Borrowing it
Nothing to install: this file belongs to jentic/jentic-api-scorecard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jentic/jentic-api-scorecard/main/.claude/skills/review-community/SKILL.mdgit clone --depth 1 https://github.com/jentic/jentic-api-scorecardWrote 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/jentic/jentic-api-scorecard/review-community)<a href="https://agentmods.dev/skills/jentic/jentic-api-scorecard/review-community"><img src="https://agentmods.dev/badge/skills/jentic/jentic-api-scorecard/review-community/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/jentic/jentic-api-scorecard/review-community"><img src="https://agentmods.dev/badge/skills/jentic/jentic-api-scorecard/review-community.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 | $0.00073 | $0.00794 |
| Opus 5 | $0.00036 | $0.00397 |
| Sonnet 5 | $0.00015 | $0.00159 |
| Haiku 4.5 | $0.00007 | $0.00079 |
Grade B, and why
review-community scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
!`cat .claude/output-styles/review-comments.md` How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review-community — review someone else's PR with the community tone
This skill wraps the built-in /review command with two additions:
- Authorship guard — refuses to run if the PR author's GitHub login matches the current user's. For self-reviews, use
/reviewdirectly with its default voice. - Tone injection — inlines the diplomatic review-comments style into this turn so the tone applies without flipping the session output style. Activating the style via
/config→ Output style would replace Claude Code's default software-engineering system prompt; this skill avoids that by overlaying the tone on top of the default.
Tone for this review
The tone, structure, and constraints below are the source of truth for voice and feedback structure. Follow them for every comment drafted in this review.
!cat .claude/output-styles/review-comments.md
Phase 0 — Resolve PR and verify authorship
Run this once and use the values for the rest of the skill. set -e
ensures any failed command stops the block; if it stops, surface the
error to the user and do not proceed.
set -e
if [ -n "$ARGUMENTS" ]; then
PR="$ARGUMENTS"
else
PR=$(gh pr view --json number -q .number)
fi
PR_AUTHOR=$(gh pr view "$PR" --json author -q .author.login)
GH_USER=$(gh api user -q .login)
echo "PR=$PR"
echo "PR_AUTHOR=$PR_AUTHOR"
echo "GH_USER=$GH_USER"
Expected outcomes:
gh pr viewwith no argument fails (no PR for current branch) → stop and ask the user for a PR number or URL. Don't guess.gh api userfails or returns empty$GH_USER→ stop. The authorship guard cannot run without a confirmed login. Tell the user to authenticate (gh auth status) and try again.$PR_AUTHORequals$GH_USER→ stop. Tell the user this is their own PR and to use/reviewdirectly. Do not proceed.$PR_AUTHORdiffers from$GH_USER→ continue. State who authored the PR before starting the review, so the user has confirmation the guard saw the right author.
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.
- 10d ago First seen · 79 lines · 73 tokens per session scan B c457e440a696
review-community is a skill published in the GitHub repository jentic/jentic-api-scorecard (21 stars, last pushed today), licensed Apache-2.0. It adds 73 tokens to every session and 794 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pr-threshold
Track commit accumulation and trigger PR when thresholds crossed.
dos-verify-done-claims
Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's dos verify and dos commit-audit — never the agent's own narration.
gitlab-merge-request-review
Review and merge GitLab merge requests via the gitlab-api MCP server — by default the MRs assigned to you or where you are a reviewer, optionally scoped to a project, group, or the whole instance. Read an MR, gate it on a green pipeline (pipeline → jobs → job log), then approve, accept/merge, or set…
code-review
Systematic code review SOP covering correctness, security, performance, and maintainability — plus GitHub PR review workflow (diff, inline comments, approve via gh/REST).
OpenAPI Contract Completeness
Ensure OpenAPI specs define consistent request/response schemas, error model, auth, pagination, and backward compatibility.
fresh-eyes-review
This skill should be used as a mandatory final sanity check before git commit, PR creation, or declaring work done. Triggers on "commit", "push", "PR", "pull request", "done", "finished", "complete", "ship", "deploy", "ready to merge". Catches security vulnerabilities, logic errors, and business rule bugs that slip…