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 agentmods add skills/ericboehs/claude-plugins/review-prnpx skills add ericboehs/claude-plugins --skill review-prgit clone --depth 1 https://github.com/ericboehs/claude-pluginsWhat 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 | $0.00065 | $0.00761 |
| Opus 5 | $0.00032 | $0.00380 |
| Sonnet 5 | $0.00013 | $0.00152 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
review-pr 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 2d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review
Fan out specialized reviewers as concurrent isolated pi subprocesses, then aggregate their reports. Reviewer prompts and the diff never enter your context — only the finished reports do.
Run it
plugins/pr-review/skills/review-pr/scripts/fan-out.sh
Use the absolute path to the script in this skill's directory. It prints progress to stderr and the output directory path to stdout.
| Invocation | Behavior |
|---|---|
fan-out.sh |
Auto-detects applicable aspects from the diff |
fan-out.sh all |
Runs all six reviewers |
fan-out.sh tests errors |
Runs only those reviewers |
fan-out.sh --base main |
Reviews main...HEAD |
fan-out.sh --model <m> |
Overrides the model for children |
Aspects: code (always), tests, errors, types, comments, simplify.
simplify is a polish pass — it only runs when explicitly requested or via all.
Diff range resolution
--base REF→REF...HEAD- else uncommitted changes exist →
git diff HEAD - else →
origin/<default-branch>...HEAD
Then aggregate
Read each <outdir>/<aspect>.md, then produce a single report. Do not dump the raw reports back to the user.
Merge duplicate findings reported by multiple reviewers into one entry, attributing each to its source. Preserve every file:line citation.
# PR Review Summary
_Reviewed N files across <range> with: <aspects>_
## Critical Issues (N)
- **[aspect]** Description — `file:line`
## Important Issues (N)
- **[aspect]** Description — `file:line`
## Suggestions (N)
- **[aspect]** Description — `file:line`
## Strengths
- What's genuinely well done
## Recommended Action
1. Fix critical issues first
2. Address important issues
3. Consider suggestions
4. Re-run affected reviewers to verify
Severity mapping: code confidence 90-100 and errors CRITICAL → Critical. code 80-89, errors HIGH, tests 8-10 → Important. Everything else → Suggestions.
If a reviewer reports nothing, note it in one line rather than omitting it.
What ships with it
7 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.
- 2d ago First seen · 79 lines · 65 tokens per session scan A bac349899d97
review-pr is a skill published in the GitHub repository ericboehs/claude-plugins (2 stars, last pushed 8d ago), licensed MIT. It adds 65 tokens to every session and 761 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.