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.
git clone --depth 1 https://github.com/sangrokjung/claude-forgeWrote 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/commands/sangrokjung/claude-forge/commit-push-pr)<a href="https://agentmods.dev/commands/sangrokjung/claude-forge/commit-push-pr"><img src="https://agentmods.dev/badge/commands/sangrokjung/claude-forge/commit-push-pr/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/commands/sangrokjung/claude-forge/commit-push-pr"><img src="https://agentmods.dev/badge/commands/sangrokjung/claude-forge/commit-push-pr.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00036 | $0.06823 |
| Opus 5.5 | $0.00014 | $0.02729 |
| Sonnet 5.5 | $0.00007 | $0.01365 |
| Haiku 4.5 | $0.00004 | $0.00682 |
Grade A, and why
commit-push-pr 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 — 836 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task
0단계: Context 수집
git status --short
git branch --show-current
git rev-parse --abbrev-ref origin/HEAD 2>/dev/null | sed 's/origin\///' || echo "main"
git log --oneline -3
git diff --staged --stat 2>/dev/null || git diff --stat
git remote get-url origin 2>/dev/null
gh --version 2>/dev/null | head -1 || echo "not installed"
1단계: 인자 파싱
$ARGUMENTS에서 옵션 추출:
--merge→ 머지 모드: merge commit--squash→ 머지 모드: squash merge--rebase→ 머지 모드: rebase merge--draft→ Draft PR (머지 옵션과 함께 사용 불가)--no-verify→ 빌드/테스트 스킵--no-checklist→ 머지 후 웹 체크리스트 생성 스킵--skip-security→ 보안 사전 검증 스킵--skip-sync-docs→ 문서 동기화 게이트 스킵 (긴급 hotfix 전용, v7 신규 — 머지 모드에서는 경고 출력)--notify→ 머지 후 MCP 알림 발송 (v6 신규)- 나머지 → 커밋 메시지
--draft와 머지 옵션 동시 사용 시:
--draft와 머지 옵션(--merge/--squash/--rebase)은 함께 사용할 수 없습니다.
Draft PR은 머지하지 않고 리뷰용으로 생성됩니다.
→ 중단
2단계: 사전 체크
변경사항 없으면:
커밋할 변경사항이 없습니다.
현재 상태:
- 브랜치: [브랜치명]
- 마지막 커밋: [커밋 메시지]
→ 중단
main/master 브랜치면:
main 브랜치에서 직접 커밋하려고 합니다.
권장: 브랜치 생성 후 작업
git checkout -b feature/[기능명]
옵션:
1. "브랜치 생성" - 새 브랜치 만들고 진행
2. "계속" - main에 직접 커밋 (PR 생략)
3. "취소" - 작업 중단
3단계: 빌드/테스트 검증
--no-verify 있으면 스킵.
프로젝트 타입별 검증:
| 파일 | 타입 | 검증 명령 |
|---|---|---|
| package.json | Node.js | npm run build && npm test |
| pyproject.toml / setup.py | Python | python -m pytest |
| go.mod | Go | go build ./... && go test ./... |
| Cargo.toml | Rust | cargo build && cargo test |
| Makefile | Make | make test |
실패 시:
검증 실패
[에러 메시지]
해결 후 다시 시도하거나:
/commit-push-pr --no-verify
→ 중단
3.5단계: Merge Gate (자동 품질 관문)
커밋 전 아래 4개 조건을 AND로 검증한다. 하나라도 FAIL이면 커밋을 중단한다.
| 검증 항목 | 명령어 | FAIL 조건 | --no-verify 시 |
|---|---|---|---|
| 빌드 | npm run build |
exit code ≠ 0 | 스킵 가능 |
| 테스트 | npm test |
exit code ≠ 0 | 스킵 가능 |
| 린트 | npm run lint |
exit code ≠ 0 | 스킵 가능 |
| 보안 스캔 | security-reviewer agent | CRITICAL 발견 | 스킵 불가 |
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 · 836 lines · 36 tokens per session scan A e281dbe91439
commit-push-pr is a command published in the GitHub repository sangrokjung/claude-forge (856 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 6,823 once invoked, about $0.0001 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 commands, from other repositories
plan-execute
Execute a validated plan: worktree isolation, TDD scaffolding, level-based parallel agents, quality gate with smoke test, PR creation and merge. Handles everything through to merged PR.
catchup
Restore context after /clear by summarizing recent work and project state.
commit
Generate a conventional commit message for staged changes.
refactor-check.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
repo-guard.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
ship-csk
DoD gate + commit proposal (waits for approval).