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 MithunWijayasiri/dotclaude --skill pr-reviewgit clone --depth 1 https://github.com/MithunWijayasiri/dotclaudeWrote 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/mithunwijayasiri/dotclaude/pr-review)<a href="https://agentmods.dev/skills/mithunwijayasiri/dotclaude/pr-review"><img src="https://agentmods.dev/badge/skills/mithunwijayasiri/dotclaude/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/mithunwijayasiri/dotclaude/pr-review"><img src="https://agentmods.dev/badge/skills/mithunwijayasiri/dotclaude/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 | $0.00062 | $0.01921 |
| Opus 5.5 | $0.00025 | $0.00768 |
| Sonnet 5.5 | $0.00012 | $0.00384 |
| Haiku 4.5 | $0.00006 | $0.00192 |
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 27d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review
Review a change for defects. Bugs first, structure second, style last.
1. Resolve the target
| Input | Commands |
|---|---|
| Nothing | git diff + git diff --cached (uncommitted) |
| PR number / URL | gh pr view <n> then gh pr diff <n> |
| Base branch named, you are on the branch under review | git diff <base>...HEAD |
| Branch to review named, you are elsewhere | git diff HEAD...<branch> |
| Commit SHA | git show <sha> |
since X / tag / HEAD~5 |
git diff X...HEAD + git log X..HEAD --oneline |
| File path | review that file's current state |
Three-dot is merge-base: A...B shows B's side. Point it the wrong way and you silently review the opposite branch. Run git branch --show-current before choosing the row.
Validate before reviewing:
- Ref (branch, commit, tag, range) →
git rev-parse <ref>. - PR →
gh pr view <n>; a fork PR may have no local ref. - File path → exists and readable; review it whether or not it changed.
Bad target or empty diff → stop and say so. Ambiguous input → ask; never review a guessed target.
Counts for the §7 header: git diff --shortstat <range>, or gh pr view <n> --json title,body,additions,deletions,changedFiles — also returns the PR intent.
2. Gather context
A diff alone misleads — code wrong in isolation is often right in context, and vice versa.
- Full file for up to ~5 key changed files (entry points, trust boundaries, shared modules); hunk plus enclosing function for the rest. Over ~15 files → state which you read in full.
- Repo standards if present:
CLAUDE.md,.claude/rules/*.md,CONTRIBUTING.md,CODING_STANDARDS.md,AGENTS.md,CONVENTIONS.md. A documented standard overrides every default here and inreferences/. - Spec: issue ref in commits (
gh issue view <n>), ticket key in branch name, or a doc underdocs//specs/. None → skip the spec axis, say so in the report. Never invent requirements. - Input, auth, storage, network, rendering, or secrets touched → trace the trust boundary, not just the changed lines.
What ships with it
8 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.
- 27d ago Changed · +2 lines 3f8a4acda551
- 1mo ago First seen · 142 lines · 62 tokens per session scan A 59f4c5492279
pr-review is a skill published in the GitHub repository MithunWijayasiri/dotclaude (4 stars, last pushed 6d ago), licensed MIT. It adds 62 tokens to every session and 1,921 once invoked, about $0.0002 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 2026-09-20.
Other skills, from other repositories
auditing-skills
Use when checking this repository's skills for security or quality issues before sharing them, or remediating findings across skills.
ship-it-or-fix-it
Oracle-frozen Builder and independent-Judge convergence cycle. Load ONLY when the operator explicitly sets Governance Dial G2 for the task, or explicitly names this skill or an active work unit already running it. Never auto-activate on task class, such as security, auth, or payments. If a task seems to warrant G2 and…
test-verification
Requires behavioral, failure-path, and durable-seam evidence for tests and review. Use when writing tests, reviewing test coverage, assessing behavioral test quality, or accepting high-risk behavior on test evidence.
nitpicker
Hostile audit toolkit: one entry point dispatching specialist commands — adversarial review, security, tests, docs, types, architecture, performance, reliability, caching, concurrency, error handling, resource leaks, dependencies, licensing, CI, commits, migrations, observability, API contracts, a11y, i18n, privacy…
new-command
Scaffolds a new nitpicker audit command through the full RED → GREEN → REFACTOR → adversarial-review → validate cycle, wiring its command file, dispatch-table row, and docs together. Use when adding a new /nitpicker command to this repository, or when asked to create, scaffold, or add an audit command here.
pr-buddy
Two-phase PR review companion. Phase 1: Socratic conversational walkthrough that builds the reviewer's mental model through guided questions — fighting cognitive debt by ensuring comprehension before approval. Phase 2: automated quality checks via pr-review-toolkit (Claude Code) or inline review (any host). Use when…