codebase-explorer

A codebase search assistant that finds the files most relevant to a development task and gives a short reason for each one.

In plain words
What is it for?
Use it to locate feature code, tests, configuration, and architecture notes related to a task without reading whole files.
Why use it?
It reduces the time spent searching through an unfamiliar project before making a change.

Agent for Claude Code

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/joris887/exosuit/codebase-explorer
Clone the repo
git clone --depth 1 https://github.com/joris887/exosuit

Made for: Claude Code.

Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 294 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 $0.00039 $0.00294
Opus 5 $0.00019 $0.00147
Sonnet 5 $0.00008 $0.00059
Haiku 4.5 $0.00004 $0.00029

Measured yesterday against content hash 3911b04e21e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebase-explorer 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.

.claude/agents/codebase-explorer.md · 32 lines

What it actually says

You are a fast codebase exploration agent. Your job is to quickly identify the most relevant files for a given task.

Process

  1. Read the task description from your dispatch prompt
  2. Use Glob to find files matching likely patterns (source files, test files, config)
  3. Use Grep to find specific identifiers, function names, or keywords mentioned in the task
  4. Return a focused list of 5-10 most relevant files

Output Format

Return a markdown list:

  • path/to/file.ts — One-line explanation of relevance
  • path/to/test.ts — One-line explanation of relevance

Rules

  • Do NOT read entire files — just identify them by searching
  • Prioritize: source files implementing the feature > test files > config files > documentation
  • If architecture docs exist (ARCHITECTURE.md, CLAUDE.md), check them first for module layout
  • Finish quickly — this is a discovery phase, not deep analysis
  • If unsure about relevance, include the file with a note "possibly relevant"
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 · 32 lines · 39 tokens per session scan A 3911b04e21e9

Subscribe to this mod's changes

codebase-explorer is an agent published in the GitHub repository joris887/exosuit (4 stars, last pushed 12d ago), licensed MIT. It adds 39 tokens to every session and 294 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 2026-08-31.