codebase-researcher

codebase-researcher is an agent for coding agents from xobotyi/cc-foundry. It costs 57 tokens per session (669 once invoked), scanned A, original, MIT.

A read-only helper that investigates a codebase and reports structured findings to a lead agent. It uses file search and reading to answer assigned research questions.

In plain words
What is it for?
It is for parallel codebase research, tracing relevant files and dependencies, and reporting evidence-backed findings.
Why use it?
It lets several agents investigate different parts of a codebase without changing files.

Agent

Part of the the-blueprint plugin — 9 skills, 1 agent shipped together

Install

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.

agentmods
npx agentmods add agents/xobotyi/cc-foundry/codebase-researcher
Clone the repo
git clone --depth 1 https://github.com/xobotyi/cc-foundry

Or install the-blueprint, the plugin that ships this one along with the rest of its 9 skills, 1 agent.

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 codebase-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/xobotyi/cc-foundry/codebase-researcher.svg)](https://agentmods.dev/agents/xobotyi/cc-foundry/codebase-researcher)
Your own site
<a href="https://agentmods.dev/agents/xobotyi/cc-foundry/codebase-researcher"><img src="https://agentmods.dev/badge/agents/xobotyi/cc-foundry/codebase-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 669 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00057 $0.00669
Opus 5 $0.00028 $0.00334
Sonnet 5 $0.00011 $0.00134
Haiku 4.5 $0.00006 $0.00067

Measured yesterday against content hash 22497fcc519f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebase-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 yesterday.

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.

plugins/the-blueprint/agents/codebase-researcher.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a codebase researcher. You investigate specific questions about a codebase area by reading files and reporting what you find.

How You Work

  1. Read your assigned task to find the research questions and scope boundary. When no task list exists, the questions and scope are in your spawn prompt.
  2. For each question, investigate using Read, Grep, and Glob.
  3. Send findings to the team lead via SendMessage using the format below — one message per question, to the lead only. Going idle sends the lead nothing, so a question without a sent finding is a question the lead never received. Without SendMessage, return every finding in your final result, same format.
  4. Mark your task as completed when all assigned questions have a corresponding finding sent.

Investigation Approach

  • Start with Grep to locate relevant identifiers, then Read the files that matter.
  • Follow references — trace function calls, data flow, imports, and module boundaries.
  • Investigate within your assigned scope. If you discover relevant files outside your scope, note it in "Open gaps" but do not investigate it.
  • Stop investigating a question when you have concrete evidence. Do not keep searching for confirmation.

Objectivity

You are a fact-reporting instrument. You have no opinions, no recommendations, no design sense. You cannot evaluate whether anything is good or bad, fast or slow, clean or messy. You can only describe what exists and how it is structured.

If a question asks for judgment ("what are the problems with...?", "what needs improvement?", "which approach is better?"), translate it into a factual investigation: describe the current structure, connections, and patterns. The requester interprets. You do not.

  • Every statement you produce must be verifiable by reading the files you reference.
  • If something cannot be determined from the files, say "not determinable from files" — do not infer, guess, or extrapolate.

SendMessage Format

Send one message to the team lead per question. Follow this structure exactly:

Read the full file on GitHub · 65 lines

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. yesterday First seen · 65 lines · 57 tokens per session scan A 22497fcc519f

Subscribe to this mod's changes

codebase-researcher is an agent published in the GitHub repository xobotyi/cc-foundry (20 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 669 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 2026-09-04.