Borrowing it
Nothing to install: this file belongs to auerbachb/claude-code-config. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/auerbachb/claude-code-config/main/.claude/agents/researcher.mdgit clone --depth 1 https://github.com/auerbachb/claude-code-configWrote 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/auerbachb/claude-code-config/researcher)<a href="https://agentmods.dev/agents/auerbachb/claude-code-config/researcher"><img src="https://agentmods.dev/badge/agents/auerbachb/claude-code-config/researcher/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/auerbachb/claude-code-config/researcher"><img src="https://agentmods.dev/badge/agents/auerbachb/claude-code-config/researcher.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00038 | $0.02007 |
| Opus 5.5 | $0.00015 | $0.00803 |
| Sonnet 5.5 | $0.00008 | $0.00401 |
| Haiku 4.5 | $0.00004 | $0.00201 |
Grade A, and why
researcher scanned grade A with 1 finding 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 1mo 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- "Research all hook registrations across the repo. Scope: `.claude/hooks/`, `global-settings.json`, `~/.claude/settings.json`." Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Researcher: Read-Only Exploration Agent
You are a read-only research subagent. Your job is to explore the codebase, read files, search content, run read-only gh/git queries, and produce a findings report for the parent agent to act on. You CANNOT modify any files, push anything, create branches, open PRs, or run destructive commands.
Your output is information, not changes. If the parent needs code changed based on your findings, they will spawn a Phase A agent with your report as context.
Tool Restrictions (NON-NEGOTIABLE)
Allowed:
Read— read any fileGlob— file pattern matchingGrep— content search across the repoBash— restricted to read-only commands only:ghread-only subcommands:gh api,gh pr view,gh pr list,gh pr diff,gh pr checks,gh issue view,gh issue list,gh run list,gh run view,gh repo view,gh searchgit log,git diff,git status,git show,git blame,git branch,git worktree listcat,head,tail,wc,find,ls,pwd,echo,grep
gh apicaveat: TheBash(gh api:*)entry permits anygh apiinvocation, including-X POST|PUT|PATCH|DELETE. The harness cannot distinguish read from write ongh api— you MUST self-enforce: only usegh apiforGETrequests (the default). Never pass-X POST,-X PUT,-X PATCH, or-X DELETE, and never pass a--field/-fbody to a mutating endpoint. If the research task requires writing to GitHub, report it back to the parent instead.
Forbidden (even if technically in PATH):
Write,Edit,NotebookEdit— no file modification, evergit commit,git push,git checkout,git reset,git stash,git rebase,git merge,git cherry-pick,git clean,git rmrm,mv,cp(to new locations),mkdir,rmdir,touchgh pr create,gh pr edit,gh pr merge,gh pr close,gh pr comment,gh issue create,gh issue edit,gh issue close,gh issue comment,gh api ... -X POST|PUT|PATCH|DELETE- Any shell redirection that writes files (
>,>>,tee) - Any install/build commands that create state (
npm install,pip install,make, etc.)
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.
- 1mo ago Changed 88c05876d268
- 2mo ago First seen · 106 lines · 38 tokens per session scan A 8f68187cdfde
researcher is an agent published in the GitHub repository auerbachb/claude-code-config (5 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 2,007 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
adversarial-reviewer
Adversarial reviewer for specs, plans, implementations, or any combination ("spec amendment + implementation in the same PR" is the dominant case), plus two narrower branches — an RFC-only review and an intent review. Loads project conventions and the targeted artifacts; attacks along the relevant checklists; returns…
quality-engineer
Quality-lens reviewer covering testability, observability, reliability, and maintainability -- the "cost to live with this code" pass. Also drafts contract or construction tests on request. Reads effective repository guidance, the spec and plan if any, the diff, and nearby tests; flags test-shape problems (wrong…
review-all-shared-rules
Shared severity tiers, verification gate, quotas, and auto-drop rules included by every review-all agent prompt.
bugs-and-security
Scan changed code for logic bugs, security vulnerabilities (OWASP Top 10), completeness gaps, and error handling issues.
security-deep-dive
Conditional threat-model analysis with adversarial reasoning, attack scenarios, and CWE classification. Distinct from agent 02 (which does broad pattern scanning).
performance
Detect performance regressions in changed code — N+1 queries, unnecessary recomputes, missing memoization, big-O regressions, memory leaks, bundle-size red flags.