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 stark-ai-de/agent-skills --skill pr-reviewgit clone --depth 1 https://github.com/stark-ai-de/agent-skillsWrote 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/stark-ai-de/agent-skills/pr-review)<a href="https://agentmods.dev/skills/stark-ai-de/agent-skills/pr-review"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/pr-review/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/stark-ai-de/agent-skills/pr-review"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/pr-review.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 | $0.00050 | $0.00612 |
| Opus 5 | $0.00025 | $0.00306 |
| Sonnet 5 | $0.00010 | $0.00122 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
pr-review 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 11d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review
Goal
Produce a maintainer-grade review that prioritizes correctness, regressions, missing tests, security concerns, docs drift, and release risk over style-only feedback.
When to use
- The user asks for a PR review, diff review, or merge readiness check.
- A branch or worktree needs review before merge.
- Agent-authored changes need an independent risk pass.
When not to use
- The user asks to implement fixes immediately; review only if requested.
- The change is only documentation; consider
docs-audit. - The request is a whole-repo health review; use
repo-health-audit.
Inputs to inspect
- PR description, changed files, commits, and diff stats.
- Relevant source files, tests, docs, CI output, and release notes.
- Existing architecture or workflow docs that govern touched areas.
Review rubric
Check behavior changes, API contracts, data migrations, error handling, tests, docs, security-sensitive paths, dependencies, and deployment risk. Read references/review-rubric.md for detailed prompts and references/risk-table-template.md for report format.
Workflow
- Inspect diff stats and changed file names first.
- Identify user-visible behavior and contract changes.
- Read only the surrounding code needed to verify risk.
- Check tests and docs touched by the change.
- Run or report relevant validation if available.
- Lead with findings ordered by severity and include file/line evidence.
- Include a verdict only after findings.
Safety rules
- Do not approve, merge, push, or dismiss review comments unless explicitly authorized.
- Do not expose secrets from diffs, logs, or CI output.
- Separate confirmed findings from assumptions and coverage limits.
References
Read only when needed:
references/review-rubric.mdreferences/risk-table-template.md
Scripts
No bundled scripts.
Output format
Return:
- Verdict
- Blocking issues
- Non-blocking suggestions
- Test coverage
- Release risk
- Suggested review comments
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 89 lines · 50 tokens per session scan A d3bd2da11a50
pr-review is a skill published in the GitHub repository stark-ai-de/agent-skills (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 50 tokens to every session and 612 once invoked, about $0.0003 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.
Other skills, from other repositories
openlore-execute-refactor
Apply a confirmed .openlore/refactor-plan.md with a test gate after each change. Use when asked to execute or continue an OpenLore refactoring plan.
openlore-review-changes
Review code changes using OpenLore risk, call, coverage, and cluster evidence without editing code. Use when asked for a change review, pre-PR safety check, or merge recommendation.
architect-init
Reverse-engineer architecture from an existing codebase to create ADRs documenting discovered decisions. Use when bootstrapping architecture documentation for brownfield projects.
architect-analyze
Analyze architecture for consistency between ADRs and AD, completeness, and quality issues. Use when validating generated or refined architecture artifacts, before feature development, during architecture review, or periodically to detect drift.
rescue
Delegate a substantial diagnosis, implementation, or follow-up task to Claude Code through the tracked-job runtime. Args: --background, --wait, --resume, --resume-last, --fresh, --write, --model , --effort , --prompt-file , [task text]. Defaults to opus with no forced effort. Use when Claude should investigate or…
adversarial-review
Run a design-challenging Claude Code review of local git changes in this repository. Args: --wait, --background, --base , --scope , --model , --effort , [focus text]. Defaults to opus with no forced effort. Use only when the user wants stronger scrutiny than a normal review, such as explicit tradeoff challenge…