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.
npx skills add LaStrada/claude --skill review-commentsgit clone --depth 1 https://github.com/LaStrada/claudeWrote 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/skills/lastrada/claude/review-comments)<a href="https://agentmods.dev/skills/lastrada/claude/review-comments"><img src="https://agentmods.dev/badge/skills/lastrada/claude/review-comments/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/skills/lastrada/claude/review-comments"><img src="https://agentmods.dev/badge/skills/lastrada/claude/review-comments.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 | $0.00091 | $0.02893 |
| Opus 5.5 | $0.00036 | $0.01157 |
| Sonnet 5.5 | $0.00018 | $0.00579 |
| Haiku 4.5 | $0.00009 | $0.00289 |
Grade A, and why
review-comments 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
review-comments
Audit every comment, docstring, and adjacent documentation block that is new or changed in the current change set. For each one, decide: keep, tighten, rephrase, or drop. Then surface the verdicts as a table with concrete suggested rewrites, and wait for approval before editing.
Two rules drive the audit:
- The default is no comment. A comment exists only when the WHY is non-obvious — a hidden constraint, a subtle invariant, a workaround, an intentional non-action, behaviour that would surprise the reader. If the code already tells the same story through naming, the comment is noise.
- Comments belong to the code, not the conversation. They must read sensibly to someone who arrives 6 months later, never saw the PR or change set, doesn't have access to internal memory, and can't tell what "previously" or "now" refers to.
When this applies
Trigger phrases (not exhaustive):
- "review the comments" / "review the new comments" / "review the changed comments"
- "audit the comments" / "comment audit" / "audit the docs"
- "are the comments overkill" / "too many comments" / "too verbose"
- "check the comments before commit" / "comments before PR" / "comment hygiene"
- "shorten / trim / tighten the comments" / "are the docstrings too long"
- "review the docs" — when scoped to docs that move with this change set
- The user invokes
/review-commentsdirectly.
Do NOT trigger for:
- Full PR / code review (use
review,code-review, orpr-review-toolkit:review-pr). - Writing new comments from scratch — this skill audits, doesn't draft.
- "What does this comment mean" — that's explanation, not audit.
- Reviewing arbitrary unchanged markdown not touched by the change set.
Scope — what counts as "new or changed"
Always include:
- Lines added in the diff (
+lines). - Comment blocks where any line changed (
-immediately followed by+with comment syntax on either side counts as a modified block — review the new version). - Every comment in newly-added files. (Whole-file additions are entirely "new" by definition.)
- Doc comments adjacent to changed code, even if the doc itself didn't textually change — if the underlying function's signature or behaviour changed, the doc may now be stale. Flag those as "stale-check" rather than re-evaluating their wording.
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 · 198 lines · 91 tokens per session scan A 8b99707bf7d8
review-comments is a skill published in the GitHub repository LaStrada/claude (2 stars, last pushed 4mo ago), licensed MIT. It adds 91 tokens to every session and 2,893 once invoked, about $0.0004 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 skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…