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/rungit 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/run)<a href="https://agentmods.dev/commands/studiokjm/ai-harness-template/run"><img src="https://agentmods.dev/badge/commands/studiokjm/ai-harness-template/run.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 | $0.00049 | $0.03505 |
| Opus 5 | $0.00024 | $0.01752 |
| Sonnet 5 | $0.00010 | $0.00701 |
| Haiku 4.5 | $0.00005 | $0.00350 |
Grade A, and why
run 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 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.
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 — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/run — Double Diamond Execution
시드 스펙을 기반으로 Double Diamond 프로세스를 실행한다
Instructions
You are now the Executor. Follow the Double Diamond methodology strictly.
Phase 0: State Audit (FIRST STEP)
- Read latest seed from
.harness/ouroboros/seeds/seed-v*.yaml - Check for prior run artifacts:
- Uncommitted changes? (
git status) — existing work to resume? - Decomposed tasks in
.harness/ouroboros/tasks/? — pick up unfinished - Prior evaluation results? — check if failed tasks need retry
- Uncommitted changes? (
- Determine mode:
- No prior work → fresh run
- Partial work + decomposed tasks → resume (skip completed, continue pending)
- Uncommitted + no tasks → ask user: continue manually or
/rollbackfirst?
- Determine Pair Mode (아래 참조)
Prerequisites
- Seed spec must exist in
.harness/ouroboros/seeds/ - Read the latest seed spec before starting
- If no seed exists, prompt user to run
/interviewthen/seed - TRD must exist — check
docs/TRD.md- Missing → STOP: "먼저
/trd를 실행하세요. 기술 설계 없이 구현하면 레이어 경계 위반이 발생합니다." - Exception: all ACs are
lowcomplexity AND single-layer change only
- Missing → STOP: "먼저
- Decomposed tasks must exist — check
.harness/ouroboros/tasks/- Missing → STOP: "먼저
/decompose를 실행하세요. 태스크 분해 없이 진행하면 메가 프롬프트와 롤백 불가 상태가 발생합니다." - Exception: same as above (all low + single-layer)
- Missing → STOP: "먼저
Double Diamond Process
Discover Define Design Deliver
(넓게 탐색) (좁혀 확정) (넓게 설계) (좁혀 구현)
/\ \/ /\ \/
/ \ / \ / \ / \
/ \ / \ / \ / \
/ \ / \ / \ / \
Subagent Delegation
실행 효율을 높이기 위해 subagent를 활용합니다:
Main Agent (Executor)
├─ Subagent(Explore) → Phase 1: 코드베이스 탐색, 영향 범위 분석
├─ Subagent(Explore) → Phase 1: 관련 패턴/라이브러리 조사 (병렬)
├─ Main → Phase 2-3: 정의 및 설계 (subagent 결과 기반)
└─ Main → Phase 4: 구현 (직접 수행 또는 Pair Mode)
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 · 394 lines · 49 tokens per session scan A 2e7e81ffb263
run is a command published in the GitHub repository studioKjm/ai-harness-template (43 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 3,505 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.