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 skills add treylom/tofu-at --skill tofu-at-spawn-templatesgit clone --depth 1 https://github.com/treylom/tofu-atWrote 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/skills/treylom/tofu-at/tofu-at-spawn-templates)<a href="https://agentmods.dev/skills/treylom/tofu-at/tofu-at-spawn-templates"><img src="https://agentmods.dev/badge/skills/treylom/tofu-at/tofu-at-spawn-templates/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/skills/treylom/tofu-at/tofu-at-spawn-templates"><img src="https://agentmods.dev/badge/skills/treylom/tofu-at/tofu-at-spawn-templates.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.01607 |
| Opus 5 | $0.00025 | $0.00804 |
| Sonnet 5 | $0.00010 | $0.00321 |
| Haiku 4.5 | $0.00005 | $0.00161 |
Grade A, and why
tofu-at-spawn-templates 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 11d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tofu-AT Spawn Prompt Templates
/tofu-at가 팀원을 스폰할 때 사용하는 프롬프트 템플릿. 변수({{VAR}})를 실제 값으로 치환하여 사용.
빠른 참조 — 어떤 템플릿을 쓸까?
| 역할 | 참조 파일 | 섹션 |
|---|---|---|
| 최종 리드 (Lead) | references/lead-templates.md |
Section 2 |
| 카테고리 리드 | references/lead-templates.md |
Section 3 |
| 워커 (General-Purpose) | references/worker-templates.md |
Section 4 |
| 기존 에이전트/스킬 래퍼 | references/worker-templates.md |
Section 4.5 |
| 워커 (Explore 읽기전용) | references/worker-templates.md |
Section 5 |
| codex-exec-worker Bridge | references/worker-templates.md |
Section 9 |
1. 핵심 변수 (Key Variables)
| 변수 | 설명 | 소스 |
|---|---|---|
{{TEAM_ID}} |
팀 ID | registry.yaml team_id |
{{TEAM_NAME}} |
TeamCreate에 전달할 팀 이름 | team_id에서 .을 -로 치환 |
{{PURPOSE}} |
팀 목적 | registry.yaml purpose |
{{ROLE_NAME}} |
에이전트 이름 | registry.yaml roles[].name |
{{ROLE_TYPE}} |
역할 유형 | category_lead / worker |
{{MODEL}} |
할당 모델 | registry.yaml roles[].model |
{{TOOLS}} |
할당 도구 목록 | registry.yaml roles[].tools |
{{MCP_SERVERS}} |
활성 MCP 서버 | .mcp.json + ToolSearch 결과 |
{{TASKS}} |
할당된 태스크 | TaskCreate 결과 |
{{EXPERT_NAME}} |
실존 전문가 이름 | Step 5-2 resolve_expert 결과 |
{{EXPERT_FRAMEWORK}} |
핵심 프레임워크/저서 | Step 5-2 resolve_expert 결과 |
{{DOMAIN_VOCABULARY}} |
전문가 핵심 용어 목록 (쉼표 구분) | Step 5-2 resolve_expert 결과 |
{{CLAUDE_BEHAVIOR_BLOCK}} |
Claude 최적화 XML 블록 | Step 5-5 결과 |
전체 변수 목록 (22개):
references/worker-templates.mdSection 1
2.5. 모델 배정 검증 (스폰 직전 — MANDATORY)
모든 워커 스폰 전에 반드시 실행합니다. Opus 워커 배정을 자동 차단합니다.
FOR each role IN spawn_queue:
IF role.type == "worker" AND role.model == "opus":
→ user_explicitly_approved_opus_workers?
→ NO: role.model = "sonnet" (강제 다운그레이드)
로그: "⚠️ {role.name}: opus → sonnet 다운그레이드 (사용자 미승인)"
→ YES: 진행 (STEP 2 응답 기록에 근거 명시)
금지 패턴:
- worker에 opus 배정 시 사용자 미승인이면 자동 차단
- "작업이 복잡해서 opus가 필요" 등 자의적 판단으로 업그레이드 금지
- STEP 2 응답에 명시적 기록 없으면 기본값(sonnet) 적용
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 137 lines · 50 tokens per session scan A 691a756dbce0
tofu-at-spawn-templates is a skill published in the GitHub repository treylom/tofu-at (56 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 1,607 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…