tsq-quick

tsq-quick is a skill for Claude Code from sonature-lab/timsquad. It costs 195 tokens per session (725 once invoked), scanned A, original, MIT.

A controller-guided way to complete one coding task while keeping the project’s existing specifications, memory, and workflow state in view.

In plain words
What is it for?
Use it for a focused bug fix, refactoring, method or API addition, test writing, a change to one file, or the next single task in a project plan.
Why use it?
It avoids the overhead of running the full project workflow for a small change while preserving context and limiting the files an agent may change.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

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.

agentmods
npx agentmods add skills/sonature-lab/timsquad/tsq-quick
Any agent
npx skills add sonature-lab/timsquad --skill tsq-quick
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-quick

README.md
[![agentmods](https://agentmods.dev/badge/skills/sonature-lab/timsquad/tsq-quick.svg)](https://agentmods.dev/skills/sonature-lab/timsquad/tsq-quick)
Your own site
<a href="https://agentmods.dev/skills/sonature-lab/timsquad/tsq-quick"><img src="https://agentmods.dev/badge/skills/sonature-lab/timsquad/tsq-quick.svg" alt="Measured on agentmods" height="20"></a>
Per session 195 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 725 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00195 $0.00725
Opus 5 $0.00097 $0.00362
Sonnet 5 $0.00039 $0.00145
Haiku 4.5 $0.00019 $0.00072

Measured 6d ago against content hash 561e82d62eb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tsq-quick 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 6d 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-quick/SKILL.md · 59 lines

What it actually says

/tsq-quick — Controller 경유 단일 태스크

풀 파이프라인 없이 단일 태스크를 Controller 경유로 실행한다. Controller를 경유하는 이유: SSOT/메모리/현재 상태를 주입받아야 이전 작업과 일관성을 유지할 수 있고, Capability Token으로 서브에이전트의 변경 범위를 제한할 수 있기 때문이다.

Protocol

  1. 현재 위치 확인: .timsquad/state/workflow.json → 진행 중인 Phase/Sequence/Task 파악
  2. 태스크 결정:
    • 사용자가 태스크를 지정 → 해당 태스크 실행
    • 미지정 → workflow.json의 다음 미완료 태스크 실행
  3. SSOT 참조: .timsquad/ssot-map.yaml → 해당 태스크 관련 spec 로드
  4. 메모리 참조: memory/ 디렉토리 읽기
  5. Controller 위임 (tsq-controller Protocol, 단일 태스크 모드):
    • Capability Token 발급
    • 에이전트 파일 + spec + methodology 조합
    • Task() 단일 호출
    • Completion Report 검증
    • Capability Token 회수
  6. 로그 기록: 최소 로그 (L1 수준)
  7. 테스트 게이트: 변경된 파일 관련 단위 테스트만 실행
  8. workflow.json 갱신: 완료된 태스크 상태 기록

vs /tsq-full

항목 /tsq-quick /tsq-full
Phase-Sequence-Task X (단일) O (전체)
Controller 경유 O O
SSOT/메모리 참조 O O
게이트 unit만 unit → integration → e2e
Librarian 호출 X O
planning.md 필요 X O

Usage

/tsq-quick 로그인 버튼 색상을 파란색으로 변경
/tsq-quick UserService에 이메일 검증 메서드 추가
/tsq-quick 태스크 13 실행
/tsq-quick                  ← 다음 미완료 태스크 자동 실행
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. 6d ago First seen · 59 lines · 195 tokens per session scan A 561e82d62eb7

Subscribe to this mod's changes

tsq-quick is a skill published in the GitHub repository sonature-lab/timsquad (11 stars, last pushed 6d ago), licensed MIT. It adds 195 tokens to every session and 725 once invoked, about $0.0010 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

btw

By-The-Way: capture improvement ideas the moment they surface, without derailing the task in progress. Triggers: /bkit:btw, /bkit:btw list, /bkit:btw analyze, /bkit:btw promote, /bkit:btw stats, btw, suggestion, improve, idea, feedback.

ww-w-ai/bkit-claude-code · 75 tokens

pdca-fast-track

Daniel-mode fast-track auto-approves Checkpoint 1-8 when Trust ≥ 80, fastTrack on, Design doc exists. Else L2 + manual gates. Triggers: pdca fast-track, skip checkpoints, auto approve.

ww-w-ai/bkit-claude-code · 53 tokens

glyph

Render an answer as ASCII art plus semantic emojis inline, right now, with no setup questions. Use for a fast visual take on status, comparisons, trade-offs, architecture, or any ad-hoc 'show me X visually' ask. For a full multi-artifact plan playground, use visualize-plan instead.

yonatangross/orchestkit · 64 tokens

rotation-check

Standard-Gerüst für rotierende Pipeline-Checks: Pro Lauf genau ein Ziel aus einer Menge (Projekte, Ordner, Repos) wählen — bevorzugt das am längsten ungeprüfte —, den Check durchführen, Ergebnis in einer Check-Registry und einem Verlaufslog festhalten. Nutze diesen Skill, wenn ein wiederkehrender Check über viele…

ellmos-ai/skills · 148 tokens

evidence-selfloop

Evidence self-loop for surveys: read evidence bindings + evidence packs, then write an actionable upstream TODO plan (which stage/skill to fix) before writing more prose.

WILLOSCAR/research-units-pipeline-skills · 38 tokens

citation-verifier

Generate and verify BibTeX entries from paper notes, writing citations/ref.bib and citations/verified.jsonl.

WILLOSCAR/research-units-pipeline-skills · 32 tokens