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/suggest-automation)<a href="https://agentmods.dev/commands/sangrokjung/claude-forge/suggest-automation"><img src="https://agentmods.dev/badge/commands/sangrokjung/claude-forge/suggest-automation/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/suggest-automation"><img src="https://agentmods.dev/badge/commands/sangrokjung/claude-forge/suggest-automation.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 | $0.00020 | $0.01097 |
| Opus 5 | $0.00010 | $0.00549 |
| Sonnet 5 | $0.00004 | $0.00219 |
| Haiku 4.5 | $0.00002 | $0.00110 |
Grade A, and why
suggest-automation 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 11d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task
0단계: 분석 범위 결정
- $ARGUMENTS 숫자 있으면 → 해당 커밋 수
- 없으면 → 기본 50개 커밋
1단계: 데이터 수집
커밋 패턴 수집
git log --oneline -[N]
git log --name-status -[N] --pretty=format:"%s"
기존 자동화 확인
Read 도구로 다음 디렉토리 확인:
.claude/commands/- 기존 command 목록.claude/agents/- 기존 agent 목록.claude/skills/- 기존 skill 목록 (있으면)
CLAUDE.md 분석
- Read 도구로 CLAUDE.md 읽기
- 반복되는 규칙 패턴 확인
- 자주 언급되는 작업 유형 파악
2단계: 패턴 분석
커밋 메시지 패턴
- 같은 prefix 빈도 분석 (fix:, feat:, docs:, test: 등)
- 같은 키워드 반복 횟수 (API, migration, test, config 등)
- 유사한 작업 패턴 그룹화
파일 변경 패턴
- 자주 생성되는 파일 유형 (*.test.ts, *.spec.ts 등)
- 자주 수정되는 디렉토리
- 함께 변경되는 파일 그룹
CLAUDE.md 패턴
- 비슷한 규칙 그룹
- 반복 추가되는 규칙 유형
3단계: 제안 생성
패턴 → 제안 매핑:
| 발견 패턴 | 제안 유형 | 예시 |
|---|---|---|
| 테스트 파일 자주 생성 | command | /generate-test |
| 특정 구조 파일 반복 생성 | skill | api-generator |
| 복잡한 작업 반복 위임 | agent | migration-helper |
| 같은 git 명령 조합 반복 | command | /quick-deploy |
| 보일러플레이트 반복 | skill | component-template |
제안 조건:
- 최소 3회 이상 반복된 패턴만 제안
- 이미 존재하는 자동화와 중복 제외
4단계: 결과 출력
🔍 자동화 기회 분석 (최근 [N]개 커밋)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
## 발견된 패턴
### 1. [패턴 이름] ([반복 횟수]회)
- 패턴: [구체적 패턴 설명]
- 제안: [command/skill/agent 이름]
- 효과: [자동화 시 이점]
### 2. [패턴 이름] ([반복 횟수]회)
- 패턴: [구체적 패턴 설명]
- 제안: [command/skill/agent 이름]
- 효과: [자동화 시 이점]
[추가 패턴...]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
## 이미 있는 자동화
- /[command1] ✓
- /[command2] ✓
- [agent1] ✓
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
## 권장 액션
1. [높음] [제안 내용]
2. [중간] [제안 내용]
3. [낮음] [제안 내용]
생성할 번호를 입력하세요 (또는 'skip'):
5단계: 선택적 생성
사용자가 번호 선택하면:
- 해당 유형(command/skill/agent) 템플릿 생성
- 적절한 디렉토리에 파일 생성
- 기본 구조 채워넣기
생성 예시 (command):
# 생성: .claude/commands/[이름].md
---
allowed-tools: [필요한 도구]
description: [자동 생성된 설명]
argument-hint: "[인자 힌트]"
---
## Task
[기본 템플릿 - 사용자가 수정 필요]
### 0단계: 환경 확인
[프로젝트 상태 확인]
### 1단계: 실행
[핵심 작업]
### 완료 안내
[결과 출력]
생성 완료 안내:
✅ 자동화 생성 완료
생성된 파일:
- .claude/commands/[이름].md
다음 단계:
1. 파일 내용 확인 및 수정
2. 테스트 실행: /[이름]
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.
- 11d ago First seen · 161 lines · 20 tokens per session scan A 4aa9b98733b8
suggest-automation is a command published in the GitHub repository sangrokjung/claude-forge (835 stars, last pushed 7d ago), licensed MIT. It adds 20 tokens to every session and 1,097 once invoked, about $0.0001 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 commands, from other repositories
context-stats
Display context window usage and token statistics.
run
Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.
help
Explain Ralph Wiggum technique and available commands.
cancel-ralph
Cancel active Ralph Wiggum loop.
catchup
Restore context after /clear by summarizing recent work and project state.
sessions
Browse Claude Code sessions history.