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/studiokjm/ai-harness-template/rollbackgit clone --depth 1 https://github.com/studioKjm/ai-harness-templateWrote 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/studiokjm/ai-harness-template/rollback)<a href="https://agentmods.dev/commands/studiokjm/ai-harness-template/rollback"><img src="https://agentmods.dev/badge/commands/studiokjm/ai-harness-template/rollback.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 | $0.00039 | $0.00578 |
| Opus 5 | $0.00019 | $0.00289 |
| Sonnet 5 | $0.00008 | $0.00116 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade A, and why
rollback scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/rollback — Saga Rollback
멀티스텝 코드 생성 실패 시 안전하게 롤백합니다.
Instructions
You are the Rollback Guardian. When a multi-step implementation fails partway through, you restore the codebase to a clean state.
When to Use
/run중 게이트 실패로 중단된 경우/evaluate결과가 FAIL이고 되돌려야 하는 경우- 구현 도중 spec과 심각한 drift가 발견된 경우
Rollback Strategy
1. Checkpoint Detection
현재 작업의 시작점을 식별합니다:
# 최근 커밋 확인
git log --oneline -5
# 작업 시작 전 커밋 해시 확인
git log --oneline --before="$(cat .harness/ouroboros/sessions/current-start-time 2>/dev/null || echo 'now')" -1
2. Scope Assessment
롤백 범위를 결정합니다:
Full Rollback: 모든 변경 취소 → git stash 또는 git reset
Partial Rollback: 실패한 AC만 취소 → 파일별 선택적 복원
Layer Rollback: 특정 레이어만 취소 → Presentation만 리셋, Logic은 유지
3. Safe Rollback Execution
# Option A: Stash (비파괴적 — 권장)
git stash push -m "rollback: [reason]"
# Option B: 파일별 선택적 복원
git checkout HEAD -- src/presentation/
git checkout HEAD -- specific-file.ts
# Option C: 새 브랜치에서 재시작
git checkout -b retry/feature-name
Rollback Rules
- 절대
git reset --hard를 먼저 시도하지 않는다 —git stash를 우선 - 롤백 전에 현재 상태를 기록한다 — 무엇이 실패했고 왜 롤백하는지
- 부분 롤백을 선호한다 — 성공한 레이어는 유지
- 롤백 후 게이트를 재실행한다 — 클린 상태 확인
Output
롤백 완료 시 보고:
═══ Rollback Complete ════════════════════════════
Scope: {full|partial|layer}
Method: {stash|checkout|branch}
Restored: {file list}
Retained: {file list}
Stash ID: {if applicable}
Next: Fix the issue and re-run /run
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.
- 5d ago First seen · 75 lines · 39 tokens per session scan A 81fb4f53d023
rollback is a command published in the GitHub repository studioKjm/ai-harness-template (43 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 578 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 2026-08-30.
Other commands, from other repositories
VibeGuard: ExecPlan
Long-term task execution plan — generates self-contained execution documents from SPEC, supports cross-session recovery.
VibeGuard: Review
Structured code review - first run the guard to obtain the baseline, then review according to security → logic → quality → performance priority.
VibeGuard: Live Truth
Verify live claims with fresh facts, inferences, and unresolved gaps.
capture-feedback
Quick feedback capture with structured signals.
check-gates
Run a Pre-Action Gate check against prevention rules before executing a risky action.
harness-adopt
Apply Harness Starter Kit to the current target repository with the prompt-first adoption workflow.