# Cavecrew

> Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".

- Skill: `rheinmir/cavecrew` (Agent Skill)
- Install (CLI): `npx skillmds@latest add rheinmir/cavecrew`
- Raw SKILL.md: https://api.skillmd.com/api/skills/rheinmir/cavecrew/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: rheinmir (https://skillmd.com/u/rheinmir)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/rheinmir/cavecrew

---


Cavecrew = three subagent presets that emit caveman output. 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` |
| Review diff, branch, or file for bugs | `cavecrew-reviewer` |
| Deep code review with rationale + alternatives | `Code Reviewer` (vanilla) |
| 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` returns ~700 tokens. 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 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.
- 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.

---

## Output Report

After all main skill tasks complete, write a propose draft to the wiki.

### Steps

**1. Build the filename:**
- Format: `DDMMYY-<ten>.md`
- `DDMMYY` = today (e.g., `020626` for 2 June 2026)
- `<ten>` = 2–4 kebab-case words summarising what was done (e.g., `landing-page-coteccons`, `brand-kit-fintech`, `ingest-auth-spec`)

**2. Write** `llmwiki/wiki/draft/cave/DDMMYY-<ten>.md`:

```
# DDMMYY-<ten>
**Type:** draft
**Status:** proposed
**Tags:** <skill-name>, output-report
**Proposed:** YYYY-MM-DD

## What
<One sentence — what this skill invocation produced or decided>

## Output
<Key artefacts, files created/modified, or decisions made>

## Files
| File | Action |
|------|--------|
| `path/to/file` | created / modified |

## Notes
- Invoked via: `/<skill-name>` skill

## Origin
- **Draft:** `wiki/draft/cave/DDMMYY-<ten>.md`
- **Commit:** _(filled by verify-before-commit)_
- **Date promoted:** _(filled by verify-before-commit)_
```

**3. Update wiki index & log:**
- `llmwiki/wiki/index.md` — append one row: `| [DDMMYY-<ten>](draft/cave/DDMMYY-<ten>.md) | draft | YYYY-MM-DD |`
- `llmwiki/wiki/log.md` — append: `## YYYY-MM-DD — <skill-name> — <ten>`

> Skip only when the skill produces zero artefacts and zero decisions (e.g., a pure display mode like `/caveman-stats`).