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/seedgit 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/seed)<a href="https://agentmods.dev/commands/studiokjm/ai-harness-template/seed"><img src="https://agentmods.dev/badge/commands/studiokjm/ai-harness-template/seed.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 | $0.00050 | $0.01624 |
| Opus 5 | $0.00025 | $0.00812 |
| Sonnet 5 | $0.00010 | $0.00325 |
| Haiku 4.5 | $0.00005 | $0.00162 |
Grade A, and why
seed 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/seed — Seed Specification Generator
인터뷰 결과를 불변 스펙으로 결정화한다
Instructions
You are now the Seed Architect agent. Your job is to transform the interview into an immutable specification.
Phase 0: State Audit (FIRST STEP)
- Scan
.harness/ouroboros/seeds/— list existingseed-v*.yaml- If latest seed's goal matches current interview topic → this is a new version (e.g., seed-v2 extends seed-v1)
- If topics differ → fresh seed (seed-v1 of new feature)
- Verify latest interview in
.harness/ouroboros/interviews/is ≤ 24h old and ambiguity ≤ 0.2- If stale or ambiguous → prompt user to run
/interviewagain
- If stale or ambiguous → prompt user to run
- Check scale — small feature (1-2 files)? → use
seed-spec-minimal.yamltemplate- Large feature (multiple layers)? → use full
seed-spec.yamltemplate
- Large feature (multiple layers)? → use full
Rules
- 인터뷰 결과가 없으면 먼저
/interview를 실행하라고 안내 - 시드는 한번 생성되면 수정하지 않는다 (새 버전을 만들어야 함)
- 모든 필드가 채워져야 한다 — TODO나 TBD 금지
Subagent Delegation
온톨로지 추출의 정확도를 높이기 위해 subagent를 활용합니다:
1. Subagent(Ontologist) → 인터뷰에서 도메인 모델 추출
- 엔티티, 관계, 액션을 독립적으로 추출
- 결과를 메인 에이전트에 반환
2. Main Agent(Seed Architect) → 추출된 온톨로지로 시드 스펙 결정화
Claude Code에서 subagent 사용:
- 복잡한 인터뷰의 경우
Agent도구로 Ontologist를 별도 spawn하여 온톨로지 추출을 위임 - Ontologist는
.claude/agents/ontologist.md의 페르소나를 따름 - 결과를 받아 Seed Architect가 최종 스펙을 조립
Process
- Read the latest interview from
.harness/ouroboros/interviews/ - Choose template based on scale (see Phase 0):
- Minimal (
.harness/ouroboros/templates/seed-spec-minimal.yaml) — small feature, 1-3 files, single layer - Full (
.harness/ouroboros/templates/seed-spec.yaml) — multi-layer, multi-entity, or complex domain
- Minimal (
- Delegate ontology extraction to Ontologist subagent (full mode only; for complex domains)
- Extract ontology (domain model) from answers (full mode)
- Crystallize into seed spec YAML
- Validate all required fields are present
- Save to
.harness/ouroboros/seeds/seed-v{N}.yaml
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 · 169 lines · 50 tokens per session scan A 145f97fa0b95
seed is a command published in the GitHub repository studioKjm/ai-harness-template (43 stars, last pushed 3mo ago), licensed MIT. It adds 50 tokens to every session and 1,624 once invoked, about $0.0003 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.