Skip to content
cccskills
FreePublished on GitHubEnglish overview

caveman-explore

Locate relevant code in an unfamiliar repository or after a direct search fails. This read-only explorer returns a short list of file paths, verified line ranges, and relevance notes for another agent to use.

OriginalShow the original description

Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or symbol is already named. Returns path:line citations only; its reads stay out of main context.

JuliusBrussee/caveman
AI rating90/ 100See how to install

Good for

  • Find starting points in an unfamiliar codebase
  • Locate logic spread across multiple files
  • Investigate after a direct search fails
  • Hand verified code locations to another agent

Overview

What it does

caveman-explore searches a repository, where code is stored, using read-only access to locate the files responsible for a particular behavior. It combines likely filename patterns, searches for function names or text, and reading promising files to narrow down the relevant locations. The result is a short list of file paths, line ranges it actually read, and brief reasons each location matters.

When it helps

Use it to find a starting point in unfamiliar code, investigate behavior spread across files, or continue after a direct search fails. It takes location-finding work delegated by another agent and returns the necessary references without bringing everything it read into the main agent’s conversation.

Example requests

  • “Find the code that decides how requests are routed.”
  • “Locate the implementation and tests related to this feature.”

Notes

Its configuration uses Read, Glob, Grep, and the haiku model. It does not edit files, run commands, or propose solutions. It is intended to be skipped when the target file or function is already known. If it cannot find relevant locations, it reports that outcome.

This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.

Objective evaluation

AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.

Clear instructionsIs it clear when to use it and what it does?
AGoodIt explicitly locates unfamiliar code or follows failed searches, returning only location references.
Concrete stepsAre steps, inputs, outputs, and examples spelled out?
AGoodIt provides search and reading steps, a rule to cite only lines actually read, and an output example.
SafetyAre sending data, deleting files, and running commands disclosed?
AGoodIt limits tools to Read, Glob, and Grep, and prohibits editing files and running commands.
Easy setupDoes it need few tools or API keys, and are they documented?
BPartly lackingIt specifies Read, Glob, Grep, and haiku, but gives no instructions for preparing the required environment.

The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 20, 2026. Treat it as a guide and read the original before installing.

Disagree? Request a re-evaluation

Tell us which point is wrong and why. No login needed. We will check it against the SKILL.md, redo the evaluation, and show the result here.

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

Files included (3)

  • SKILL.md1.9 KB
  • package.json354 B
  • tests/skill-file.test.mjs2.1 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

You are FastContext, a fast, cheap, read-only repository explorer. Another agent (the solver) delegates a localization question to you. Your only job is to find WHERE the relevant code lives and report it as a compact list of file paths with line ranges. You never edit files, run commands, or propose a solution.

How to work:

  1. Issue several tool calls IN PARALLEL in your first turn — cast a broad net. Cover complementary hypotheses at once: likely path patterns (Glob), symbol and string matches (Grep), and reading the most promising files (Read). Do not probe one file at a time when you can fan out.
  2. Follow the evidence over one or two more turns only if needed. Stop as soon as you can name the relevant locations. You are optimizing for the solver's token budget, so finish fast.
  3. Only cite line ranges you actually read. Never invent or estimate a range, and never cite a range past the end of a file. A precise small range beats a vague large one.

Your reply MUST be ONLY an evidence block: one citation per line, nothing else. No preamble, no explanation, no summary, no markdown headings. Use exactly this shape, one per line:

path/to/file.ext:START-END reason it is relevant

Example reply:

src/router/pick.go:42-71 route selection — where a model is chosen src/router/pick_test.go:18-40 the table test covering pick()

If you genuinely cannot find anything relevant, reply with the single line:

no relevant locations found

That honest answer is better than a guess. The solver reads your citations and nothing else from your work, so keep the list short, specific, and correct.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

cavecrew

FreeSummaryAI rating 90

Delegate code lookup, small edits, and diff reviews to three specialized subagents. Their compact, structured results help conserve the main agent's context, with guidance on when to delegate and when to keep work in the main conversation.

  • Locating definitions and callers
  • Making a focused edit across one or two files
  • Reviewing a diff for bugs
JuliusBrussee/caveman113.8KUpdated Oct 19, 2026

caveman

FreeSummaryAI rating 100

Make agent replies shorter and easier to scan by putting answers first and removing filler. Preserves technical details, exact commands, numbers, and essential conditions while keeping the user's chosen language.

  • Reading concise replies in a terminal
  • Getting conclusions before explanations
  • Reducing wording while keeping technical details
JuliusBrussee/caveman113.8KUpdated Oct 19, 2026

caveman-commit

FreeSummaryAI rating 100

Create short commit messages using Conventional Commits, a format that labels the type of change. Emphasize intent, keep the subject concise, and include explanatory text when breaking changes, security fixes, data migrations, or reversions require context.

  • Writing a commit message for code changes
  • Standardizing commit message format
  • Documenting breaking changes and migration steps
JuliusBrussee/caveman113.8KUpdated Oct 19, 2026

caveman-compress

FreeSummaryAI rating 90

Compress memory files and task lists into shorter wording to reduce input tokens. Keeps code and document structure intact, saves a readable backup separately, and sends the text to the configured model provider.

  • Shortening CLAUDE.md to reduce input tokens
  • Compressing task lists and preference files
  • Keeping readable backups of compressed files
JuliusBrussee/caveman113.8KUpdated Oct 19, 2026

caveman-discover

FreeSummaryAI rating 90

Find LLM workflows in a codebase and label them by the job they perform, so Caveman Cloud can separate spending by workflow. Present a labeling proposal for approval, apply focused code changes, and check an affected execution path.

  • Breaking down LLM spending by job
  • Inventorying LLM use in APIs, scheduled jobs, and scripts
  • Separating evaluation spending from other workflows
JuliusBrussee/caveman113.8KUpdated Oct 19, 2026

caveman-evidence-review

FreeSummaryAI rating 90

Review Caveman Cloud spending, latency, errors, and potential improvements using current reports and traces, or individual execution records. Produce findings tied to time windows and trace IDs, while keeping measured costs, estimated opportunities, and verified savings separate.

  • Understanding which workflows drive LLM spending
  • Investigating slow responses and errors
  • Reviewing measured costs and verified savings separately
JuliusBrussee/caveman113.8KUpdated Oct 19, 2026

See all skills by JuliusBrussee

Report a problem with this skill