tsq-librarian

tsq-librarian is a skill for Claude Code from sonature-lab/timsquad. It costs 82 tokens per session (1,116 once invoked), scanned A, original, MIT.

A record-keeping skill for closing development phases and updating the project's source-of-truth documents. It creates phase summaries, archives decisions, records unresolved work, and updates phase memory.

In plain words
What is it for?
Use it after a phase is complete to collect logs and decisions, create a phase trail and report, identify stale documentation, and prepare context for the next phase.
Why use it?
It preserves why decisions were made and carries unfinished or outdated items into the next phase instead of losing them in logs.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it after a phase is complete to collect logs and decisions, create a phase trail and report, identify stale documentation, and prepare context for the next phase.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sonature-lab/timsquad/tsq-librarian
Install

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.

Any agent
npx skills add sonature-lab/timsquad --skill tsq-librarian
Clone the repo
git clone --depth 1 https://github.com/sonature-lab/timsquad

Made for: Claude Code.

Wrote 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.

agentmods badge for tsq-librarian

README.md
[![agentmods](https://agentmods.dev/badge/skills/sonature-lab/timsquad/tsq-librarian/github.svg)](https://agentmods.dev/skills/sonature-lab/timsquad/tsq-librarian)
Your own site
<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.

agentmods 80×15 button for tsq-librarian

Your own site · 80×15
<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>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,116 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 12d ago against content hash 3e4bff059c93, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

templates/base/skills/tsq-librarian/SKILL.md · 79 lines

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

  1. L1/L2 로그 수집: .timsquad/logs/ 하위 해당 Phase 로그 전체 읽기
  2. Decision Log 수집: .timsquad/state/decisions.jsonl 읽기
  3. SSOT 상태 확인 + Carry-over:
    • .compile-manifest.json hash 비교 → stale 목록 식별
    • .timsquad/.daemon/drift-warnings.json 존재 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)
  4. Phase Trail 작성: .timsquad/trails/phase-{id}.md 생성
    • 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)
  5. Phase Memory 아카이브 + 새 HEAD 생성: a. 현재 phase-memory.mdtrails/phase-{id}-memory.md 복사 (아카이브) b. 새 phase-memory.md 생성 (~50줄 엄수):
    ---
    phase: {new-phase-id}
    prev: trails/phase-{id}-memory.md
    created: {ISO8601}
    ---
    
    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
  6. Decision Log 아카이브:
    • decisions.jsonl → trails/phase-{id}-decisions.jsonl 복사
    • decisions.jsonl 초기화 (빈 파일)
  7. Trails 정리: trails/ 내 memory 아카이브가 10개 초과 시 가장 오래된 것부터 삭제
  8. 종합 리포트 + Context Note 작성
    • .timsquad/reports/{phase}-report.md 생성
    • docs/sprint/ 하위에 다음 Phase 맥락 문서

Constraints

  • 소스 코드(src/, lib/, app/) 수정 절대 금지
  • .timsquad/docs/ 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

Read the full file on GitHub · 79 lines

Changes

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.

  1. 12d ago First seen · 79 lines · 82 tokens per session scan A 3e4bff059c93

Subscribe to this mod's changes

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.

Related

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.

griddynamics/rosetta · 10 tokens

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.

oliver-zehentleitner/keep-the-why · 65 tokens

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.

zhinjs/zhin · 61 tokens

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.

docmancer/docmancer · 62 tokens

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.

Goldziher/ai-rulez · 60 tokens

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.

nicholasglazer/gnosis-mcp · 38 tokens