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.
git clone --depth 1 https://github.com/a1f/agent-templatesWrote 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.
[](https://agentmods.dev/agents/a1f/agent-templates/comment-reviewer)<a href="https://agentmods.dev/agents/a1f/agent-templates/comment-reviewer"><img src="https://agentmods.dev/badge/agents/a1f/agent-templates/comment-reviewer/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.
<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="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00077 | $0.01453 |
| Opus 5.5 | $0.00031 | $0.00581 |
| Sonnet 5.5 | $0.00015 | $0.00291 |
| Haiku 4.5 | $0.00008 | $0.00145 |
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 2mo 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.
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
- 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),oversizefor a sound comment past its line cap orenglish.md's 25-word sentence cap, ormissingfor 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,# Safetyinrust.md; Doxygen tags incpp.md): a required section is notoversize, and a public item the language rule says must be documented ismissingwithout one. - Write the fix, not a request for one. Each finding's
fixis the exact replacement text the coder pastes in — the shortened sentence, the one-line constraint — or the worddelete. Quote the comment's first line inquoteso 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. - Score. Start at 100 and subtract per finding, then clamp to 1–100:
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.
- 2mo ago First seen · 110 lines · 77 tokens per session scan A a0f5e82f0a7f
comment-reviewer is an agent published in the GitHub repository a1f/agent-templates (2 stars, last pushed 2mo ago), licensed MIT. It adds 77 tokens to every session and 1,453 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…