skill

Cavecrew

When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main context lasts longer.

juliusbrussee372,505+ installsVetted

About

Cavecrew = three subagent presets that answer in ultracave voice (tool runs: one status line in, one out; nothing between routine calls). Same job as Anthropic defaults (`Explore`, edit-style agents, reviewer); difference is the tool-result they return is compressed, so main context shrinks per delegation.

## When to use cavecrew vs alternatives

| Task | Use | |---|---| | "Where is X defined / what calls Y / list uses of Z" | `cavecrew-investigator` | | Same but you also want suggestions/architecture commentary | `Explore` (vanilla) | | Surgical edit, ≤2 files, scope obvious | `cavecrew-builder` | | New feature / 3+ files / cross-cutting refactor | Main thread, or `feature-dev:code-architect` if installed | | Review diff, branch, or file for bugs | `cavecrew-reviewer` | | Deep code review with rationale + alternatives | `Code Reviewer` (vanilla) if installed, else main thread | | One-line answer you already know | Main thread, no subagent |

Rule of thumb: **if you'd want the subagent's output in 1/3 the tokens, pick cavecrew. If you'd want prose, pick vanilla.**

## Why this exists (the real win)

Subagent tool results get injected into main context verbatim. A vanilla `Explore` that returns 2k tokens of prose costs 2k tokens of main-context budget every time. The same finding from `cavecrew-investigator` comes back as a compressed `path:line` table instead. Across 20 delegations in one session that's the difference between context exhaustion and finishing the task.

## Output contracts

What main thread can rely on per agent:

**`cavecrew-investigator`** ``` <Header>: - path:line — `symbol` — short note totals: <counts>. ``` Or `No match.` Always file-path-first, line-number-attached, backticked symbols. Safe to grep with `path:\d+`.

**`cavecrew-builder`** ``` <path:line-range> — <change ≤10 words>. verified: <re-read OK | mismatch @ path:line>. ``` Or one of: `too-big.` / `needs-confirm.` / `ambiguous.` / `regressed.` (terminal first token).

**`cavecrew-reviewer`** ``` path:line: <emoji> <severity>: <problem>. <fix>. totals: N🔴 N🟡 N🔵 N❓ ``` Or `No issues.` Findings sorted file → line ascending.

## Chaining patterns

**Locate → fix → verify** (most common): 1. `cavecrew-investigator` returns site list. 2. Main thread picks 1-2 sites, hands paths to `cavecrew-builder`. 3. `cavecrew-reviewer` audits the diff.

**Parallel scout** (when investigation is broad): Spawn 2-3 `cavecrew-investigator` calls in one message (different angles: defs vs callers vs tests). Aggregate in main thread.

**Single-shot edit** (when site is already known): Skip investigator. Hand exact path:line to `cavecrew-builder` directly.

## What NOT to do

- Don't accept or reject a subagent's absence claim (`No match.`, `No issues.`, "section missing", "unchanged") without one targeted check of the relevant file, search scope, or diff. Check cited line numbers are within the file before acting. - Don't use `cavecrew-builder` when you don't already know the file. Spawn investigator first or main thread will eat tokens passing context. - Don't chain `cavecrew-investigator → cavecrew-builder` for a 5-file refactor. Builder will return `too-big.` and you'll have wasted a turn. - Don't ask `cavecrew-reviewer` for "general feedback" — it returns findings only, no architecture opinions. Use `Code Reviewer` for that when installed. - Don't expect prose. Cavecrew output is structured, sometimes terse to the point of cryptic. If a human will read it directly, paraphrase.

## Auto-clarity (inherited)

Subagents drop caveman → normal English for security warnings, irreversible-action confirmations, and any output where fragment ambiguity could be misread. Resume caveman after.

Install

Run this command

npx skills add juliusbrussee/caveman

Works with

claude appclaude codeclaude apicursorcodexwindsurfclinezed

Manual steps

Install with `npx skills add juliusbrussee/caveman`, or clone the repository and copy the `skills/cavecrew` folder into your Claude skills directory.

View source

Frequently asked questions

What is the Cavecrew skill?

When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main context lasts longer.

How do I install Cavecrew?

Run this in your terminal:

npx skills add juliusbrussee/caveman
Which AI tools does Cavecrew work with?

It works with claude_app, claude_code, claude_api, cursor, codex, windsurf, cline, zed.

Who made Cavecrew?

juliusbrussee.

Is Cavecrew free?

Yes, it is free to use.

Related assets

More curated picks in Development & Code.

All Cavecrew alternatives →
skillclaude_appclaude_codeclaude_api
git clone https://github.com/anthropics/skills && cp -r skills/skills/claude-api ~/.claude/skills/
Claude Api
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.…★ 4.8 · 2,500+
skillclaude_appclaude_codeclaude_api
npx skills add heygen-com/hyperframes
Hyperframes CLI
The HyperFrames CLI by job - scaffold, check, look at frames, edit the timeline, preview, render locally or in the cloud, publish, project history - p…1,464,086+
skillclaude_appclaude_codeclaude_api
npx skills add mattpocock/skills
Tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.1,046,962+
skillclaude_appclaude_codeclaude_api
npx skills add mattpocock/skills
Grilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrase…1,041,607+
skillclaude_appclaude_codeclaude_api
npx skills add mattpocock/skills
Code Review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented cod…840,484+
skillclaude_appclaude_codeclaude_api
npx skills add mattpocock/skills
Diagnosing Bugs
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing…746,030+

Audit before you install

Run any source through our checks - AI visibility, security, performance, and stack detection.

More in Development & Code