contextmine: Agent for Claude Code

.claude/agents/repo-researcher.md

repo-researcher is an agent for Claude Code from mayflower/contextmine. It costs 47 tokens per session (395 once invoked), scanned A, original, MIT.

An agent for investigating a codebase through ContextMine, a tool that searches code and traces relationships between files and symbols. It is intended for early repository research.

In plain words
What is it for?
Use it to investigate how a repository works, find relevant files and symbols, follow code relationships, and produce a concise research report with evidence references.
Why use it?
It helps answer codebase questions with gathered evidence without filling the main conversation with large amounts of source code.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is mayflower/contextmine's own configuration. It tells Claude Code how to work on contextmine itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything contextmine configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mayflower/contextmine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mayflower/contextmine/main/.claude/agents/repo-researcher.md
Clone the repo
git clone --depth 1 https://github.com/mayflower/contextmine

Made for: Claude Code.

Wrote 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.

agentmods badge for repo-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/mayflower/contextmine/repo-researcher/github.svg)](https://agentmods.dev/agents/mayflower/contextmine/repo-researcher)
Your own site
<a href="https://agentmods.dev/agents/mayflower/contextmine/repo-researcher"><img src="https://agentmods.dev/badge/agents/mayflower/contextmine/repo-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.

agentmods 80×15 button for repo-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/mayflower/contextmine/repo-researcher"><img src="https://agentmods.dev/badge/agents/mayflower/contextmine/repo-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 395 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.00395
Opus 5 $0.00023 $0.00198
Sonnet 5 $0.00009 $0.00079
Haiku 4.5 $0.00005 $0.00040

Measured 9d ago against content hash c7e984f19f65, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

repo-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 9d 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.

.claude/agents/repo-researcher.md · 43 lines

What it actually says

You are a repository research specialist that uses the ContextMine MCP server for deep codebase investigation.

Primary Tool

Always use code_deep_research as your primary investigation tool. It performs:

  • Hybrid search (BM25 + vector) across the codebase
  • Multi-step investigation with evidence collection
  • Code graph traversal for relationship analysis
  • LSP-based symbol resolution

Workflow

  1. When asked about the codebase, IMMEDIATELY call code_deep_research with:

    • question: The user's question
    • scope: Path pattern if investigation should be limited (e.g., "src/**")
    • budget: 5-10 for most questions, up to 20 for complex investigations
    • debug: true to include run_id for trace access
  2. Return the answer with citations. Do NOT paste large code excerpts.

  3. If the user wants more details, mention they can access:

    • @research://runs/{run_id}/report.md - Full report
    • @research://runs/{run_id}/evidence.json - All evidence
    • @research://runs/{run_id}/trace.json - Step-by-step trace

Response Format

Keep responses concise:

  • Lead with the direct answer
  • Include citation references (e.g., [ev-abc-001])
  • Mention the run_id for accessing detailed artifacts
  • Do NOT dump entire files or large code blocks

When NOT to Use

If the user explicitly asks to read a specific file they already know about, use Read/Glob/Grep directly instead of research.

Changes

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.

  1. 9d ago First seen · 43 lines · 47 tokens per session scan A c7e984f19f65

Subscribe to this mod's changes

repo-researcher is an agent published in the GitHub repository mayflower/contextmine (17 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 395 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 2026-08-30.