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 fmflurry/settings-opencode --skill comment-judgegit clone --depth 1 https://github.com/fmflurry/settings-opencodeWrote 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/fmflurry/settings-opencode/comment-judge)<a href="https://agentmods.dev/skills/fmflurry/settings-opencode/comment-judge"><img src="https://agentmods.dev/badge/skills/fmflurry/settings-opencode/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.
<a href="https://agentmods.dev/skills/fmflurry/settings-opencode/comment-judge"><img src="https://agentmods.dev/badge/skills/fmflurry/settings-opencode/comment-judge.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 | $0.00087 | $0.02597 |
| Opus 5.5 | $0.00035 | $0.01039 |
| Sonnet 5.5 | $0.00017 | $0.00519 |
| Haiku 4.5 | $0.00009 | $0.00260 |
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 19d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
comment-judge
LLM-as-a-judge for code comments. Applies rubric-based verdict, harvests blocks, emits structured findings. Loaded in-process by code-reviewer/dotnet-cop/angular-cop during review; used by the comment-judge agent for module-scoped purges.
Modes
REVIEW: Candidates are added/changed comments in the diff. Source: bash scripts/check-added-comments.sh <base> if the repo provides that script; otherwise git diff -U0 <base>...HEAD | grep -nE '^\+.*(//|/\*|#|<!--)', merged with pre-existing comments within ±10 lines of changed hunks (git diff -U10 <base>...HEAD | grep -nE '^\+.*(//|/\*|#|<!--)'). Goal: verify each comment truthfully describes code behavior.
PURGE: Scans a directory for all comments (added or pre-existing). Source: bash scripts/check-added-comments.sh --path <dir> if available; otherwise grep -rnE '(//|/\*|#|<!--)' <dir> (directory-scoped only; repo-wide is prohibitively slow). Goal: delete stale, false, forbidden, or noisy comments in bulk.
EXPLICIT: Caller supplies a list of path:start-end line ranges (used for manual calibration and edge-case handling).
Grouping
Merge consecutive path:line hits in the same file into blocks: start_line..end_line. One block = one contiguous region. Emit verdict and reasoning once per block, not per line.
Asymmetric cost (REVIEW vs PURGE)
REVIEW mode: Missing a false comment is costly (reviewers trust the code). A wrong flag is cheap (human ignores). Strategy: flag suspected false/stale/forbidden comments even with partial evidence. Tier as ❓ (low) when evidence is incomplete.
PURGE mode: Verdicts are bulk-applied to many files. Delete only at high confidence (🔴 or 🟡). Any doubt → keep + ❓ marker for follow-up.
Never auto-apply false: Comment may be correct and code may be wrong = possible bug. Always require human review.
Rubric
Read the code the comment describes: enclosing symbol, or ±15 lines, or ≤60 lines below a doc block. Never read files >400 lines whole. For stale checks, use codememory_definitions or one targeted Grep.
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.
- 19d ago First seen · 146 lines · 87 tokens per session scan A 32a85232366d
comment-judge is a skill published in the GitHub repository fmflurry/settings-opencode (171 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 2,597 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 2026-09-27.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
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"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
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…