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.
git clone --depth 1 https://github.com/idavidov13/agentic-playwrightWrote 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/commands/idavidov13/agentic-playwright/pr-reviewer)<a href="https://agentmods.dev/commands/idavidov13/agentic-playwright/pr-reviewer"><img src="https://agentmods.dev/badge/commands/idavidov13/agentic-playwright/pr-reviewer/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/commands/idavidov13/agentic-playwright/pr-reviewer"><img src="https://agentmods.dev/badge/commands/idavidov13/agentic-playwright/pr-reviewer.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 | $0.00075 | $0.02219 |
| Opus 5 | $0.00037 | $0.01110 |
| Sonnet 5 | $0.00015 | $0.00444 |
| Haiku 4.5 | $0.00007 | $0.00222 |
Grade A, and why
pr-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Reviewer
You are reviewing a branch as a pull request, the way a careful human reviewer on this team would — against this repo's own contract, not generic best practice. The contract is CLAUDE.md (the Constitution — MUST / SHOULD / WON'T tables) plus the specialized skill files in .claude/skills/ that govern whatever the branch touched. A finding only counts if you can tie it to a concrete rule, a real bug, or a coverage gap — opinion without a rule behind it is noise.
The deliverable is a report, not a code change. Fixing is opt-in, after the report.
Input
Ask for a branch name if not given. The base branch is auto-resolved (Phase 1): origin/HEAD (main or master), falling back to master. Accept an override.
Workflow — phases in order
Phases 1–7 always run (Phase 6 is a mandatory gate before the report). Phases 8–9 are gated on user opt-in.
Phase 1 — Fetch & switch
BASE=$(git symbolic-ref --short refs/remotes/origin/HEAD 2>/dev/null | sed 's#^origin/##')
BASE=${BASE:-master}
git fetch origin "${input:branch}" "$BASE"
git switch "${input:branch}"
- Dirty tree (
git status --porcelainnon-empty) → STOP and ask before switching (offergit stash+ restore). Never switch over uncommitted work silently. - Missing branch on
origin→ report and stop. - Below,
master= the resolved$BASE.
Phase 2 — Diff against the merge-base (THREE-DOT, MANDATORY)
git diff master...HEAD --stat
git diff master...HEAD
Three-dot diffs against the merge-base — only what the branch authored. Two-dot (master..HEAD) drags in master's later commits → false findings against code the author never wrote. NEVER use two-dot. Confirm every finding's hunk is in the three-dot diff. Read the whole diff before forming an opinion.
Phase 3 — Route changed paths to skills
Read the routed skill files in .claude/skills/<name>/SKILL.md before reviewing; always also hold CLAUDE.md.
| Changed path (glob) | Read these skills |
|---|---|
tests/**/api/** |
api-testing, test-standards, type-safety |
tests/**/e2e/**, tests/**/functional/** |
test-standards, page-objects, fixtures |
tests/**/*.setup.ts |
helpers, fixtures, test-standards |
pages/** |
page-objects, selectors, playwright-cli |
fixtures/api/schemas/** |
type-safety, api-testing |
fixtures/** |
fixtures, helpers |
test-data/factories/** |
data-strategy, type-safety |
test-data/static/** |
data-strategy, refactor-values, type-safety |
enums/** (new values) |
enums |
enums/**, test-data/static/** (changed existing values) |
refactor-values |
config/** |
config |
helpers/** |
helpers |
any **/*.ts |
type-safety |
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.
- yesterday First seen · 139 lines · 75 tokens per session scan A 313598bce4a2
pr-reviewer is a command published in the GitHub repository idavidov13/agentic-playwright (162 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 2,219 once invoked, about $0.0004 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 2026-09-08.
Other commands, from other repositories
prp-commit
Quick commit with natural language file targeting: describe what to commit in plain English.
hatch3r-pr-resolve
Read open PR comments, evaluate each against current code via the rigor contract, implement accepted findings, reply inline. Multi-platform.
pr-description
Write a pull request description that helps reviewers: what changed, why, and how to verify, from a diff.
pr-package
Prepare a clean delivery package for GitHub from the real git diff vs an explicit base branch, persisted as PRPACKAGE.md (or PRPACKAGE. .md for multi-repo tasks). Produces branch name, commit messages, fetch, checkout, add, commit, and push commands, PR title and body, and reviewer attention points; never invents work…
remove-deadcode
Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits.
elegant-code-review
Review the current working diff against the elegant-code decision ladder and propose deletions, honoring the negligence floor.