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/adelie-squad/solosquad/workflow-managernpx skills add Adelie-Squad/solosquad --skill workflow-managergit clone --depth 1 https://github.com/Adelie-Squad/solosquadWrote 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/adelie-squad/solosquad/workflow-manager)<a href="https://agentmods.dev/skills/adelie-squad/solosquad/workflow-manager"><img src="https://agentmods.dev/badge/skills/adelie-squad/solosquad/workflow-manager.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 | $0.00168 | $0.02122 |
| Opus 5 | $0.00084 | $0.01061 |
| Sonnet 5 | $0.00034 | $0.00424 |
| Haiku 4.5 | $0.00017 | $0.00212 |
Grade A, and why
workflow-manager 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Manager Skill — v1.3.7 (작성 권위)
너는 workflow 의 대화형 매니저이자 SoloSquad 의 워크플로 작성 표준을 보유한 권위다. workflow YAML 의
합성/검토/개선을 안내하고, 다른 워크플로를 만들거나 고칠 때마다 이 표준을 적용한다. 결정적 동작은
solosquad workflow * 헬퍼로 위임(파일 직접 조작 금지 — 검증·확인 게이트를 거치게).
작성 표준 (점진공개)
공통 작성 표준은 skills/skill-core/primitive-core.md 가 단일 진실원이다. 워크플로를 쓰거나 고칠 때
그 파일을 먼저 읽어 적용한다 — 특히 §0(workflow=org 조립물, skill·agent 참조) · §1(universal) ·
§2(인터뷰·초안앵커 4-mode) · §4.0–§4.1(본질 원칙·DAG) · §4.4(기획 3대 편향 가드) · §5(rubric).
3대 요지(코어 없이도 기억):
- 본질 원칙 — 워크플로 = 목표·근거·방법 → 결론 → 핸드오프(판단 단위). 단순 행위면 워크플로가 아니라 skill. 모든 stage 가 "무엇을 왜 어떤 근거·방법으로 하고 어떤 결론을 넘기나"를 갖춰야 한다.
- DAG 무순환 + measurable 게이트 —
_workflow/합성은 깊이 ≤2·순환 금지(workflow validate --all).exit_criteria는 measure+operator+threshold(free-text 금지). - 조립이지 발명 아님 — stage 의 agent-ref 는 워크스페이스 베이스(skill·agent)에 해소돼야 한다. 없으면 [[skill-manager]]·[[agent-manager]] 로 베이스부터 만든 뒤 조립.
C (생성) — 초안-앵커 인터뷰 (primitive-core §2)
- case 감지 — Chief 의
[creation_case:N]로 mode 결정(⑴명시 ⑵마이그레이션 ⑶대화 ⑷마이닝). - 초안 제시 — 매니저가 원재료(사용자 서술/리포 아티팩트/추론 shape/마이너 패턴)로 초안을 깔고, 빈 클러스터(objective/done·stages·handoff·exit_criteria·agents·failure·simplicity)를 명시.
- 인터뷰(암묵지 추출) — 빈 클러스터 위주로 enumerable 질문. 마이그레이션(⑵)은 1급 — 아티팩트에 없는 왜·판단·예외를 끌어내고, stage agent-ref 가 베이스에 해소되는지 검증(미해소면 베이스부터).
- 합성 — base 템플릿(아래) 정합 ≥70 이면 복사 후 customize, 아니면 ≥2 approaches 제시(anti-sycophancy).
<org>/workflows/wf-YYYY-MM-DD-<slug>/workflow.yaml+_status.yaml(첫 stage pending→in_progress). - 검증 —
solosquad workflow validate(DAG·agent-ref·sub-workflow cycle/depth) + 수용 rubric(§5) 자가채점.
durable 파일 — _log.md (v1.4.0 S-3)
장기 워크플로 디렉토리(<org>/workflows/<id>/)는 4종 durable-md 로 컨텍스트를 디스크에 남긴다
("컨텍스트 윈도우가 아니라 파일시스템이 진짜 메모리"): PRD.md(고정 스펙) · _status.yaml(마일스톤) ·
stage-<N>/_handoff.md(다음 단계 인계) · _log.md(신규 — 실행 감사 로그).
_log.md≠_handoff.md— handoff 는 다음 stage 에이전트 1회용 인계,_log.md는 워크플로 누적 감사(append-only)._handoff.md를 대체하지 않는다(spawn-assembler Layer[7] 는_handoff.md를 그대로 읽음 — 회귀 금지).- 누가·언제 쓰나: 라이브 Chief 턴이 stage 전이·주요 결정·알려진 이슈가 생길 때 한 줄씩 append. (토큰-임계 자동 핸드오프 작성자는 v1.4.x S-2b — 현재는 라이브 턴만 쓴다.)
- 포맷(append 블록):
## <ISO ts> — <stage|event> - 진행: <한 줄> - 결정: <왜·대안 기각 이유> - 제약/알려진 이슈: <있으면>
What ships with it
19 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.
- assets/workflows/data-analysis/workflow.yaml 718 B
- assets/workflows/five-whys/workflow.yaml 1.7 KB
- assets/workflows/hypothesis/workflow.yaml 1.4 KB
- assets/workflows/idea-refinement/workflow.yaml 1.3 KB
- assets/workflows/improvement/workflow.yaml 1.3 KB
- assets/workflows/kpi-check/workflow.yaml 1.2 KB
- assets/workflows/market-research/workflow.yaml 1.2 KB
- assets/workflows/new-build/workflow.yaml 1.6 KB
- assets/workflows/README.md 4.2 KB
- assets/workflows/requirements-analysis/workflow.yaml 2.1 KB
- assets/workflows/research/examples/backtest-example.md 2.7 KB
- assets/workflows/research/research-workflow.md 11 KB
- assets/workflows/research/subject-template/26xxxx_c1_experiment-name/experiment-plan.md 2.7 KB
- assets/workflows/research/subject-template/26xxxx_c1_experiment-name/experiment-result.md 2.0 KB
- assets/workflows/research/subject-template/final-result.md 1.8 KB
- assets/workflows/research/subject-template/research-plan.md 0 B
- assets/workflows/research/workflow.yaml 4.1 KB
- assets/workflows/scqa/workflow.yaml 1.9 KB
- assets/workflows/tdcc/workflow.yaml 1.7 KB
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 · 92 lines · 168 tokens per session scan A b5fb14aac162
workflow-manager is a skill published in the GitHub repository Adelie-Squad/solosquad (19 stars, last pushed 14d ago), licensed MIT. It adds 168 tokens to every session and 2,122 once invoked, about $0.0008 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
cost-efficiency-analyzer
Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for "are we spending too…
executive-financial-briefing
Generates a concise executive-level financial briefing or summary suitable for a CEO, CFO, or board presentation. Use when the user asks for a summary, briefing, executive summary, board update, financial overview, financial health check, or "how is the business doing". Covers the full P&L picture in one page. Also…
multi-quarter-trend-analysis
Analyzes financial trends across multiple quarters by comparing P&L metrics over time. Use when the user wants to see trends, patterns, trajectories, or directional movement across 3 or more quarters. Also use for "how are we trending", "show me the trend", "track performance over time", "quarter over quarter…
trend-analysis
Analyze price and volume trends for one or more stocks to determine momentum direction and key technical levels.
sector-rotation
Identify which market sectors to overweight or underweight based on current macro conditions and sector performance data.
persistent-notes
Save notes locally to /mnt/workspace/notes.json file. Use when user wants to "save a note" or "remember something".