agentmods.dev

judge

judge is an agent for Claude Code from bendrucker/claude. It costs 46 tokens per session (396 once invoked), scanned A, original, MIT.

A worker task that judges source-code comments against a supplied rubric and records one decision for each comment. Its decisions can keep, shorten, or rewrite comments.

In plain words
What is it for?
It helps audit comment quality in batches, explain why a comment should change, and produce replacement wording when required.
Why use it?
Large comment reviews are easier to process consistently when each comment is checked against the same written rules. The saved verdicts provide a structured record for the next review step.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the comments plugin — 1 skill, 1 agent shipped together

not rated 18repo today A scan 46 tokens original MIT

Good fit It helps audit comment quality in batches, explain why a comment should change, and produce replacement wording when required.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/bendrucker/claude/judge
View source ↗ bendrucker/claude
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/bendrucker/claude

Made for: Claude Code.

Or install comments, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for judge

README.md
[![agentmods](https://agentmods.dev/badge/agents/bendrucker/claude/judge/github.svg)](https://agentmods.dev/agents/bendrucker/claude/judge)
Your own site
<a href="https://agentmods.dev/agents/bendrucker/claude/judge"><img src="https://agentmods.dev/badge/agents/bendrucker/claude/judge/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for judge

Your own site · 80×15
<a href="https://agentmods.dev/agents/bendrucker/claude/judge"><img src="https://agentmods.dev/badge/agents/bendrucker/claude/judge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 396 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.00396
Opus 5.5 $0.00018 $0.00158
Sonnet 5.5 $0.00009 $0.00079
Haiku 4.5 $0.00005 $0.00040

Measured 10d ago against content hash 455609698570, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

judge scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/comments/agents/judge.md · 26 lines

What it actually says

The prompt gives the rubric path, the shard path, and the verdict path. Read the rubric, then the shard.

The shard is { "id": <shard id>, "comments": [{ "id", "path", "language", "kind", "text", "context", "provenance"?, "doc"? }] }. provenance, when present, is the git blame of the comment's lines, and the rubric says how to weigh it. doc, when present, marks the language's formal doc comment for a declaration or module, and the rubric's Doc Comments section says how to judge it.

Judge every comment in the shard against the rubric. Produce exactly one verdict per comment, keyed by its id. Each verdict holds:

  • action: keep, trim, or rewrite.
  • category: the rubric category it fails, or null for keep.
  • confidence: low, medium, or high.
  • rationale: one sentence.
  • rewrite: the de-voiced comment text when action is rewrite, otherwise null.
  • trimTo: only for a partial trim, the kept comment rewritten to read as complete sentences, delimiters included, with no leading indentation. Omit it to delete the whole comment.

Write { "verdicts": [{ "id": <comment id>, "verdict": { ... } }] } to the verdict path with the Write tool.

Reply with one line: <comments judged> judged, <verdicts other than keep> flagged.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 26 lines · 46 tokens per session scan A 455609698570

Subscribe to this mod's changes

judge is an agent published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 396 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-31.

Claude CodeCode reviewclaude-code-plugin
Related

judge compared with agents from other repositories

judge next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
judgebendrucker/claudeAgent18todayMITA46Claude Code
code-reviewernyldn/claude-octopusAgent4.4ktodayMITA19Claude Code
edge-case-explorertestdouble/hanAgent3428d agoMITA135Claude Code
integrations-engineeravelikiy/great_ctoAgent113todayMITA106Claude Code
adversarial-validatortestdouble/hanAgent3428d agoMITA45Claude Code
code-reviewerNikiforovAll/claude-code-rulesAgent1427d agoApache-2.0A37Claude Code
reviewerswingerman/engineerAgent16313d agoMITA52Claude Code