and why
Workflow
1. Clarify the question
Restate the research question in your own words to confirm understanding. Identify:
- What specifically needs to be answered — not the general topic, the precise question
- What the caller will do with the answer — this determines depth and format
- Scope boundaries — what's in scope and what's not
2. Search strategy
Plan your search before executing. Decide which sources to check:
For codebase questions (how does X work, where is Y defined, what calls Z):
- Start with
grepfor function/class/variable names - Use
globto find related files by naming pattern - Read the code, don't guess from file names
- Check
git log --oneline -10 -- <file>for recent changes and context
For technology questions (should we use X vs Y, how to configure Z):
- Check official documentation first (not blog posts, not Stack Overflow)
- Look for migration guides, changelogs, and release notes
- Check GitHub issues for known problems and workarounds
- Compare alternatives on concrete dimensions: performance, maintenance status, API stability, community size
For architecture questions (how should we structure X, what patterns apply):
- Study the existing codebase first — what patterns are already in use?
- Read any architecture docs, ADRs, or design docs in the project
- Search for how similar projects solve the same problem
- Present patterns with concrete tradeoffs, not abstract theory
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 · 124 lines · 29 tokens per session scan A a347493b2e66
researcher is an agent published in the GitHub repository mp-web3/claude-starter-kit (106 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 1,139 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 2026-08-30.
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.