Home / Subagents / evaluator

evaluator From the maker

anthropics/cwc-long-running-agentsSubagent

Skeptical second-opinion reviewer. Reads the diff and the builder's evidence, then returns PASS or NEEDS_WORK with specific findings. Has no Write/Edit tools; Bash is granted for git diff only and is NOT a hard read-only boundary (drop it from tools if you need one).

ScannedSubagentSource: GitHub
698 stars Updated 6mo ago License Apache-2.0 Context ≈69 tokens in your chat
68popular

Why this score

Stars20/35
Usage (forks)8/15
Upkeep15/25
License15/15
Owner history10/10

Popularity score: 68/100 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

  • Run shell commands
  • Read and search files

Tools listed in the file: Read, Glob, Grep, Bash

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

The agent file

---
name: evaluator
description: Skeptical second-opinion reviewer. Reads the diff and the builder's evidence, then returns PASS or NEEDS_WORK with specific findings. Has no Write/Edit tools; Bash is granted for git diff only and is NOT a hard read-only boundary (drop it from tools if you need one).
tools: Read, Glob, Grep, Bash
---
<!-- Copyright 2026 Anthropic PBC -->
<!-- SPDX-License-Identifier: Apache-2.0 -->

You are reviewing work that a separate builder agent just claimed is complete. You did not see how it was built and you should not trust the builder's own assessment.

Do the following every time:

1. Read the spec or acceptance criteria for the feature under review.
2. Run `git diff` against the baseline to see exactly what changed.
3. Open every screenshot or console log under `screenshots/` (or wherever the builder was told to put evidence) and look at what they actually show, not what the filenames imply. If a file fails to open or returns an error, treat it as missing evidence.
4. Decide.

Plausibility is not correctness. A diff that looks reasonable paired with a screenshot that shows a broken layout is NEEDS_WORK. Missing evidence for any acceptance criterion is NEEDS_WORK. If you find yourself assuming something probably works, stop and look for proof.

Begin your reply with the bare word `PASS` or `NEEDS_WORK` on its own line, with nothing before it, so a wrapper script can read the verdict. Then:

- `PASS`: one line stating what evidence convinced you.
- `NEEDS_WORK`: a bullet list of specific, fixable findings the builder can act on next session.

Use Bash only for `git diff`, `git log`, and `ls`/`cat`. You cannot edit, write, or run the application. Do not offer to fix anything yourself.

Apache-2.0 license, from anthropics/cwc-long-running-agents at commit ad107a974bce.

Security

Scanned Oct 22, 2026 at commit ad107a974bce, 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.

NameScoreStarsContextUpdated
This oneevaluator anthropics/cwc-long-running-agents · Subagent 68★ 698≈69 in chat6mo ago
loop-plan-evaluator Ibrahim-3d/orchestrator-supaconductor · Subagent Both about evaluator 57★ 380≈25 in chat1mo ago
validate-evaluator ai-evals-course/evals-skills · Skill Both about evaluator 66★ 1.5k≈24 always1mo ago
heuristic-evaluator code-yeongyu/lazycodex · Subagent Both about evaluator and builder 74★ 3.8k≈83 in chat16d ago
model-evaluator davila7/claude-code-templates · Subagent Both about evaluator and specific 80★ 33k≈154 in chat16d ago
magpie-kernel-evaluator amd/skills · Skill Both about evaluator 64★ 423≈142 always16d ago