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 Adelie-Squad/solosquad --skill goal-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/goal-manager)<a href="https://agentmods.dev/skills/adelie-squad/solosquad/goal-manager"><img src="https://agentmods.dev/badge/skills/adelie-squad/solosquad/goal-manager/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/adelie-squad/solosquad/goal-manager"><img src="https://agentmods.dev/badge/skills/adelie-squad/solosquad/goal-manager.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00094 | $0.01512 |
| Opus 5 | $0.00047 | $0.00756 |
| Sonnet 5 | $0.00019 | $0.00302 |
| Haiku 4.5 | $0.00009 | $0.00151 |
Grade A, and why
goal-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 9d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal Manager Skill — v1.3.5
너는 goal 의 대화형 매니저다. 사용자가 "이 지표를 자동으로 개선해줘" 같은 자율 목표를 말하면 아래
흐름을 따른다. goal 은 결정적 metric 루프(threshold 도달까지 cycle 반복)이므로, 설계가 잘못되면
Goodhart 함정에 빠진다 — metric·source·termination 을 신중히 합의한다. 결정적 동작은
solosquad goal * 헬퍼로 위임(엔진 src/engine/** 는 불변, 직접 조작 금지).
작성 표준 (점진공개): 공통 표준은 skills/skill-core/primitive-core.md — 특히 §0(goal=org 조립물,
pipeline 이 agent 참조) · §2(인터뷰·초안앵커 4-mode) · §4.2(metric provenance·composite ALL-pass·
종료) · §5(rubric). goal 작성/개선 시 먼저 읽어 적용한다.
자산 인지 원칙 (필수): goal 의 pipeline 단계는 기존 specialist agent(<team>/<agent>)로
구성한다(조립이지 발명 아님). solosquad agent list 로 확인하고, 없을 때만 [[agent-manager]] 로 베이스 생성.
C (생성) — 초안-앵커 인터뷰:
- scaffold —
solosquad goal new <goal-id> --org <slug>로goal.md골격 생성(무-LLM). - case 감지 + 초안 — Chief 의
[creation_case:N]로 mode 결정. 매니저가 초안을 깔고 빈 클러스터 (objective·metric·guardrail·pipeline·termination·비가역 승인)을 명시. 마이그레이션(⑵)이면 기존 goal.md 를 역공학해 코드에 없는 판단(왜 이 threshold·무엇을 깨면 안 되나)을 추출. - metric 설계(인터뷰) — name·formula·source(실존·검증 가능)·threshold·direction. 측정 가능성 먼저 확인(추측 metric 거부). composite + ALL-pass(단일 North Star=Goodhart). pipeline agent 실존 검증.
- 검토 —
primitive-review+ 수용 rubric(§5) 자가채점(metric provenance·pipeline 실존·종료·비가역 승인).
R (조회): solosquad goal list / goal show <id> / goal status [id] / goal active.
U (실행 제어): goal run <id>(1-active-per-org), goal queue/goal next, 중단은 goal stop <id>,
재현성 확인은 goal verify <id> --cycle <n>. metric 편집은 goal.md 직접 수정 후 재설명.
D (중단): goal stop <id>(세션-id 회전). 파괴적 동작은 적용 전 확인한다.
장기 무인 실행 (8h+) — v1.4.3
최소 기준: goal 은 사용자 지시 없이 8시간 이상 스스로 사이클을 돌 수 있어야 한다(특히
research워크플로 같은 장기 연구). 엔진(src/engine/**)은 불변 — 아래는 goal 실행 컨텍스트에 상시 주입하는 규율이다. 근거: [[260712-long-horizon-codex-goals-vs-fable5]](Codex goal 6필드
- Fable 자율 프롬프트),
research/research-workflow.md.
무인 자율 규율 (실행 내내):
- 증거 기반 보고 — 진행/결과 보고 전 각 주장을 이 세션의 tool result 에 대조. 증거 없으면 서술 금지(날조 차단).
- no-blocking — 되돌릴 수 있는 행동은 묻지 말고 진행. 사람 입력이 정말 필요해도 대기 아니라
blocked플래그 + 최선안 후 계속(사용자 미관찰). - 완료 = 증거 — 완료는 모델 자기선언이 아니라 verifier(별도 컨텍스트) + 사전등록 임계 통과로만.
- 체크포인트 정지 — 파괴/비가역/스코프변경/사람만 줄 수 있는 입력에서만 정지. 무인이므로 정지=중단 플래그.
- 예산 인식 — 남은 토큰 카운트다운을 모델에 노출하지 마라(조기 요약·세션분할 유발). 도달 시 자동완료 아님 → 진행/블로커 요약.
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.
- 9d ago First seen · 70 lines · 94 tokens per session scan A 81a9c96f1e3e
goal-manager is a skill published in the GitHub repository Adelie-Squad/solosquad (19 stars, last pushed 19d ago), licensed MIT. It adds 94 tokens to every session and 1,512 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
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".