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.
curl -O https://raw.githubusercontent.com/radif-ru/ai-multi-agent-system/main/.agents/skills/pull-request-discipline/SKILL.mdgit clone --depth 1 https://github.com/radif-ru/ai-multi-agent-systemWrote 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/radif-ru/ai-multi-agent-system/pull-request-discipline)<a href="https://agentmods.dev/skills/radif-ru/ai-multi-agent-system/pull-request-discipline"><img src="https://agentmods.dev/badge/skills/radif-ru/ai-multi-agent-system/pull-request-discipline.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00044 | $0.00649 |
| Opus 5 | $0.00022 | $0.00324 |
| Sonnet 5 | $0.00009 | $0.00130 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
pull-request-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 8d 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.
What it actually says
Skill: pull-request-discipline
Правила подготовки PR/MR. Источник истины — _board/process.md §7, §9 и _docs/instructions.md §2.
Когда использовать
- Готовишь pull request (GitHub) или merge request (GitLab).
- Пользователь попросил создать PR/MR.
- Проверяешь готовность ветки к merge.
Алгоритм
- Ветка. Одна
feature/<NN>-<short-name>на спринт, отmain. Не смешивать задачи разных спринтов в одной ветке. - Коммиты — атомарные, по Conventional Commits на русском (см.
git-discipline). Ритуал задачи:python3 -m scripts.task start <NN>.<stage>.<task>→ код/доки →python3 -m scripts.task done <NN>.<stage>.<task> --note "...". - Перед открытием PR — зелёный
bash .agents/skills/git-discipline/scripts/preflight.sh(весь набор гейтов —_board/process.md§7.10; тот же набор прогоняет CI). - Тело PR/MR:
- Summary — что сделано и зачем, 2–5 строк. Ссылка на спринт (
_board/sprints/<NN>-*.md). - Test plan — как проверялось:
pytest -q, smoke-test, конкретные тесты на новое поведение. - DoD — отметить выполненные пункты из файла спринта.
- Summary — что сделано и зачем, 2–5 строк. Ссылка на спринт (
- Скоуп PR — один спринт. Не добавлять задачи следующих спринтов (см.
process.md§9 п.6). - Merge / push в
main— только пользователь по явному запросу (см.process.md§2 п.8 и §9). Агент никогда не делает merge/push самостоятельно. - GitHub vs GitLab:
- GitHub:
gh pr create --base main --head feature/<NN>-.... - GitLab:
glab mr create --target-branch main --source-branch feature/<NN>-.... - Если CLI нет — дать готовый заголовок и тело для веб-интерфейса.
- GitHub:
Чего избегать
- Открытия PR при красных
pytest/flake8/покрытии. - Смешивания задач разных спринтов в одном PR.
- Самостоятельного merge/push в
main— это делает только пользователь. - PR без Test plan — reviewer не знает, как проверять.
- Больших PR (>300 строк diff) без разбиения на ревьюемые части.
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.
- 8d ago First seen · 39 lines · 44 tokens per session scan A d0a0cdca278d
pull-request-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 44 tokens to every session and 649 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.
Other skills, from other repositories
dev6-review-fix
Apply fixes for review comments from dev5-review and commit. Sub-skill of the /dev workflow.
lean-review
CocoLean diff-scoped over-engineering audit — scans uncommitted git diff and applies five classification tags (delete/stdlib/native/yagni/shrink) to identify unnecessary surface area before commit.
developer_pr_prep
Prepare branches, diffs, tests, and GitHub PR text from Developer Studio.
flag-cleanup
Weekly reusable-session feature-flag cleanup for {{targetrepo}}. Inventories every feature flag, classifies each as fully rolled out, long dead, partial rollout, or active experiment, removes the flag and the dead branch it guards on an isolated branch when the suite is green, and opens a PR — never touching a flag…
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.
git
Run git version control commands for repository management. Use when the user asks to check status, view history or diffs, stage and commit changes, manage branches, merge or rebase, work with remotes, stash changes, tag releases, cherry-pick commits, bisect regressions, resolve conflicts, manage worktrees or…