rtk is a command-line proxy that filters and compresses output from development commands before it reaches an LLM's context. It is used with coding agents to reduce the tokens consumed by commands such as Git operations. The catalogue includes skills, commands, agents, and instructions for using rtk in agent workflows.
Borrowing it
Nothing to install: this file belongs to rtk-ai/rtk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rtk-ai/rtk/develop/.claude/skills/pr-review/SKILL.mdgit clone --depth 1 https://github.com/rtk-ai/rtkWrote 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/rtk-ai/rtk/pr-review)<a href="https://agentmods.dev/skills/rtk-ai/rtk/pr-review"><img src="https://agentmods.dev/badge/skills/rtk-ai/rtk/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/rtk-ai/rtk/pr-review"><img src="https://agentmods.dev/badge/skills/rtk-ai/rtk/pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk warn
- 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 | $0.00128 | $0.02096 |
| Opus 5.5 | $0.00051 | $0.00838 |
| Sonnet 5.5 | $0.00026 | $0.00419 |
| Haiku 4.5 | $0.00013 | $0.00210 |
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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pr-review
Batch review des PRs RTK — du plus simple au plus complexe, une par une, avec validation utilisateur avant chaque merge.
Quand utiliser
- Après un
/rtk-triagepour agir sur les résultats - Régulièrement pour dégraisser le backlog
- Avant une release pour vider la file quick wins
Workflow
Phase 0 — Préconditions
git rev-parse --is-inside-work-tree
gh auth status
date +%Y-%m-%d
Si l'argument triage est passé, exécuter /rtk-triage d'abord et utiliser sa liste de quick wins comme séquence. Sinon, construire la liste soi-même.
Phase 1 — Construire la liste de PRs (si pas de triage)
gh pr list --state open --limit 200 \
--json number,title,author,additions,deletions,changedFiles,mergeable,mergeStateStatus,isDraft,statusCheckRollup,reviewDecision,body \
| jq 'sort_by(.additions + .deletions)'
Classement par taille :
| Taille | Critère | Traitement |
|---|---|---|
| XS | < 30 lignes, 1 fichier | En premier |
| S | 30-100 lignes, 1-3 fichiers | Ensuite |
| M | 100-200 lignes, logique non triviale | Après |
| L | > 200 lignes | Dernier ou skip |
| XL | > 500 lignes | Skip (session dédiée) |
Filtrer d'emblée :
- Exclure les PRs draft
- Exclure les PRs de nous (les nôtres ont une review flow différente)
- Si
from:<num>passé en argument : commencer à ce numéro
Phase 2 — Pour chaque PR (une par une, dans l'ordre)
Étape A — Vérification état (AVANT de lire le diff)
# 1. Etat mergeable + CLA
gh pr view <num> --json mergeable,mergeStateStatus,statusCheckRollup,reviewDecision
# 2. Reviews existantes (CHANGES_REQUESTED ?)
gh api repos/rtk-ai/rtk/pulls/<num>/reviews \
--jq '.[] | {author: .user.login, state: .state, body: .body}'
# 3. Commentaires inline (si CHANGES_REQUESTED)
gh api repos/rtk-ai/rtk/pulls/<num>/comments \
--jq '.[] | {author: .user.login, body: .body, path: .path, line: .line}'
Décision rapide selon état :
| État | Action |
|---|---|
| MERGEABLE + CLA ok + pas de CHANGES_REQUESTED | → lire le diff |
| CONFLICTING | → préparer commentaire rebase, skip diff |
| CLA non signé | → préparer commentaire CLA, skip diff |
| CHANGES_REQUESTED par un maintainer | → skip (ne pas override), noter |
| Draft | → skip silencieusement |
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 · 228 lines · 128 tokens per session scan A e374d12b9339
pr-review is a skill published in the GitHub repository rtk-ai/rtk (84,655 stars, last pushed yesterday), licensed Apache-2.0. It adds 128 tokens to every session and 2,096 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
eval-skills
Audit a project or library of skills for metadata, trigger boundaries, workflow completion criteria, local resource closure, instruction economy, tool scope, effort, and routing evidence. Use before shipping skills, after importing a skill collection, or when a skill triggers too often or not at all.
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.
design-patterns
Detect, suggest, and evaluate GoF design patterns in TypeScript/JavaScript codebases. Use when refactoring code, applying singleton/factory/observer/strategy patterns, reviewing pattern quality, or finding stack-native alternatives for React, Angular, NestJS, and Vue.
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
eval-rules
Audit Claude Code instruction rules in .claude/rules/ and /.claude/rules/: frontmatter, paths glob validity against real files, symlink load status, and day-to-day usefulness, then update rules with the user. Use for first-time rules setup, rules that apply too often or never, or periodic rules hygiene. Not for Codex…
review-pr
Perform a comprehensive code review of a pull request.