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 commands/sangrokjung/claude-forge/checkpointgit 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/checkpoint)<a href="https://agentmods.dev/commands/sangrokjung/claude-forge/checkpoint"><img src="https://agentmods.dev/badge/commands/sangrokjung/claude-forge/checkpoint.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 | $0.00011 | $0.01491 |
| Opus 5 | $0.00005 | $0.00745 |
| Sonnet 5 | $0.00002 | $0.00298 |
| Haiku 4.5 | $0.00001 | $0.00149 |
Grade C, and why
checkpoint scanned grade C with 1 finding 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 6d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .claude/checkpoints/{name} How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/checkpoint - 작업 상태 저장/복원 (v6)
0단계: 파라미터 파싱
| 서브커맨드 | 설명 | 필수 인자 |
|---|---|---|
save |
현재 상태 저장 | "이름" |
restore |
저장된 상태 복원 | "이름" |
list |
저장된 체크포인트 목록 | 없음 |
diff |
체크포인트 간 차이 비교 | "이름" |
delete |
체크포인트 삭제 | "이름" |
옵션:
--tag 태그: 체크포인트에 태그 부착 (예:--tag stable,--tag pre-refactor)
1단계: 저장소 경로
체크포인트 저장 위치:
.claude/checkpoints/
{name}/
metadata.json
staged.patch # staged 변경사항
unstaged.patch # unstaged 변경사항
untracked/ # untracked 파일 복사본
저장소 디렉토리가 없으면 생성한다:
mkdir -p .claude/checkpoints
2단계: save 서브커맨드
2-1. 현재 상태 수집
# 현재 브랜치
git branch --show-current
# 현재 커밋
git rev-parse --short HEAD
# staged 변경사항
git diff --cached > .claude/checkpoints/{name}/staged.patch
# unstaged 변경사항
git diff > .claude/checkpoints/{name}/unstaged.patch
# 변경 통계
git diff --stat HEAD
# untracked 파일 목록
git ls-files --others --exclude-standard
2-2. untracked 파일 복사
untracked 파일이 있으면 복사본을 저장한다:
mkdir -p .claude/checkpoints/{name}/untracked
# 각 untracked 파일을 디렉토리 구조 유지하며 복사
2-3. 메타데이터 생성
{
"name": "기능완료",
"timestamp": "2026-02-07T15:30:00Z",
"branch": "feature/auth",
"commit": "abc1234",
"files": [
"src/auth/login.ts",
"src/auth/register.ts"
],
"stats": {
"additions": 45,
"deletions": 12,
"files_changed": 3,
"untracked_count": 1
},
"tags": ["stable"],
"auto": false,
"v6_metadata": {
"security_status": "pass"
}
}
v6_metadata 필드 설명:
security_status: 마지막 보안 검사 결과 (pass/fail/unknown)
2-4. 자동 체크포인트
다음 상황에서 자동으로 체크포인트를 생성한다:
/commit-push-pr실행 전/handoff-verify검증 3회 실패 시
자동 체크포인트의 auto 필드는 true로 설정한다.
이름 형식: auto-{YYYYMMDD-HHmmss}
3단계: restore 서브커맨드
3-1. 체크포인트 존재 확인
ls .claude/checkpoints/{name}/metadata.json
3-2. 현재 상태 백업
복원 전 현재 상태를 pre-restore-{timestamp} 이름으로 자동 저장한다.
3-3. 복원 실행
# staged 변경사항 복원
git apply .claude/checkpoints/{name}/staged.patch
git add -A
# unstaged 변경사항 복원
git apply .claude/checkpoints/{name}/unstaged.patch
# untracked 파일 복원
cp -r .claude/checkpoints/{name}/untracked/* ./ 2>/dev/null
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.
- 6d ago First seen · 238 lines · 11 tokens per session scan C ac71c6bec2cd
checkpoint is a command published in the GitHub repository sangrokjung/claude-forge (825 stars, last pushed 2d ago), licensed MIT. It adds 11 tokens to every session and 1,491 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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
Slash commands for SPEC-First development workflow.
review
Review plans with multi-angle analysis (mandatory + extended + autonomous).
review
Perform a thorough code review of changes in this branch.
01_confirm
Extract plan from conversation, create file in draft/, auto-apply non-BLOCKING improvements, move to pending.
05_cleanup
Safe dead code cleanup - detect and remove unused imports and dead files with auto-apply for Low/Medium risk.
add-tool
Scaffold and implement a new tool for VisionAgent.