Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sonature-lab/timsquadnpx agentmods add skills/sonature-lab/timsquad/tsq-decomposeWrote 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/sonature-lab/timsquad/tsq-decompose)<a href="https://agentmods.dev/skills/sonature-lab/timsquad/tsq-decompose"><img src="https://agentmods.dev/badge/skills/sonature-lab/timsquad/tsq-decompose/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/sonature-lab/timsquad/tsq-decompose"><img src="https://agentmods.dev/badge/skills/sonature-lab/timsquad/tsq-decompose.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 | $0.00093 | $0.01189 |
| Opus 5 | $0.00046 | $0.00594 |
| Sonnet 5 | $0.00019 | $0.00238 |
| Haiku 4.5 | $0.00009 | $0.00119 |
Grade A, and why
tsq-decompose 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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/tsq-decompose — 자동 태스크 분해
Sub-PRD의 요구사항을 분석하여 Phase-Sequence-Task 구조의 실행 계획을 자동 생성한다.
Concepts
Phase = Topological Layer (순차 실행, 이전 Phase 완료 필요)
Sequence = Parallel Batch (동일 Phase 내 병렬 실행 가능 단위)
Task = Atomic Work Unit (단일 에이전트가 수행하는 최소 작업)
- Phase ID:
P{N}(P1, P2, ...) - Sequence ID:
P{N}-S{NNN}(P1-S001, P1-S002, ...) - Task ID:
P{N}-S{NNN}-T{NNN}(P1-S001-T001, ...)
Process
Step 1: Sub-PRD 스캔
.timsquad/ssot/prd/하위 Sub-PRD 파일 전체 읽기- 각 Sub-PRD에서 Must-Have(P0) 요구사항 추출
- Should-Have(P1)는 별도 Phase 후순위 배치
Step 2: 의존성 분석
요구사항 간 의존성 그래프 구성:
데이터 모델 → API 구현 → UI 구현
인증 → 권한 기반 기능
공통 컴포넌트 → 화면별 구현
의존성 판단 기준:
- 데이터 의존: 테이블/스키마가 필요한 기능은 DB 설계 후
- API 의존: API가 필요한 UI는 API 구현 후
- 기능 의존: Sub-PRD 간 명시적 참조
Step 3: DAG 정렬 → Phase 배치
- Topological sort로 의존성 레이어 계산
- 같은 레이어 = 같은 Phase
- Phase 내에서 독립적인 작업 그룹 = Sequence
- Sequence 내 개별 작업 = Task
Phase 배치 관례:
| Phase | 일반적 내용 |
|---|---|
| P1 | 인프라/DB 스키마/공통 설정 |
| P2 | 핵심 API + 비즈니스 로직 |
| P3 | UI/UX 구현 |
| P4 | 통합 + E2E 테스트 |
| P5+ | 보안 감사, 성능 최적화, 배포 |
Step 4: Task 상세화
각 Task에 포함할 정보: Task ID, 설명, 담당 에이전트, 입력(SSOT refs, 선행 산출물), 출력(코드, 테스트, 문서), 완료 기준.
Step 5: Traceability 매핑 (Layer A)
각 Sub-PRD의 Mapped Artifacts 테이블에 생성된 Task ID를 역링크:
| Type | ID | Link |
|------|----|------|
| Tasks | P1-S001-T001~T003 | [planning.md](../planning.md#P1-S001) |
Step 6: planning.md 생성
.timsquad/ssot/planning.md에 Phase-Sequence-Task 전체 계획 작성.
각 Sequence에 PRD 역방향 링크 포함 (Layer B):
### Sequence S001: Authentication (PRD: [prd/auth](./prd/auth.md))
| Task ID | Description | Agent | PRD Ref | FR Ref |
|---------|-------------|-------|---------|--------|
| P1-S001-T001 | DB schema | dba | prd/auth | FR-AUTH-001 |
Step 6.5: Plan Review (자동)
planning.md 생성 후 Controller에 Plan Reviewer 위임 요청. Reviewer(fork 컨텍스트)가 Sub-PRD 커버리지 100%, DAG 무결성, Task 크기(1에이전트 1세션), Phase 배치 순서를 검증. 결과를 Step 7에서 함께 제시.
Step 7: Human Checkpoint
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 · 118 lines · 93 tokens per session scan A 03a4e8d6d36e
tsq-decompose is a skill published in the GitHub repository sonature-lab/timsquad (11 stars, last pushed 9d ago), licensed MIT. It adds 93 tokens to every session and 1,189 once invoked, about $0.0005 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
agentrq
Lead multiple agents to accomplish big tasks with specialized workspaces/agents by assigning tasks to specialized agents.
agentrq
Execute tasks assigned by humans or supervisor agents within a specific AgentRQ workspace. Use when you receive channel messages or need to report progress on tasks.
run-task
Execute a single Todo task through In Progress to Review, meeting every acceptance criterion with tests and vibe-lint checks. Refuses Planning-status tasks. Invoked as /agiflow:run-task . Uses gettask, updatetask, createtaskcomment.
bbs-relay-pickup
A coordination procedure for agents that share work on tasks through a BBS task system, where BBS is the service used to claim, run, and report task steps.
bbs-relay-single-task
A relay procedure for taking over a task from an engine notification, which includes the task's current state.
lean4
Use when editing .lean files, debugging Lean 4 builds (type mismatch, sorry, failed to synthesize instance, axiom warnings, lake build errors), searching mathlib for lemmas, formalizing mathematics in Lean, or learning Lean 4 concepts. Also trigger when the user asks for help with Lean 4, mathlib, or lakefile. Do NOT…