New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Caveman Repository Explorer

by JuliusBrussee in JuliusBrussee/caveman

A read-only explorer for cold-start orientation or failed searches that replies with nothing but file path and line range citations, keeping its reads out of main context.

Apache-2.0Auto-check passedAgent Workflows

Install Caveman Repository Explorer

skills CLI
$ npx skills add JuliusBrussee/caveman --skill caveman-explore -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install JuliusBrussee/caveman caveman-explore --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/JuliusBrussee/caveman.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/caveman-explore .claude/skills/caveman-explore && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
caveman-explore
GitHub stars
111k
Used in
1 other repo
Token cost
~492 tokens
SKILL.md length
267 words
Files
3
Skills in repo
18
Repo updated
First seen
Licence
Apache-2.0

At a glance

A read-only explorer for cold-start orientation or failed searches that replies with nothing but file path and line range citations, keeping its reads out of main context.

  • Works in 3 steps: Issue several tool calls IN PARALLEL in… → Follow the evidence over one or two more… → Only cite line ranges you actually read.…
  • Getting oriented in an unfamiliar repository
  • Runs JavaScript scripts from its folder
  • A direct grep or search did not find where something lives

What it does

A fast, cheap helper called FastContext is defined here, and another agent delegates a localization question to it. It never edits files, runs commands or suggests fixes. In its first turn it fires several Glob, Grep and Read calls in parallel to test different hypotheses, follows the evidence for one or two more turns at most, and stops as soon as it can name the relevant places.

Its reply is only an evidence block with one citation per line: a path, a start and end line, then a short reason. It cites only ranges it actually read and never estimates them. If nothing relevant turns up, it says no relevant locations found rather than guessing. The skill is not meant for cases where the exact file or symbol is already known. The folder also holds a package.json and a small test file.

When your agent uses it

  • Getting oriented in an unfamiliar repository
  • A direct grep or search did not find where something lives
  • Locating code across many files without filling the main context

Example prompts

  • “Find where model selection happens in this repo and cite the exact lines.”
  • “My grep for retry logic found nothing; explore the repo and tell me where it might live.”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Issue several tool calls IN PARALLEL in your first turn — cast a broad net.
  2. Follow the evidence over one or two more turns only if needed. Stop as soon as
  3. Only cite line ranges you actually read. Never invent or estimate a range, and

What it can do on your machine

Read from SKILL.md and the folder at commit 2e08b91. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (JavaScript), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Caveman Repository Explorer loads about 492 tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 267 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~66
When it runs · the whole SKILL.md, loaded when a task matches
~492

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from JuliusBrussee/caveman at commit 2e08b91, republished under its Apache-2.0 licence (© JuliusBrussee). 267 words, ~492 tokens.

Download SKILL.mdSave it as .claude/skills/caveman-explore/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
caveman-explore
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.
tools
Read, Glob, Grep
model
haiku

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.

© JuliusBrussee, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files in skills/caveman-explore of JuliusBrussee/caveman.

  • SKILL.md
  • package.json
  • tests/skill-file.test.mjs

Open the folder on GitHubat commit 2e08b91

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in JuliusBrussee/caveman, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Caveman Repository Explorer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Caveman Repository Explorer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Caveman Repository Explorer this skillJuliusBrussee/caveman111k1 repos~492Automated safety check: PassApache-2.0
Codebase Exploreryologdev/yoyo-evolve1.9k—~2.8kAutomated safety check: PassMIT
ccc Semantic Code Searchcocoindex-io/cocoindex-code2.8k—~938Automated safety check: PassApache-2.0
Repomix Codebase Packeryamadashy/repomix29k—~1.3kAutomated safety check: NotesMIT
Code Context Slicingtrailofbits/skills7.4k—~2.1kAutomated safety check: PassCC-BY-SA-4.0
MoAI Foundation Coremodu-ai/moai-adk1.2k—~5kAutomated safety check: PassApache-2.0

Similar skills

  • Codebase Explorer

    yologdev/yoyo-evolve

    Builds a structural map of a large or unfamiliar codebase by dispatching sub-agents to summarize regions, keeping the main context small.

    1.9k GitHub stars~2.8k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • ccc Semantic Code Search

    cocoindex-io/cocoindex-code

    Semantic code search and index management with the ccc CLI: the agent initializes, indexes and queries the project by concept, filtering by language or path.

    2.8k GitHub stars~938 tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

  • Repomix Codebase Packer

    yamadashy/repomix

    Packs a local directory or remote GitHub repository into one AI-friendly file with Repomix, then searches it to explore structure, find patterns and count tokens.

    29k GitHub stars~1.3k tokensUpdated 5 days ago
    Agent WorkflowsAuto-check: notes

  • Code Context Slicing

    trailofbits/skills

    Official

    Picks a small, graph-based slice of source with Trailmark and hands a focused code task to a smaller or local model without exposing the whole repository.

    7.4k GitHub stars~2.1k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

  • MoAI Foundation Core

    modu-ai/moai-adk

    Reference for MoAI-ADK's core development principles: TRUST 5 quality gates, SPEC-first domain-driven workflow, agent delegation and token budgeting.

    1.2k GitHub stars~5k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Agentsop Context Scope Discipline

    agentsope/SkillAlchemy

    Coder-agent working-file budget discipline: keep the editable working set (files you /add into writable context) under ~25k tokens, separate "read" from "edit", delegate breadth to a read-only…

    466 GitHub stars~3k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from JuliusBrussee/caveman

All 18 skills in this repo

  • Caveman Workflow Labeler

    JuliusBrussee/caveman

    Finds every LLM workflow in a repository, proposes a labeling table and, once you agree, wires labels so Caveman Cloud groups spend per workflow.

    111k GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed

  • Caveman Evidence Review

    JuliusBrussee/caveman

    Read-only review of Caveman Cloud data to explain where LLM spend goes: cost, score, workflows, traces, latency, errors, routing and verified savings.

    111k GitHub starsUsed in 1 repo~927 tokens
    Auto-check passed

  • Caveman Experiment Manager

    JuliusBrussee/caveman

    Reads the state and results of Caveman Cloud experiments and reports one recommendation or a block, without changing an experiment's lifecycle itself.

    111k GitHub starsUsed in 1 repo~975 tokens
    Auto-check passed

  • Caveman Optimization Evaluator

    JuliusBrussee/caveman

    Turns a Caveman report-only optimization observation into one minimal code change and a paired baseline evaluation, after the operator picks which to pursue.

    111k GitHub starsUsed in 1 repo~1.2k tokens
    Auto-check passed

  • Caveman Gateway Setup

    JuliusBrussee/caveman

    Routes every LLM call in a repository through the Caveman Cloud gateway in record mode, so requests and costs are measured without changing behavior.

    111k GitHub starsUsed in 1 repo~2.6k tokens
    Auto-check: warnings

  • Caveman Help Card

    JuliusBrussee/caveman

    Quick-reference card for the three caveman skills and their commands. Trigger: /caveman-help or "caveman help".

    111k GitHub stars~690 tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Caveman Repository Explorer

What does Caveman Repository Explorer do?

A read-only explorer for cold-start orientation or failed searches that replies with nothing but file path and line range citations, keeping its reads out of main context. A fast, cheap helper called FastContext is defined here, and another agent delegates a localization question to it. It never edits files, runs commands or suggests fixes.

When should I use Caveman Repository Explorer?

Caveman Repository Explorer fits situations like: getting oriented in an unfamiliar repository; A direct grep or search did not find where something lives; locating code across many files without filling the main context.

How do I install Caveman Repository Explorer in Claude Code?

Run `npx skills add JuliusBrussee/caveman --skill caveman-explore -a claude-code`. Or copy the skill folder (skills/caveman-explore in JuliusBrussee/caveman) into .claude/skills/caveman-explore in your project. Claude Code loads it when a task matches its description.

How do I install Caveman Repository Explorer in Codex?

Run `npx skills add JuliusBrussee/caveman --skill caveman-explore -a codex`. Or copy the skill folder (skills/caveman-explore in JuliusBrussee/caveman) into .agents/skills/caveman-explore in your project. Codex loads it when a task matches its description.

Can I use Caveman Repository Explorer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JuliusBrussee/caveman --skill caveman-explore -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/caveman-explore, .gemini/skills/caveman-explore, .github/skills/caveman-explore and .opencode/skills/caveman-explore in your project.

What does Caveman Repository Explorer need to run?

Going by SKILL.md and its folder, Caveman Repository Explorer needs JavaScript for the scripts in its folder.

Does Caveman Repository Explorer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Caveman Repository Explorer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Caveman Repository Explorer use?

Caveman Repository Explorer is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Caveman Repository Explorer use?

About 492 tokens (SKILL.md is roughly 2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Caveman Repository Explorer?

Skills that share tags, products or a category with Caveman Repository Explorer: Codebase Explorer (yologdev/yoyo-evolve, 1.9k stars), ccc Semantic Code Search (cocoindex-io/cocoindex-code, 2.8k stars), Repomix Codebase Packer (yamadashy/repomix, 29k stars) and Code Context Slicing (trailofbits/skills, 7.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Caveman Repository Explorer?

JuliusBrussee (a GitHub user) maintains it in JuliusBrussee/caveman, which has 110,632 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 8, 2026.

Source: JuliusBrussee/caveman on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.