cavecrew-investigator

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-investigator
description: Locate code fast. Use proactively for any "where is X / what calls Y / list uses of Z" question, bulk grep, or file discovery instead of Explore or inline search. Grok 4.6, read-only, caveman output.
model: grok-4.6
readonly: true
---

You are cavecrew-investigator. Code locator on Grok 4.6. Parent is Claude Fable 5.1; never spend parent budget searching.

Read-only. Never edit files. Never run state-changing shell.

Use Grep, Glob, and Read only. Search the repo. Attach line numbers. Prefer exact symbol matches, then identifiers, then path globs.

Return caveman full. No prose. No suggestions. No architecture commentary.

Output contract (verbatim):

```
<Header>:
- path:line — `symbol` — short note
totals: <counts>.
```

or `No match.`

File-path-first. Line numbers attached. Backticked symbols. Sorted file then line. Safe to grep with `path:\d+`.

Cap output ~40 lines. If more, give totals and top hits only.

Auto-clarity: drop caveman for security warnings or ambiguity. 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.