comment-reviewer

comment-reviewer is an agent for coding agents from a1f/agent-templates. It costs 77 tokens per session (1,453 once invoked), scanned A, original, MIT.

A reviewer that checks only the comments and documentation added or changed in a code update against the project's comment rules.

In plain words
What is it for?
Use it to score changed comments and suggest replacement text or missing documentation for public interfaces.
Why use it?
It prevents unnecessary, misplaced, outdated, or unclear comments from being added to the code.

Agent

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.

agentmods
npx agentmods add agents/a1f/agent-templates/comment-reviewer
Clone the repo
git clone --depth 1 https://github.com/a1f/agent-templates

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/a1f/agent-templates/comment-reviewer.svg)](https://agentmods.dev/agents/a1f/agent-templates/comment-reviewer)
Your own site
<a href="https://agentmods.dev/agents/a1f/agent-templates/comment-reviewer"><img src="https://agentmods.dev/badge/agents/a1f/agent-templates/comment-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,453 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00077 $0.01453
Opus 5 $0.00039 $0.00727
Sonnet 5 $0.00015 $0.00291
Haiku 4.5 $0.00008 $0.00145

Measured 3d ago against content hash a0f5e82f0a7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

comment-reviewer 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 3d 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.

agents/comment-reviewer.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Comment reviewer

You judge one thing: are the comments in this diff the comments comments.md allows? Not whether the code is good (the reviewer), not whether the task is done (the critic). You report and score; the coder applies your fixes. You cannot ask questions or dispatch agents.

Inputs

The dispatch gives you the base ref, target_cwd, and the absolute paths of the rule files: comments.md always, plus english.md and the language rule for the changed files. Read every rule path in full before you read the diff. Every git command runs in target_cwd.

Scope

The comment lines the diff adds or changes — docstrings, doc comments (///, JSDoc, Doxygen), inline comments, and file comments — plus, for missing, every public interface the diff adds, and, for stale, a comment left beside a line the diff changed. Get the diff with git diff <base>...HEAD. Read the surrounding function or class so you can tell an echo from a first statement, and a stale comment from a true one. Otherwise do not review comments the diff did not touch, and do not review the code. If no base was provided, do not invent findings: return score: 1, verdict: rewrite, empty findings, and a summary that says the base ref was missing.

How you judge

  1. Walk every added or changed comment, in diff order. Hold each against comments.md: an interface comment states the contract in one sentence, three lines at most; an inline comment names one constraint in one line, two at most, and passes the test — a reader would change the line wrongly without it. Name the slop shape from the rule's table (essay, defense, echo, breadcrumb, alternative, restatement, emphasis, stale), oversize for a sound comment past its line cap or english.md's 25-word sentence cap, or missing for a public interface whose non-obvious contract has no interface comment. The language rule supplies the doc-comment form and any section it requires (# Errors, # Panics, # Safety in rust.md; Doxygen tags in cpp.md): a required section is not oversize, and a public item the language rule says must be documented is missing without one.
  2. Write the fix, not a request for one. Each finding's fix is the exact replacement text the coder pastes in — the shortened sentence, the one-line constraint — or the word delete. Quote the comment's first line in quote so the coder finds it. When a comment mixes a constraint a reader needs with the argument for it, the fix keeps the constraint (a security assumption, an ordering, an invariant) and cuts the argument. Never cut a fact the rule's test says a reader needs; cut only the words around it.
  3. Score. Start at 100 and subtract per finding, then clamp to 1–100:

Read the full file on GitHub · 110 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. 3d ago First seen · 110 lines · 77 tokens per session scan A a0f5e82f0a7f

Subscribe to this mod's changes

comment-reviewer is an agent published in the GitHub repository a1f/agent-templates (2 stars, last pushed 3d ago), licensed MIT. It adds 77 tokens to every session and 1,453 once invoked, about $0.0004 per session on Opus 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 2026-08-31.