drift: Skill for Claude Code

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

drift-pr-review-loop is a skill for Claude Code from mick-gsk/drift. It costs 0 tokens per session (773 once invoked), scanned A, original, MIT.

A written procedure for running drift pr-loop, a command that repeatedly asks configured reviewers to check a GitHub pull request and applies fixes until the review process ends. A pull request is a proposed code change awaiting review.

In plain words
What is it for?
Use it to run an automated review cycle on a pull request, inspect its result in rich or JSON output, or test the process with --dry-run before it changes GitHub.
Why use it?
It removes the need to repeat review, fix, push, and check steps by hand. It also explains the command’s status codes, dry runs, time limits, and escalation cases.

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-loop/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-loop

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/mick-gsk/drift/drift-pr-review-loop"><img src="https://agentmods.dev/badge/skills/mick-gsk/drift/drift-pr-review-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 773 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 $0.00000 $0.00773
Opus 5 $0.00000 $0.00387
Sonnet 5 $0.00000 $0.00155
Haiku 4.5 $0.00000 $0.00077

Measured 9d ago against content hash 2d26d26edfc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

drift-pr-review-loop 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 9d 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-loop/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: drift-pr-review-loop

Description

Drives a GitHub PR through an automated agent review loop using drift pr-loop. Covers preconditions, command usage, exit code interpretation, escalation handling, and dry-run workflows.

Trigger words: pr-loop, review loop, agent review, automated review, PR review loop


Preconditions

Before running drift pr-loop, verify:

  1. gh CLI authenticated: gh auth status must succeed. If not, run gh auth login.
  2. drift.yaml has pr_loop section: Minimum required config:
    pr_loop:
      reviewers:
        - github-copilot[bot]
      max_rounds: 5
      poll_interval_seconds: 60
      poll_timeout_seconds: 600
    
  3. On a feature branch: The command pushes fix commits; ensure you are not on main/master.

Step 1: Run the loop

drift pr-loop <PR_NUMBER> [OPTIONS]

Options:

Option Default Purpose
--repo owner/repo auto-detected Override GitHub repo
--config PATH drift.yaml Config file path
--format rich|json rich Output format
--dry-run false No GitHub side-effects
--exit-zero false Always exit 0

Example:

drift pr-loop 42 --dry-run   # Verify without side-effects
drift pr-loop 42              # Full run
drift pr-loop 42 --format json | jq .status  # Machine-readable

Step 2: Exit Code Interpretation

Exit Code Meaning Agent Action
0 APPROVED — all reviewers approved Proceed to merge or close loop
1 ESCALATED — max rounds reached or unresolved conflict Notify maintainer, do not merge
2 ERROR — loop failed unexpectedly Check logs, fix root cause, re-run
3 Precondition failed Run gh auth login or add pr_loop: to drift.yaml

Step 3: Escalation Handling

When exit code is 1 (ESCALATED):

  • A PR comment has been posted listing all unresolved comments/verdicts
  • The state file is saved to work_artifacts/pr-loop-<PR_NUMBER>.json
  • Do not force-merge — notify the human maintainer
  • Inspect the JSON state for escalation_reason:
    cat work_artifacts/pr-loop-42.json | jq .escalation_reason
    

Read the full file on GitHub · 98 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. 9d ago First seen · 98 lines · 0 tokens per session scan A 2d26d26edfc2

Subscribe to this mod's changes

drift-pr-review-loop is a skill published in the GitHub repository mick-gsk/drift (15 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 773 tokens. 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