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 guimatheus92/pr-review --skill helpgit clone --depth 1 https://github.com/guimatheus92/pr-reviewWrote 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/guimatheus92/pr-review/help)<a href="https://agentmods.dev/skills/guimatheus92/pr-review/help"><img src="https://agentmods.dev/badge/skills/guimatheus92/pr-review/help/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/guimatheus92/pr-review/help"><img src="https://agentmods.dev/badge/skills/guimatheus92/pr-review/help.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 | $0.00201 | $0.00718 |
| Opus 5.5 | $0.00080 | $0.00287 |
| Sonnet 5.5 | $0.00040 | $0.00144 |
| Haiku 4.5 | $0.00020 | $0.00072 |
Grade A, and why
help 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 1mo 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.
What it actually says
pr-review — help & documentation
One skill, all the docs. Read the matching reference file for the topic — each is the full guide, kept short so this index stays cheap to load.
| If asked about… | Read |
|---|---|
| Quickstart: install, authenticate, daily usage, common flags | reference/pr-review-usage.md |
Publication volume vs pipeline status: --publish-min-severity, --fail-on, dry-run evidence and sticky resume |
reference/pr-review-usage.md, reference/ci-integration.md |
| Configuration: 5-level merge, YAML, env vars, models, extra paths | reference/configuration.md |
| Review passes & skills: skill packs, how passes are selected, frontmatter, the on-demand index | reference/reviewers-vs-skills.md |
Managing skills & packs: add your own, packs sync/add/suggest, override, disable, list what's loaded |
reference/adding-your-own-md.md |
| Companion plugins: pr-review-toolkit, code-review — install, auto-invocation, opting out | reference/companion-plugins.md |
CI/CD: GitHub Actions, Azure DevOps Pipelines, exit codes, --fail-on gating |
reference/ci-integration.md |
| Caching: gather cache, invalidation, bypass flags, clearing | reference/caching.md |
| Performance: diff exclusion, pre-filtering, single-session, early-exit, size limits | reference/performance.md |
| Architecture: execution model, source map, design decisions, resume/background | reference/architecture.md |
| Guarantees: what pr-review always does and never does, and how to audit a run against them | ../../INVARIANTS.md |
Answer from the reference file's content; don't guess. When a question spans topics (e.g. "why is my large PR rejected and how do I speed it up?"), read both relevant files.
What ships with it
9 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.
- reference/adding-your-own-md.md 9.3 KB
- reference/architecture.md 23 KB
- reference/caching.md 4.0 KB
- reference/ci-integration.md 8.8 KB
- reference/companion-plugins.md 9.8 KB
- reference/configuration.md 11 KB
- reference/performance.md 5.9 KB
- reference/pr-review-usage.md 12 KB
- reference/reviewers-vs-skills.md 8.6 KB
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.
- 1mo ago Changed · +1 lines c41a6e70b47b
- 1mo ago Changed · +1 lines · +58 tokens per session af8917ca2679
- 1mo ago First seen · 25 lines · 143 tokens per session scan A 83526547f480
help is a skill published in the GitHub repository guimatheus92/pr-review (3 stars, last pushed 6d ago), licensed MIT. It adds 201 tokens to every session and 718 once invoked, about $0.0008 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
review
Adversarial review of an increment before it ships, by a fresh context or another model family; every finding cites path:line and is re-verified. Use for "review", "qa", "critique this".
sw-review
Adversarial review of an increment before it ships, by a fresh context or another model family; every finding cites path:line and is re-verified. Use for "review", "qa", "critique this".
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…
code-review
You are a senior code reviewer. You receive diffs via stdin.
sw-do
Work a SpecWeave increment task by task - claim, implement inside its Files, test, commit, done with evidence - alone, unattended or in lanes, then close. Use for "implement", "continue", "auto".