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/rtk-ai/rtk/pr-reviewnpx skills add rtk-ai/rtk --skill pr-reviewgit clone --depth 1 https://github.com/rtk-ai/rtkWhat 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 | $0.00128 | $0.02096 |
| Opus 5 | $0.00064 | $0.01048 |
| Sonnet 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 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 — 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.
- 2d 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 (78,131 stars, last pushed today), licensed Apache-2.0. It adds 128 tokens to every session and 2,096 once invoked, about $0.0006 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.
Other skills, from other repositories
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
orchestrator-lanes
Claude Code dev-orchestrator only. File-based multi-lane PM playbook (score, DAG, run-controller, L0/L1/L2, ship). Use when this session IS that agent, or user says info / справка / lane-stack:orchestrator-lanes info. SKIP: Grok, Codex, Kimi, Qwen, AGY, Cursor writer CLIs and any default coding agent — do not load, do…
source-command-methodology-advisor
Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack.
info
Lane-stack work-process cheat sheet. Catalog of resume, onboard, architect a new app, design, docs. Use when user says info, справка, lane-stack:info, /lane-stack:info, что умеет стек, как запускать.
lane-memory
SMA-style project fact corpus under .agents/memory/. Opt-in via adoc stages.memory.enabled. Use when user says память, lane-memory, corpus, CORE, почему бот забыл, or an agent needs durable non-code facts. Not PROGRESS/LESSONS dumps.
source-command-ccguide-daily
Daily update check — official Anthropic docs diff + guide/CC releases digest.