agentmods.dev

ai-multi-agent-system: Skill for Claude Code

.agents/skills/pr-review-discipline/SKILL.md

pr-review-discipline is a skill for Claude Code, Codex from radif-ru/ai-multi-agent-system. It costs 48 tokens per session (828 once invoked), scanned A, original, MIT.

A checklist and decision process for reviewing a pull request or merge request, which is a proposed code change awaiting approval.

In plain words
What is it for?
Use it to check CI, tests, code coverage, asynchronous code, error handling, security, documentation, and whether each changed line belongs to the task. It rejects a review when CI is failing.
Why use it?
It catches failed checks, missing tests, unsafe code, and unnecessary changes before code is merged into the main project.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is radif-ru/ai-multi-agent-system's own configuration. It tells Claude Code and Codex how to work on ai-multi-agent-system 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 ai-multi-agent-system configures →

not rated 6repo 1mo ago A scan 48 tokens original MIT
View source ↗ radif-ru/ai-multi-agent-system radif.ru
Reuse

Borrowing it

Nothing to install: this file belongs to radif-ru/ai-multi-agent-system. 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/radif-ru/ai-multi-agent-system/main/.agents/skills/pr-review-discipline/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/radif-ru/ai-multi-agent-system

Made for: Claude Code, Codex.

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 pr-review-discipline

README.md
[![agentmods](https://agentmods.dev/badge/skills/radif-ru/ai-multi-agent-system/pr-review-discipline/github.svg)](https://agentmods.dev/skills/radif-ru/ai-multi-agent-system/pr-review-discipline)
Your own site
<a href="https://agentmods.dev/skills/radif-ru/ai-multi-agent-system/pr-review-discipline"><img src="https://agentmods.dev/badge/skills/radif-ru/ai-multi-agent-system/pr-review-discipline/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 pr-review-discipline

Your own site · 80×15
<a href="https://agentmods.dev/skills/radif-ru/ai-multi-agent-system/pr-review-discipline"><img src="https://agentmods.dev/badge/skills/radif-ru/ai-multi-agent-system/pr-review-discipline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 828 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 $0.00048 $0.00828
Opus 5 $0.00024 $0.00414
Sonnet 5 $0.00010 $0.00166
Haiku 4.5 $0.00005 $0.00083

Measured 12d ago against content hash 0605014804db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pr-review-discipline 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 12d 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.

.agents/skills/pr-review-discipline/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: pr-review-discipline

Правила ревью pull request / merge request. Дополняет промпт .agents/prompts/code-review.prompt.md (чек-лист проверок) и добавляет процедуру исхода ревью.

Когда использовать

  • Ревьюишь PR/MR (свой или чужой).
  • Пользователь попросил проверить ветку перед merge.
  • Проводишь само-ревью перед открытием PR.

Алгоритм

  1. Проверить CI зелёный. Если хоть один гейт красный (набор — _board/process.md §7.10) — reject без детального ревью. Сначала чиним CI.
  2. Пройти чек-лист из .agents/prompts/code-review.prompt.md:
    • Хирургичность — каждая изменённая строка соответствует задаче (AGENTS.md §3).
    • Минимализм — нет лишних абстракций/фич (AGENTS.md §2).
    • Тесты на новое поведение — изменения в app/ сопровождаются тестом; моки внешних систем, без сети (_docs/instructions.md §8.1).
    • Покрытие — порог --cov-fail-under=80 не нарушен.
    • Async-дисциплина — I/O через await, синхронные либы через asyncio.to_thread (_docs/instructions.md §4).
    • Обработка ошибок — ожидаемые исключения ловятся, пользователю — человеческое сообщение, stacktrace — в logger.exception (_docs/instructions.md §5).
    • Безопасность — нет хардкоженных секретов; конфиг через Settings; sanitize на входе / bastion на выходе; per-user скоуп read_file (_docs/security.md).
    • Документация — изменение поведения отражено в _docs/; ссылки относительные (_docs/instructions.md §9).
    • Язык — комментарии/докстринги/логи/сообщения — на русском; идентификаторы — латиницей (_docs/instructions.md §1).
  3. Замечания — сгруппировать по серьёзности: blocker → major → minor → nit. Для каждого: файл, строка, проблема, конкретное предложение.
  4. Исход ревью:
    • Approve — нет blocker/major, nit можно не блокировать.
    • Approve with comments — есть minor, не блокирующие merge, но желательно поправить.
    • Request changes — есть blocker или major.
  5. Не апрувить если:
    • CI красный.
    • Нет тестов на новое поведение в app/.
    • Документация не обновлена при изменении поведения.
    • Найден хардкоженный секрет/токен.

Read the full file on GitHub · 46 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. 12d ago First seen · 46 lines · 48 tokens per session scan A 0605014804db

Subscribe to this mod's changes

pr-review-discipline is a skill published in the GitHub repository radif-ru/ai-multi-agent-system (6 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 828 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 2026-08-31.

Code reviewGit and workflowLLMMulti-Agentaiogramlocal-llmollama
Related

Other skills, from other repositories

developer_pr_prep

Prepare branches, diffs, tests, and GitHub PR text from Developer Studio.

siddsachar/row-bot · 22 tokens

review-agent

Perform a read-only, defect-first review of a specified code change and return every actionable finding. Use when another agent delegates review of uncommitted changes, a base-branch diff, a commit, or custom review instructions.

MasihMoafi/Elpis · 48 tokens

dev7-pr

Create a PR, push to GitHub, wait for Greptile review, address comments, and push final. Sub-skill of the /dev workflow.

rahulcvwebsitehosting/wayfinder · 36 tokens

dev6-review-fix

Apply fixes for review comments from dev5-review and commit. Sub-skill of the /dev workflow.

rahulcvwebsitehosting/wayfinder · 27 tokens

github

GitHub via gh CLI: PRs, issues, reviews, repos, auth.

NousResearch/hermes-agent · 19 tokens

github

GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available)…

opensquilla/opensquilla · 101 tokens