drift: Skill for Claude Code

.github/skills/drift-pr-review/SKILL.md

drift-pr-review is a skill for Claude Code from mick-gsk/drift. It costs 32 tokens per session (844 once invoked), scanned A, original, MIT.

An evidence-based pull-request review process for changes to the Drift codebase, tests, documentation, or scoring logic.

In plain words
What is it for?
Use it when reviewing pull requests that change src/drift/, tests, docs-site, signal quality, scoring, output formats, or benchmark evidence.
Why use it?
It prevents reviews from relying on informal judgment by requiring a policy check and a point-by-point checklist with a short reason for every answer.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

This is mick-gsk/drift's own configuration. It tells Claude Code how to work on drift itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything drift configures →

Part of the drift plugin — 31 skills, 17 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to mick-gsk/drift. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mick-gsk/drift/main/.github/skills/drift-pr-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mick-gsk/drift

Made for: Claude Code.

Or install drift, the plugin that ships this one along with the rest of its 31 skills, 17 agents.

Wrote 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.

agentmods badge for drift-pr-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/mick-gsk/drift/drift-pr-review/github.svg)](https://agentmods.dev/skills/mick-gsk/drift/drift-pr-review)
Your own site
<a href="https://agentmods.dev/skills/mick-gsk/drift/drift-pr-review"><img src="https://agentmods.dev/badge/skills/mick-gsk/drift/drift-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.

agentmods 80×15 button for drift-pr-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/mick-gsk/drift/drift-pr-review"><img src="https://agentmods.dev/badge/skills/mick-gsk/drift/drift-pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 844 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.00844
Opus 5 $0.00016 $0.00422
Sonnet 5 $0.00006 $0.00169
Haiku 4.5 $0.00003 $0.00084

Measured 10d ago against content hash 04f244806fc1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

drift-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 10d 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.

.github/skills/drift-pr-review/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drift PR Review Skill

Purpose

Guide Copilot agents through a policy-conformant, evidence-based pull request review for the drift repository.

When to Use

  • Reviewing PRs that change src/drift/, tests/, or docs-site/
  • Evaluating signal quality, scoring changes, or output format changes
  • Checking benchmark evidence for new features

Strukturierte Review-Checkliste

Pflicht-Referenz: Die vollständige Review-Checkliste liegt unter .github/prompts/_partials/review-checkliste.md. Bei jedem adversarialen Review wird diese Checkliste Punkt für Punkt abgearbeitet. Der Reviewer dokumentiert pro Punkt Ja / Nein / N/A mit Kurzbegründung.

Review Workflow

Step 1: Policy Gate

Before reviewing code, verify the PR passes the Policy Gate:

### Drift Policy Gate
- Aufgabe: [PR title / description]
- Zulassungskriterium erfüllt: [JA / NEIN] → [which criterion]
- Ausschlusskriterium ausgelöst: [JA / NEIN] → [if YES: which]
- Roadmap-Phase: [1 / 2 / 3 / 4] — blockiert durch höhere Phase: [JA / NEIN]
- Entscheidung: [ZULÄSSIG / ABBRUCH]
- Begründung: [one sentence]

If the gate fails, comment with the reason and suggest what should be prioritized instead.

Step 2: Signal Quality Checklist

For every new or modified finding/signal, verify all 5 mandatory elements:

  • Technical traceability — finding points to specific code location
  • Reproducibility — finding can be reproduced from the same input
  • Unique cause attribution — finding maps to exactly one root cause
  • Clear justification — rationale is documented and understandable
  • Actionable next step — a concrete remediation or investigation step exists

A finding missing any element is non-compliant with Policy §13.

Step 3: Benchmark Evidence

For feature PRs (feat: commits), verify:

  • benchmark_results/v*_feature_evidence.json artifact exists
  • Self-analysis score is equal or better than baseline
  • No regression in precision/recall on known test repos

Read the full file on GitHub · 103 lines

Changes

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.

  1. 10d ago First seen · 103 lines · 32 tokens per session scan A 04f244806fc1

Subscribe to this mod's changes

drift-pr-review is a skill published in the GitHub repository mick-gsk/drift (15 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 844 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

argot-setup

Set argot up for a repository end to end — audit its history, decide what should shape its voice, fit, verify the fit actually catches things, tune the rules its own history says are noisy, and wire the places it runs (pre-write hook, pre-commit, MCP, CI). One sitting, one decision at a time, each proposed with the…

get-tmonier/argot · 129 tokens

pull-request-automation

Audits and improves the pull request workflow for a GitHub repository. Covers PR description templates, auto-labelling, CODEOWNERS, PR size checks, and branch protection rules. Invoked when the user asks to improve the PR process, set up PR automation, or add a PR template.

soulcodex/agentic · 65 tokens

umbra-trust-review

Verify AI-generated code before shipping. Run Umbra's Trust Score scan before committing or finishing any coding task, treat findings as blocking issues, and re-scan until clean. Use when finishing a task, before a commit, or when reviewing code written by an agent.

elberacasa/umbra · 60 tokens

ai-debt-audit

Scan a repository for AI-generated technical, cognitive, and intent debt. Use when the user asks to audit a codebase for AI/vibe-coding risk, check for issues an AI coding assistant may have introduced (disabled RLS, hardcoded secrets, missing auth checks, SSTI, debug mode left on), assess technical debt after heavy…

aniruddhavasudev/ai-debt-audit · 108 tokens

gh-find-prs

Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.

Hmbown/CodeWhale · 27 tokens

hunk-release

Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.

modem-dev/hunk · 38 tokens