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-retrogit 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-retro)<a href="https://agentmods.dev/skills/sonature-lab/timsquad/tsq-retro"><img src="https://agentmods.dev/badge/skills/sonature-lab/timsquad/tsq-retro/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-retro"><img src="https://agentmods.dev/badge/skills/sonature-lab/timsquad/tsq-retro.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 | $0.00092 | $0.01242 |
| Opus 5 | $0.00046 | $0.00621 |
| Sonnet 5 | $0.00018 | $0.00248 |
| Haiku 4.5 | $0.00009 | $0.00124 |
Grade A, and why
tsq-retro 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 10d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retrospective Cycle
피드백 수집 → KPT 회고 → 개선 적용의 전체 학습 루프를 관리한다.
Contract
- Trigger:
/tsq-retro,/tsq-retro feedback,/tsq-retro improve - Input: 모드에 따라 다름 (아래 Mode 참조)
- Output: 피드백 엔트리 / KPT 리포트 / 개선 적용 결과
- Error: 데이터 부족 시 수집 가능 범위 안내
- Dependencies: tsq-protocol
Modes
Mode 1: feedback — 피드백 기록
/tsq-retro feedback "<메시지>" 또는 작업 중 이슈 발견 시.
- 레벨 분류: 메시지 내용으로 L1/L2/L3 판정
- L1 (구현): 버그, 코드 품질, 테스트 누락 — 현재 Task에서 바로 수정 가능
- L2 (설계): 아키텍처 변경, API 재설계, 스키마 수정 — Sequence/Phase 수준 조정 필요
- L3 (기획): 요구사항 변경, 스펙 모순, 우선순위 재조정 — SSOT 수정 필요
- 기록:
.timsquad/retrospective/feedback.jsonl에 append{"ts":"ISO8601","level":1,"phase":"P2","message":"...","status":"open"} - 즉시 조치 판단:
- L1 → 현재 Task에서 수정 권고 (알림만)
- L2 → 현재 Sequence 완료 후 Architect 검토 권고
- L3 → Phase 완료 시
/tsq-retro에서 우선 다룸
상세 분류 기준은 references/feedback-guide.md 참조.
Mode 2: retro — KPT 회고 (기본)
/tsq-retro 또는 /tsq-retro retro. Phase 완료 후 실행 권장.
- 데이터 수집:
.timsquad/logs/— 작업 로그.timsquad/retrospective/feedback.jsonl— 수집된 피드백.timsquad/retrospective/metrics/— 메트릭.timsquad/retrospective/patterns/— 기존 패턴
- 메트릭 계산: 작업 수, 성공률, 평균 수정 횟수, 피드백 레벨별 건수
- KPT 분석: Keep / Problem / Try 분류
- 패턴 식별: 실패 패턴(FP, 3회+ 반복) / 성공 패턴(SP, 효과 검증)
- 리포트 작성:
.timsquad/retrospective/retro-{phase}.md - 개선 제안: 실행 가능한 액션 아이템 도출 → 사용자 승인 대기
- 피드백 정리: 처리된 feedback.jsonl 엔트리를
status: "resolved"처리
리포트 구성: 메트릭 요약 → 에이전트별 성과 → 피드백 분석(L1/L2/L3) → 패턴(FP/SP) → 개선 조치 → 다음 목표.
Mode 3: improve — 개선 적용
/tsq-retro improve. 회고에서 승인된 개선을 실제로 적용.
- 제안 로드: 최근 retro 리포트에서 승인된 개선 항목 읽기
- 대상 분류: 개선 대상별로 분류
- 스킬 패치: SKILL.md 규칙/프로토콜 수정
- 템플릿 수정: agent.md, config.yaml 등
- 패턴 등록:
.timsquad/retrospective/patterns/에 FP/SP 기록 - lessons 기록:
.timsquad/retrospective/lessons.md에 학습 사항 append
- 적용: 각 대상에 diff 형태로 변경 사항 제시 → 사용자 확인 후 적용
- 검증: 변경 후
npm test통과 확인 - 기록: 적용된 개선을 lessons.md에 기록, 다음 retro에서 효과 측정
What ships with it
3 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.
- 10d ago First seen · 87 lines · 92 tokens per session scan A 9700055aec4a
tsq-retro is a skill published in the GitHub repository sonature-lab/timsquad (11 stars, last pushed 10d ago), licensed MIT. It adds 92 tokens to every session and 1,242 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
learning-agility
Builds the leader's capacity for rapid, continuous learning through humility, curiosity, feedback receptivity, cross-training, reflective practice, and deliberate skill selection. Use when a leader's expertise has become stale, when the organisation faces skills gaps that training alone cannot close, when setbacks…
run-team-retrospective
Use when a team needs to reflect on a completed period, project, or significant event — to extract what worked, what didn't, and what specific changes to make before the next cycle, rather than repeating the same patterns.
kaizen
Kaizen (改善): every process has waste; eliminate it incrementally.
self-improver
Review affiliate campaign results and improve strategy. Triggers on: "review my results", "what went wrong", "how to improve conversions", "analyze my campaign", "affiliate retrospective", "why am I not converting", "improve my strategy", "what should I change", "campaign review", "optimize my approach", "learn from…
Effective Memory
The essential habits for an AI agent with memory — session bookends, learning triggers, verification, safety, and the operational discipline that turns raw recall into compounding intelligence. Pinned, always-injected.
humility-and-power
Addresses the corrosive effects of power on leadership and prescribes humility as the primary antidote. Covers staying humble as authority grows, recognising the early signs of ego distortion, creating channels for honest feedback, acknowledging weaknesses as a strength, and maintaining genuine connection with the…