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 skills/sonature-lab/timsquad/tsq-controllernpx skills add sonature-lab/timsquad --skill tsq-controllergit clone --depth 1 https://github.com/sonature-lab/timsquadWrote 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-controller)<a href="https://agentmods.dev/skills/sonature-lab/timsquad/tsq-controller"><img src="https://agentmods.dev/badge/skills/sonature-lab/timsquad/tsq-controller.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 | $0.00090 | $0.01798 |
| Opus 5 | $0.00045 | $0.00899 |
| Sonnet 5 | $0.00018 | $0.00360 |
| Haiku 4.5 | $0.00009 | $0.00180 |
Grade A, and why
tsq-controller 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 5d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Controller (Hybrid — Context DI + CLI)
서브에이전트에게 작업을 위임할 때 컨텍스트를 자동 해석하고 주입하는 컨테이너.
v3.0: 결정론적 로직(상태, 순서, 게이트)은 tsq next CLI로 이동. Controller는 판단(스펙 결정, 품질 평가, 프롬프트 구성)에 집중.
Contract
- Trigger: 서브에이전트 위임 시 (구현, 테스트, 리뷰 등)
- Input:
tsq nextJSON + 에이전트 파일 + compiled specs - Output: 조합된 프롬프트로 Task() 실행
- Error: spec stale 시
tsq compile재실행 안내
Protocol
- 다음 태스크 조회:
tsq next실행 → JSON 출력에서 taskId, phaseId, sequenceId, title, agent 추출all_complete→ 사용자에게 완료 안내error→ planning.md 부재 시/tsq-decompose안내
- Task Context 기록:
.timsquad/.daemon/task-context.json에 현재 태스크 정보 저장 (SubagentStop hook이 읽음) - Memory 참조:
memory/디렉토리의 모든 .md 파일 Read - SSOT Map 참조:
.timsquad/ssot-map.yaml→ 티어 compiled spec 목록 확인 - Capability Token 발급:
.timsquad/state/controller-active+allowed-paths.txt생성 - 에이전트 파일 확인:
.claude/agents/{agent}.md읽기 - Prerequisites 파싱:
<prerequisites>태그에서 SSOT 목록 추출 - Spec Resolve:
references/에서 해당 compiled spec 로드 - Meta Index 쿼리:
.timsquad/.daemon/task-context.json읽기 → scope 파일 구조를 프롬프트에 주입 (Daemon이 자동 갱신) - Stale 체크:
.compile-manifest.jsonhash 비교 - 방법론 참조:
config.yaml의methodology.development→ 해당 스킬 Protocol 로드 - 프롬프트 조합: tsq-protocol + phase-memory carry-over + memory + specs + meta-index scope + methodology + phase 제약 + 지시
.timsquad/state/phase-memory.md존재 시 carry-over/주의 섹션을 프롬프트 앞에 강제 삽입
- Model Routing → Task() 호출: Model Routing 테이블에 따라 최종 모델을 결정한 뒤, 조합된 프롬프트로 서브에이전트 실행. 결정된 모델을 Task()의 model 파라미터로 전달
- Completion Report 검증: 5개 필드(Task, Status, Files, Tests, Notes) 확인 — 누락 시 재요청
- Capability Token 회수:
controller-active+allowed-paths.txt삭제 - 다음 태스크: Step 1로 돌아가서 반복 (또는 Phase 완료 시 Librarian 호출)
이전(v2.1)에서 Controller가 직접 하던 작업의 코드 이동:
planning.md 파싱→tsq nextCLI (결정론적)workflow.json 갱신→ SubagentStop hook이tsq next --complete자동 호출Phase 완료 판정→ completion-guard hook이tsq next --phase-status호출phase-memory append→ SubagentStop hook이 자동 append
What ships with it
5 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.
- 5d ago First seen · 105 lines · 90 tokens per session scan A 3478094949bc
tsq-controller is a skill published in the GitHub repository sonature-lab/timsquad (11 stars, last pushed 7d ago), licensed MIT. It adds 90 tokens to every session and 1,798 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
angular-migration-v2
Angular Migration workflow skill. Use this skill when the user needs Master AngularJS to Angular migration, including hybrid apps, component conversion, dependency injection changes, and routing migration and the operator should preserve the upstream workflow, copied support files, and provenance before merging or…
agent-memory-mcp-v2
Agent Memory Skill workflow skill. Use this skill when the user needs A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions) and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing…
vector-hybrid-search
Retrieve knowledge from a vector-store collection via the vector-mcp MCP server's vectorsearch tool — semantic (ANN) search, lexical BM25 search, or a hybrid of the two fused with Reciprocal Rank Fusion. Use when the agent must answer a question from an indexed corpus, pull top-k relevant chunks for RAG context, or…
apply-distributed-team-practices
Use when managing a team where members work in different locations, time zones, or on hybrid schedules — to adapt management practices so remote members have equal access to information, relationships, and advancement opportunities as in-office members.
ionic-framework-docs
Ionic Framework 8.x — UI components, Angular/React/Vue integrations, theming, CLI, Capacitor, navigation.
angular-di-docs
Angular v22 Dependency Injection — DI overview, creating and using services with @Service and @Injectable, defining dependency providers (InjectionToken, useClass, useValue, useFactory, useExisting, multi providers), injection context and runInInjectionContext, hierarchical injectors (EnvironmentInjector…