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 magic3007/dotfiles --skill pr-reviewgit clone --depth 1 https://github.com/magic3007/dotfilesWrote 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/magic3007/dotfiles/pr-review)<a href="https://agentmods.dev/skills/magic3007/dotfiles/pr-review"><img src="https://agentmods.dev/badge/skills/magic3007/dotfiles/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/magic3007/dotfiles/pr-review"><img src="https://agentmods.dev/badge/skills/magic3007/dotfiles/pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00028 | $0.01651 |
| Opus 5.5 | $0.00011 | $0.00660 |
| Sonnet 5.5 | $0.00006 | $0.00330 |
| Haiku 4.5 | $0.00003 | $0.00165 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Code Review (Dynamic Agent Allocation)
Intelligent code review for the current branch's Pull Request. Dynamically generates targeted review tasks based on PR changes.
Usage
Invoke with /pr-review or when the task matches.
Arguments:
- No arguments: Review PR for current branch
- PR number: Review specific PR (e.g.,
pr-review 123) --quick: Quick mode, only run Phase 1 analysis
Quick Start
- Get current branch PR:
gh pr view --json number,title,state,isDraft - If PR doesn't exist or is closed, stop and explain
- Execute Phases 1-4 in order
Workflow Overview
Phase 1: Deep PR Analysis
├─ 1.0 PR Status Check
├─ 1.1 Get PR Summary
└─ 1.2-1.4 Change Type Detection
↓
Phase 2: Dynamic Agent Planning
↓
Phase 3: Execute Review Tasks [Parallel]
↓
Phase 4: Confidence Scoring & Summary
Model Configuration
| Mode | CRITICAL/HIGH | MEDIUM | LOW |
|---|---|---|---|
| Default | Opus | Sonnet | Haiku |
Quick (--quick) |
Sonnet | Sonnet | Sonnet |
Economy (--economy) |
Sonnet | Haiku | Haiku |
Phase 1: Deep PR Analysis
1.0 PR Status Check
Check if PR should be reviewed:
- Is it closed? → Stop
- Is it a draft? → Note but continue
- Is it bot-generated? → Skip
1.1 Get PR Summary
Get basic PR info: title, description, modified files, change summary.
1.2 Change Type Detection
Analyze each file change, detecting change types by risk level.
CRITICAL level types: FrameworkA, FrameworkB, FrameworkC, FrameworkD HIGH level types: distributed comm, DTensor, MoE, TP/EP/CP MEDIUM level types: tensor ops, workflow, API, compile LOW level types: tests, docs, config
1.3 Framework-Specific Risk Identification
Based on detected types, identify corresponding risks.
1.4 Output Change Analysis Report
CHANGE_ANALYSIS_REPORT:
- detected_types: [FRAMEWORK_PARALLEL, COMPONENT_A, FRAMEWORK_CORE, ...]
- risk_level: CRITICAL | HIGH | MEDIUM | LOW
- affected_files: [file1.py, file2.py, ...]
- identified_risks: [risk1, risk2, ...]
- related_frameworks: [frameworkA, frameworkB, frameworkC, ...]
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 First seen · 233 lines · 28 tokens per session scan A d0b9782dd7a5
pr-review is a skill published in the GitHub repository magic3007/dotfiles (11 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 1,651 once invoked, about $0.0001 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
merge-ready
Drive an existing pull request to a mergeable state: get CI green, resolve merge conflicts with the base branch, address and resolve review comments, trigger required bot reviews/approvals (e.g. commenting '@claude review'), link associated issues, and clean up the PR title and description. Ends with a readiness…
review-code
Standalone code review for any scope — PR number, branch, file paths, or current changes. Synthesizes intent, runs 11 parallel specialized agents, and presents actionable findings with a verdict. For PR scope, optionally posts the review to GitHub with inline comments.
review-converge
Autonomously review and fix the current branch or specified scope in iterative rounds until clean, leaving all changes in the working tree. Escalates only genuine design decisions. Ends with a transparent report of every round, every fix, and anything it couldn't resolve.
review-prs
Fetch and present a prioritized summary of all PRs awaiting the current user's review across the relevant projects and provide an interactive workflow helping the user phrase and post inline review comments and overall review decisions.
review-pr-comments-converge
Fetch PR review comments, validate each against the actual code, auto-fix obvious issues, and escalate genuine design decisions. Leaves all changes in the working tree. Use when you want to action reviewer feedback autonomously.
implement-unattended
Take a ticket whose approach and design are already approved through implementation, review and evidence to a draft PR, with nobody watching. Escalates decisions on the ticket and stops rather than choosing.