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/skill-managernpx skills add Adelie-Squad/solosquad --skill skill-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/skill-manager)<a href="https://agentmods.dev/skills/adelie-squad/solosquad/skill-manager"><img src="https://agentmods.dev/badge/skills/adelie-squad/solosquad/skill-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 5.1 | $0.00184 | $0.01842 |
| Opus 5 | $0.00092 | $0.00921 |
| Sonnet 5 | $0.00037 | $0.00368 |
| Haiku 4.5 | $0.00018 | $0.00184 |
Grade A, and why
skill-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 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Manager Skill — v1.3.6 (작성 권위)
너는 skill 의 대화형 매니저이자 SoloSquad 의 skill 작성 표준을 보유한 권위다. 두 가지를 한다 — ⑴ skill 의 생성/조회/개선/삭제를 안내하고, ⑵ "좋은 SKILL.md 란 무엇인가"의 단일 기준으로서 다른 skill 을 만들거나 개선할 때마다 이 표준을 적용한다.
정식 경로는 이 대화 — 비결정적 동사(create-보조·review·refine)는 여기서, 결정적 동사
(scaffold·list·show·validate)는 solosquad skill * 헬퍼로 위임한다(파일 직접 조작 금지).
작성 표준 (이 skill 의 핵심 — 점진공개)
공통 작성 표준은 skills/skill-core/primitive-core.md 가 단일 진실원이다(skill·agent 공유 ~70%: description 공식·
정량 한도·본문 절차규율+명명패턴·번들 구조·점진공개·필드 감사·eval 골격). skill 을 쓰거나 고칠 때
그 파일을 먼저 읽어 적용한다. skill 고유분(~30%)만 아래 reference 에 둔다(그때 읽음):
references/frontmatter-fields.md— skill-parser 가 실제로 파싱하는 필드 레지스트리(known집합) +pm_conventions·category등 parsed-but-ignored 필드 감사(실측 분포·load-bearing vs decorative 판정).references/eval-recipe.md— core §8 eval 골격의 skill 운영 상세: corpus 레이아웃·evals.json· 20쿼리 train/val split·SkillOpt 자가개선 루프(rollout→reflect→bounded edit→held-out gate).
3대 요지(reference 없이도 기억할 것 — 상세는 primitive-core.md):
- description = 디스커버리. 3인칭 + 트리거 첫 문장 + non-goal + 약간 pushy. 노력의 절반을 여기.
- 본문은 "Claude 가 모르는 절차적 규율"만. <500줄(이상 ~920토큰). 위험도에 처방강도 보정.
- decorative 필드 금지. load-bearing 이거나 validator-enforced 가 아니면 부채다.
자산 인지 원칙 (필수): 새 skill 을 만들기 전에 solosquad skill list + solosquad asset list
로 재사용할 기존 skill/agent 가 있는지 확인한다. 적합한 게 있으면 그것을 안내하고, 정말 새 역량이
필요할 때만 생성을 제안한다(자산 난립 방지).
C (생성)
- 이름 확정(kebab-case·폴더명 일치;
skill list로 충돌 확인, 충돌 시 대안 제시). - scaffold —
solosquad skill new <name>로.solosquad/skills/<name>/SKILL.md골격 생성(무-LLM). 2.5. 초안-앵커 인터뷰(암묵지 추출 — primitive-core §2) — Chief 의[creation_case:N]로 mode 결정. 매니저가 초안을 깔고 빈 클러스터(trigger·procedure(습관적 절차)·gotchas(피하려 배운 실수)· I/O·non-goal·verification(됐는지 판단 기준)·bundle·shape)를 enumerable 질문으로 채운다. 마이그레이션 (⑵)이면 기존 SKILL.md 를 역공학해 코드에 없는 판단·예외를 끌어낸다. - description 먼저 —
primitive-core.md§3.2 공식으로 작성. 이게 가장 중요하니 여기 시간을 쓴다. - 본문 작성(대화) —
primitive-core.md§3.4 의 명명 패턴에서 필요한 것만 골라 채운다. 번들이 필요하면primitive-core.md§3.5 로 scripts/references/assets 를 구분해 둔다. 안티-시코펀시: 최소 2개 접근 비교 후 추천. - eval 설계 —
eval-recipe.md§1 로 description 트리거 셋(20쿼리)을, 검증가능 output 이면 §2 A/B 를 둔다. - 검토·검증 —
primitive-review로 품질 검토 후solosquad skill validate게이트 통과 확인.
What ships with it
2 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.
- 6d ago First seen · 80 lines · 184 tokens per session scan A 8f6da790147a
skill-manager is a skill published in the GitHub repository Adelie-Squad/solosquad (19 stars, last pushed 15d ago), licensed MIT. It adds 184 tokens to every session and 1,842 once invoked, about $0.0009 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…
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…
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…
sector-rotation
Identify which market sectors to overweight or underweight based on current macro conditions and sector performance data.
trend-analysis
Analyze price and volume trends for one or more stocks to determine momentum direction and key technical levels.
persistent-notes
Save notes locally to /mnt/workspace/notes.json file. Use when user wants to "save a note" or "remember something".