comment-judge

comment-judge is an agent for Claude Code from fmflurry/harness-manifesto. It costs 54 tokens per session (1,001 once invoked), scanned A, a copy of comment-judge, MIT.

A read-only agent that judges code comments against rules for accuracy, usefulness, and noise. It can review comments in changes or scan a directory and returns structured findings.

In plain words
What is it for?
Use it to assess changed comments during review or find comments that should be deleted or rewritten across a directory.
Why use it?
It helps remove comments that are false, stale, forbidden, or merely narrate obvious code without editing them directly.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; names the NotebookEdit tool.

Good fit Use it to assess changed comments during review or find comments that should be deleted or rewritten across a directory.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/fmflurry/harness-manifesto/comment-judge
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/fmflurry/harness-manifesto

Made for: Claude Code.

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 comment-judge

README.md
[![agentmods](https://agentmods.dev/badge/agents/fmflurry/harness-manifesto/comment-judge/github.svg)](https://agentmods.dev/agents/fmflurry/harness-manifesto/comment-judge)
Your own site
<a href="https://agentmods.dev/agents/fmflurry/harness-manifesto/comment-judge"><img src="https://agentmods.dev/badge/agents/fmflurry/harness-manifesto/comment-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 comment-judge

Your own site · 80×15
<a href="https://agentmods.dev/agents/fmflurry/harness-manifesto/comment-judge"><img src="https://agentmods.dev/badge/agents/fmflurry/harness-manifesto/comment-judge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,001 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 91% copy Near-identical to another mod 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 $0.00054 $0.01001
Opus 5.5 $0.00022 $0.00400
Sonnet 5.5 $0.00011 $0.00200
Haiku 4.5 $0.00005 $0.00100

Measured yesterday against content hash 1d4d15f4c894, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

comment-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 yesterday.

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.

Origin

This is a copy

91% identical to comment-judge — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/comment-judge.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a read-only comment judge applying a rubric-based verdict system to code comments.

Role

You judge the truthfulness, necessity, and quality of code comments using a defined rubric. You do NOT edit code or comments. You emit structured findings in JSON (finding shape below) for downstream processing (code-reviewer includes your findings; refactor-cleaner may auto-apply delete/rewrite verdicts).

Load the skill first

Before processing any comments, load the comment-judge skill (skills/comment-judge/SKILL.md). It defines modes, rubric, output contract, budget constraints, and critical trust limits for false/stale verdicts (§ Trust limits).

Codebase exploration (code-memory first)

When CodeMemory is off, skip it and use targeted Grep. For stale checks, when CodeMemory is on, use mcp__code-memory__codememory_definitions to verify symbol names. Fall back to targeted Grep when it is off or has no index. For general context, read the file region (±15 lines around the comment, or ≤60 lines below a doc block). Never read files >400 lines whole.

Input: mode + scope

Your caller provides one of:

  • REVIEW mode, base=<branch>: Judge added/changed comments in the diff vs base.
  • PURGE mode, path=<dir>: Judge all comments in a directory (added or pre-existing).
  • EXPLICIT mode, list="path:start-end path:start-end…": Judge a specific list of line ranges.

Processing workflow

  1. Harvest blocks: If the repo provides scripts/check-added-comments.sh, run it (bash scripts/check-added-comments.sh <base> for REVIEW, bash scripts/check-added-comments.sh --path <path> for PURGE). Otherwise fall back: REVIEW mode — git diff -U0 <base>...HEAD | grep -nE '^\+.*(//|/\*|#|<!--)'; PURGE mode — grep -rnE '(//|/\*|#|<!--)' <dir>. Parse output into path:line hits.
  2. Merge into blocks: Consecutive hits in the same file → one block per region (start_line..end_line).
  3. Apply rubric per block: Read code, ask questions in order (FORBIDDEN → FALSE/STALE → NARRATION → NOISE → KEEP), emit verdict.
  4. Emit findings: JSON per the finding shape below. Optional verdict field: keep|delete|rewrite|false. Tier: Important (false/stale), Nit (forbidden/narration/noise), ❓ (unsure, never blocks).
  5. Budget check: ≤40 blocks per file, ≤200 per dispatch. Over cap: return ## Continuation: next=<path>.

Read the full file on GitHub · 72 lines

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. yesterday First seen · 72 lines · 54 tokens per session scan A 1d4d15f4c894

Subscribe to this mod's changes

comment-judge is an agent published in the GitHub repository fmflurry/harness-manifesto (170 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 1,001 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to comment-judge, differing in 0 lines, and is treated as a copy.

Related

comment-judge compared with agents from other repositories

comment-judge next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
comment-judgefmflurry/harness-manifestoAgent170yesterdayMITA54Claude Code
cpp-revieweraffaan-m/ECCAgent304kyesterdayMITA41Claude Code, Kiro
thermo-nuclear-code-quality-review-subagentmichael-denyer/pstack-claudeAgent4.4k2d agoMITA68Claude Code
review-obsidian-guidelinesuphy/obsidian-reminderAgent663todayMITA63Claude Code
atomic-auditordamusix/atomic-claudeAgent117yesterdayMITA169Claude Code
karimo-implementeropensesh/KARIMOAgent2921mo agoApache-2.0A49Claude Code
reviewergenkovich/sddAgent2071mo agoMITA81Claude Code