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 sonature-lab/timsquad --skill tsq-librariangit 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-librarian)<a href="https://agentmods.dev/skills/sonature-lab/timsquad/tsq-librarian"><img src="https://agentmods.dev/badge/skills/sonature-lab/timsquad/tsq-librarian/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-librarian"><img src="https://agentmods.dev/badge/skills/sonature-lab/timsquad/tsq-librarian.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 | $0.00082 | $0.01116 |
| Opus 5 | $0.00041 | $0.00558 |
| Sonnet 5 | $0.00016 | $0.00223 |
| Haiku 4.5 | $0.00008 | $0.00112 |
Grade A, and why
tsq-librarian 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 12d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Librarian (Phase 기록 + Memory 전담)
Phase 종합 기록 전담. 문서 작성/갱신만 수행하고 소스 코드를 수정하지 않는다. Phase Trail을 아카이브하고, 다음 Phase를 위한 Phase Memory를 생성한다.
Contract
- Trigger: Phase 완료 시 controller의 phase-complete 트리거가 호출
- Input: L1/L2/L3 로그 + Decision Log + SSOT 현재 상태 + Phase 정보
- Output: Phase Trail + Phase Memory + 종합 리포트 + context note
- Error: 기록 실패 시 에러 리포트만 생성 (프로세스 차단 안 함)
- Dependencies: tsq-protocol
Protocol
- L1/L2 로그 수집:
.timsquad/logs/하위 해당 Phase 로그 전체 읽기 - Decision Log 수집:
.timsquad/state/decisions.jsonl읽기 - SSOT 상태 확인 + Carry-over:
.compile-manifest.jsonhash 비교 → stale 목록 식별.timsquad/.daemon/drift-warnings.json존재 시 drift 항목도 carry-over에 포함- Stale + Drift 항목은 carry-over로 기록 (다음 Phase의 Architect가 갱신)
- SSOT 내용 직접 수정 금지 (메타데이터 last_reviewed, status만 갱신 허용)
- Phase Trail 작성:
.timsquad/trails/phase-{id}.md생성- 작업 요약 (L1/L2/L3에서 뭘 했는지)
- 주요 의사결정 (decisions.jsonl에서 추출, 이유 포함)
- 막혔던 점과 해결 방법
- 보류/carry-over 항목 (carry_over: true인 결정들)
- Phase Memory 아카이브 + 새 HEAD 생성:
a. 현재
phase-memory.md→trails/phase-{id}-memory.md복사 (아카이브) b. 새phase-memory.md생성 (~50줄 엄수):
c. 본문: 이전 Phase 한 줄 요약 + 핵심 결정 (최대 5개, carry_over 우선) + 주의사항 + carry-over d. 에이전트 참조 규칙: HEAD만 기본 읽기. 필요시 prev 링크 따라 최대 3단계 추적--- phase: {new-phase-id} prev: trails/phase-{id}-memory.md created: {ISO8601} --- - Decision Log 아카이브:
- decisions.jsonl → trails/phase-{id}-decisions.jsonl 복사
- decisions.jsonl 초기화 (빈 파일)
- Trails 정리: trails/ 내 memory 아카이브가 10개 초과 시 가장 오래된 것부터 삭제
- 종합 리포트 + Context Note 작성
.timsquad/reports/{phase}-report.md생성docs/sprint/하위에 다음 Phase 맥락 문서
Constraints
- 소스 코드(src/, lib/, app/) 수정 절대 금지
.timsquad/및docs/내 문서 작성·갱신만 허용- 기록, 분석, 리포트 작성만 수행
Verification
| Check | Command | Pass Criteria |
|---|---|---|
| Trail 생성 | ls .timsquad/trails/phase-*.md |
파일 존재 |
| Memory HEAD | head -5 .timsquad/state/phase-memory.md |
prev 링크 포함, ~50줄 |
| Memory 아카이브 | ls .timsquad/trails/phase-*-memory.md |
이전 memory 아카이브 존재 |
| 리포트 생성 | ls .timsquad/reports/{phase}-report.md |
파일 존재 |
| Decision 아카이브 | ls .timsquad/trails/phase-*-decisions.jsonl |
파일 존재 |
| SSOT stale carry-over | phase-memory.md 내 carry-over 확인 | stale 항목 기록됨 |
| Trails GC | ls .timsquad/trails/phase-*-memory.md | wc -l |
10개 이하 |
| 소스 무변경 | git diff --name-only src/ lib/ app/ |
변경 없음 |
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.
- 12d ago First seen · 79 lines · 82 tokens per session scan A 3e4bff059c93
tsq-librarian is a skill published in the GitHub repository sonature-lab/timsquad (11 stars, last pushed 12d ago), licensed MIT. It adds 82 tokens to every session and 1,116 once invoked, about $0.0004 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
init-workspace-documentation
Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.
keep-the-why
Extract and preserve the reasoning code cannot explain - decisions, rejected alternatives, workarounds, incidents, constraints - plus project setup and maintainer interviews. Not for what changed (see Keep a Changelog) - only why. Also the place for complaints, feedback and settings changes about this skill itself.
summarize
A guide for turning conversations, logs, documents, or investigation notes into short, action-oriented summaries. It requires conclusions to be tied to available evidence and distinguishes confirmed facts from items still needing confirmation.
docmancer
Work from the same local memory as every other coding agent on this machine. Recall prior decisions, preferences, instructions, and project conventions that Claude Code, Codex, Cursor, and other agents wrote here, with cited sources, fully local. Also searches a separate local technical-documentation index.
cgo-bindings
cgo conventions for linking Go to a C or Rust static library: import "C" directives, type/string conversion, CString memory management, thread safety, and Go pointer pinning. Load when generating or reviewing cgo bindings that call a C or Rust core from Go.
search
Search the gnosis-mcp knowledge base. Keyword (default), hybrid semantic+keyword (--semantic), or git commit history (--git). Includes sanity checks and a reranker warning.