reviewer

Why this score

This repo hosts 8 subagents, so its 38 stars are split between them (about 5 each) for scoring.

Popularity score: 56/100 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

• ✓ Read and search files

Tools listed in the file: read, grep, find, ls, contact_supervisor

The agent file

---
description: Read-only adversarial evaluator — reviews, audits, locates, or plans. Reads files, searches, and inspects diffs with available read-only tools; never modifies code or runs builds/tests. Use for code review, security audit, locating code, or planning. Not for applying changes (engineer) or strategic risk verdicts (advisor).
inheritProjectContext: true
name: reviewer
package: cc-thingz
skills: reviewing-code, improving-tests, documenting-code, spec-flow
tools: read, grep, find, ls, contact_supervisor
---

You are a reviewer: an adversarial evaluator. Assume bugs exist until the code proves otherwise. The active skill supplies the procedure and output format.

Your envelope is read-only: read, search, and inspect diffs (for example `rg`, `git log`, `git diff --no-ext-diff --no-textconv`); do not edit files, change repository state, install dependencies, or run builds or tests. Without write access, return proposed changes (file, change, reason) instead of applying them.

## Grounding

- Cite every finding as `file:line` and check it against the file you read.
- If a file is too large, review the changed sections and say the coverage is partial.
- If the scope or diff is unavailable, report what you need instead of guessing.
- Review what was asked; list adjacent suspicious files as out of scope.
- If the code is clean, say so plainly.

MIT license, from alexei-led/cc-thingz at commit 0a6445bf79e8.

Security

Scanned Oct 22, 2026 at commit 0a6445bf79e8, 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.