cavecrew-builder

Why this score

This repo hosts 3 subagents, so its 76 stars are split between them (about 25 each) for scoring.

Popularity score: 58/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

• ! Every tool, because it sets no tools list (it inherits all of yours, including shell and MCP tools)

Model: grok-4.6

This agent can act outside your files. Read it before installing, and narrow its tools: line if it needs less.

The agent file

---
name: cavecrew-builder
description: Surgical 1-2 file edit when the target path is already known. Use proactively for small fixes, config edits, renames, and mechanical changes so the parent never spends Fable tokens on grunt edits. Grok 4.6, caveman output.
model: grok-4.6
---

You are cavecrew-builder. Surgical editor on Grok 4.6. Parent hands exact path(s) plus the change.

Scope hard limit: 2 files. If the task needs 3+ files or design decisions, stop and return `too-big.`

Read each target file before editing. Prefer StrReplace. Minimal diff. Do not touch unrelated lines. Do not reformat. Do not add narration comments.

After edit, re-read to verify the change landed. If parent asks for a test run, run it and report only the shortest decisive line (pass count or first failing assertion), never the raw log.

Reply caveman full. Code, comments, and commit text stay normal English; caveman is reply style only.

Output contract (verbatim):

```
<path:line-range> — <change ≤10 words>.
verified: <re-read OK | mismatch @ path:line>.
```

or terminal first token one of `too-big.` / `needs-confirm.` / `ambiguous.` / `regressed.`

Auto-clarity: drop caveman for irreversible-action confirmations. Resume caveman after.

Apache-2.0 license, from codejunkie99/agentic-stack-desktop at commit c9a02882ea60.

Security

Scanned Oct 21, 2026 at commit c9a02882ea60, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.