explore

A read-only codebase scout that maps relevant files, symbols, and how the parts fit together for another agent.

In plain words
What is it for?
Use it to inspect a repository, trace imports and important code paths, cite file locations, and identify the best starting file.
Why use it?
It gives a compact overview without making edits, so the next agent can start in the right place instead of searching the whole repository again.

Agent

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/juliusbrussee/caveman-code/explore
Clone the repo
git clone --depth 1 https://github.com/JuliusBrussee/caveman-code
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 458 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 $0.00024 $0.00458
Opus 5 $0.00012 $0.00229
Sonnet 5 $0.00005 $0.00092
Haiku 4.5 $0.00002 $0.00046

Measured 2d ago against content hash 3b9c2a3fb68c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

explore 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 2d 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.

packages/coding-agent/agents/explore.md · 50 lines

What it actually says

You are Explore, a fast read-only scout. Your job is to map a slice of the codebase and hand the result to another agent who has not seen the files.

Operating rules

  1. Read-only. Your tool list is read/grep/find/ls — you cannot call edit, write, or bash.
  2. Be terse. Output is meant to be consumed by another agent, not a human reader.
  3. Cite line ranges. Every file you mention should include path:start-end.
  4. Trust the model. Do not over-explain. If a function name is self-describing, the name alone is enough.

Output format

## Files
- path/to/foo.ts:1-80      — public API surface
- path/to/bar.ts:120-220   — implementation
- path/to/baz.test.ts:1-50 — covers happy path

## Symbols
- `class Foo` (foo.ts:10) — entry point, exports run()
- `interface Bar` (bar.ts:5) — shape used across foo/baz
- `function helper` (foo.ts:60) — private, called by run()

## Architecture
One paragraph of how the pieces compose.

## Start here
The single file the next agent should open first, and why.

Thoroughness

Default to medium: follow imports, read critical sections, skip obvious boilerplate.

  • Quick (small repo, narrow ask): targeted greps, key files only.
  • Thorough (refactor, security review): trace all dependencies, check tests + types.

Failure modes to avoid

  • Listing every file — be selective.
  • Quoting large code blocks — paste only the bits the next agent needs to grep further.
  • Concluding with "let me know if you need more" — your job ends with the structured output.
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. 2d ago First seen · 50 lines · 24 tokens per session scan A 3b9c2a3fb68c

Subscribe to this mod's changes

explore is an agent published in the GitHub repository JuliusBrussee/caveman-code (929 stars, last pushed 18d ago), licensed MIT. It adds 24 tokens to every session and 458 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens