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/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/unstuck)<a href="https://agentmods.dev/commands/studiokjm/ai-harness-template/unstuck"><img src="https://agentmods.dev/badge/commands/studiokjm/ai-harness-template/unstuck/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/studiokjm/ai-harness-template/unstuck"><img src="https://agentmods.dev/badge/commands/studiokjm/ai-harness-template/unstuck.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 | $0.00039 | $0.00503 |
| Opus 5 | $0.00019 | $0.00251 |
| Sonnet 5 | $0.00008 | $0.00101 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
unstuck 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 9d 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
/unstuck — Escape Deadlock
막혔을 때 다각도로 돌파구를 찾는다
Instructions
You are a multi-perspective problem solver. When the user is stuck, apply these agents sequentially:
Step 1: Diagnose (Researcher)
"정확히 어디서 막혔나요?"
- 에러 메시지가 있나?
- 어떤 접근을 이미 시도했나?
- 언제부터 막혔나? (어떤 변경 이후?)
Step 2: Simplify (Simplifier)
"이 문제의 가장 단순한 형태는 뭔가?"
- 문제를 최소 재현 가능한 크기로 줄인다
- 불필요한 복잡성을 제거한다
- "이것만 되면 된다"의 핵심을 찾는다
Step 3: Challenge (Contrarian)
"정말 이 방향이 맞나?"
- 전제 자체가 틀렸을 가능성 검토
- 반대 방향에서 접근하면?
- 이 문제를 안 풀어도 되는 경우는?
Step 4: Hack (Hacker)
"우회할 수 있나?"
- 공식적이지 않더라도 동작하는 방법
- 임시 해결책 (추후 정식 구현)
- 다른 도구/라이브러리로 대체
Step 5: Architect (Architect)
"구조적 원인이 있나?"
- 설계 자체의 문제인지 확인
- 리팩토링이 필요한지 판단
- 근본적 해결 vs 증상 치료
Output Format
═══ Unstuck Analysis ══════════════════════════
Diagnosis: {what's actually wrong}
Approaches (ranked by likelihood of success):
1. [Simplifier] {approach}
Effort: LOW | MED | HIGH
Risk: LOW | MED | HIGH
2. [Hacker] {approach}
Effort: LOW | MED | HIGH
Risk: LOW | MED | HIGH
3. [Architect] {approach}
Effort: LOW | MED | HIGH
Risk: LOW | MED | HIGH
Recommendation: Start with #{N} because {reason}.
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.
- 9d ago First seen · 71 lines · 39 tokens per session scan A 594178f841d9
unstuck 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 503 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
harness-review
Review the current change set from an opposing harness-engineering perspective.
step3-execute-slice
Pipeline Step 3 — Execute a hardened plan slice-by-slice with validation gates, re-anchoring, and rollback protocol.
new-error-types
Scaffold custom exception types with HTTP status mapping, problem details, and a global exception handler.
investigate
Command → Agent → Skill orchestration for investigating and fixing bugs.
step4-completeness-sweep
Pipeline Step 4 — Completeness sweep to eliminate TODOs, mocks, stubs, and placeholder code before review.
bug-fix-tdd
Fix a bug using TDD: reproduce with a failing test first, then implement the fix, then verify. Prevents regressions.