caveman-explore
An agent skill by JuliusBrussee, from JuliusBrussee/caveman. Tags: codebase, developer-tools, local-workflow, research.
What it does
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.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add JuliusBrussee/caveman --skill caveman-exploreOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/JuliusBrussee/caveman
cp -r caveman/skills/caveman-explore ~/.claude/skills/caveman-exploreSafety box score
Grade A, minimal risk: 4 of 100 risk points, rated 2026-10-16. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill is a narrowly scoped, read-only repository explorer: it uses only Read, Glob, and Grep to find code locations and then returns citations. Its main effect is limited exposure of repository contents for localization; it does not execute code, access the network, or modify files.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 0 (none) | SKILL.md only exposes Read, Glob, and Grep and explicitly says, "You never edit files, run commands, or propose a solution." |
| Network access | 0 (none) | There are no URLs, download steps, API calls, or other remote data transfers in the shipped skill files. |
| Filesystem reach | 1 (low) | The skill is designed to read repository files for localization, so it can inspect project contents, but it is explicitly read-only and non-destructive. |
| Secrets & credentials | 0 (none) | The files do not mention tokens, keys, passwords, env files, browser sessions, or other secret-bearing stores. |
| Privilege & persistence | 0 (none) | No sudo, global installs, services, shell startup edits, or OS/git setting changes are requested. |
| Instruction hijack surface | 0 (none) | The instructions constrain output format and workflow, but they do not ask the agent to ignore higher-priority rules, hide actions, or follow remote instructions. |
| Irreversible actions | 0 (none) | It only localizes code and emits citations; it does not send messages, deploy, publish, pay, book, or delete anything. |
| Transparency | 0 (none) | All shipped content is plain text Markdown/JS/JSON; there are no binaries, embedded blobs, or unreviewable installers. |
Before installing
- Read `SKILL.md` to confirm you want a citation-only, read-only explorer.
- Check that the only declared tools remain `Read, Glob, Grep` and no write or shell tools were added.
- Use it only when you need broad localization, not when you already know the exact file or symbol.
Rated 2026-10-16 by an automated review of 3 files from the skill's repository.
Source
- Repository
- JuliusBrussee/caveman (all skills from this repository)
- Path
- skills/caveman-explore/SKILL.md
- Branch
- main
- Updated
- 2026-10-05
Related skills
- cavecrew — When to delegate to `cavecrew-investigator` (locate code).
- agents-get-started — Use when a developer wants to create a new agent project or get started with AgentCore.
- devcontainer-setup — Creates devcontainers with Claude Code, language-specific tooling (Python/Node/Rust/Go), and persistent volumes.
- expo-examples — Framework (OSS). Expo's official example projects - the expo/examples repo of ~70 `with-*` integrations (Stripe, Clerk, Supabase, OpenAI, maps, Reanimated.
- cad — Create/edit parametric CAD models, organize CAD projects, export STEP/STL/3MF/GLB files, resolve prompt references, and measure geometry with cadgen.
- debugging-wizard — Parses error messages, traces execution flow through stack traces, correlates log entries to identify failure points.