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 b3rys/b3rys-team-os --skill b3os-bwfgit clone --depth 1 https://github.com/b3rys/b3rys-team-osWrote 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/b3rys/b3rys-team-os/b3os-bwf)<a href="https://agentmods.dev/skills/b3rys/b3rys-team-os/b3os-bwf"><img src="https://agentmods.dev/badge/skills/b3rys/b3rys-team-os/b3os-bwf/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/b3rys/b3rys-team-os/b3os-bwf"><img src="https://agentmods.dev/badge/skills/b3rys/b3rys-team-os/b3os-bwf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 90 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00193 | $0.02839 |
| Opus 5 | $0.00097 | $0.01419 |
| Sonnet 5 | $0.00039 | $0.00568 |
| Haiku 4.5 | $0.00019 | $0.00284 |
Grade A, and why
b3os-bwf 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
b3os-bwf — 기본 과제 수행 워크플로우 (stage router)
BWF(b3os workflow)는 harness가 아니다. b3rys 팀이 과제를 받아 끝까지 수행하는 기본 흐름이다. harness·multi-ai review·judge panel·적대적 리뷰는 이 흐름의 한 단계에서 고르는 품질방법일 뿐이다. (이 구분을 먼저 박는다 — 과거 "BWF=harness" 오해 방지.)
이 스킬은 얇은 라우터다. 각 단계는 "무엇을·어떻게 고르나"만 짧게 두고, 실제 실행은 하위 스킬을 참조한다(복붙 금지 — 정본은 각 스킬).
한 줄: 실행 과제는 이 6단계로. 작은 일은 가볍게, 큰 일은 풀 루프. 끝나지 않은 일이 조용히 사라지지 않게.
적용 범위(scope guard — 먼저 읽기): BWF는 the team lead 컨펌을 받은 팀 실행 과제·위임 과제에 적용한다. 단순 답변·가벼운 조회·의견·즉시 끝나는 국소 작업에는 풀 절차를 강제하지 않는다 — TEAM-OS §4/§10 "작은 일" 기준대로 thread에 owner·근거만 남기면 충분하다. (이걸 안 박으면 openclaw 런타임에서 작은 질문까지 PM계획→카드로 끌려간다 — cross-runtime review 2026-06-22.)
0. 모드 판단 (시작)
- 턴모드: 한 번 묻고 한 번 답하는 대화·검토. (열린 과제 = 범위·완료기준을 새로 정해야 함 → 계획·확인 먼저, 산출물 생성은 컨펌 후.)
- 주행모드(실행 기본): the team lead 컨펌으로 실행 시작된 과제.
다음 액션·재개 시각·fallback·stop_rule남기고 완료/blocked/컨펌대기까지 들고 감. - 완전자율모드: 기획
검증보고까지 넓게 위임. 범위·권한·stop_rule 더 명확히.
판정: "내가 범위·형식·완료기준을 새로 발명해야 하나?" YES=열린 과제(계획 먼저) / NO=명확한 지시(바로).
1~6. 스테이지 (실행 루프)
1. PM 계획 목표 / 비목표 / 완료기준(rubric)을 먼저. owner 결정.
역할 밖 실행과제면 PM 전환 — 직접 다 하지 말고 적임자에 위임.
★착수(the team lead 컨펌) 즉시 칸반 카드 등록(필수·자동) — 누가 물어서가
아니라 PM 킥오프 기본 스텝. reminder 의존 금지.
2. 팀 배정 owner · ETA · 검증자. handoff = 받는쪽 ack/거절/ETA 확인까지 추적
(보냄 ≠ 수신확인). → b3os-team-inbox(reply.sh·thread.sh)
3. 실행 + 품질 작업모양 → 품질방법 선택(아래 표). 작업크기 게이팅:
턴=솔로 / 주행=limited harness / 완전자율=full harness.
4. 검증 완료기준(rubric) 대조 + 검증증거(테스트·빌드·실측). "됐다" 단정 금지.
중요 릴리즈/공개 = 팀원리뷰 + 하네스 다차원 (TEAM-OS §4, 무조건).
5. 보고 + 카드 the team lead에게 실제 보이는 보고(생성 ≠ 보임) + 칸반 갱신. closure까지 owner가.
→ b3os-task-loop(카드·guard 필드) · b3os-report(보고서)
6. 학습 hook 교훈·재발사례 → learning-loop 입력으로. (합치지 않고 넘김.)
→ b3os-team-learning-loop
작은 일(즉시 끝남)은 1·4·5만 thread에 가볍게. 10분+·handoff·배포·대기/재개가 생기면 카드 + 풀 루프.
★ PM 루프 — status cadence (트리거→액션, 외워서 따라 한다)
PM의 핵심 = 단계마다 상황파악 → the team lead에게 보이는 보고. "보고해라"(추상)로는 안 됨 — 아래 트리거가 오면 반사적으로 1줄 쏜다. (stall의 흔한 이유 = "완료될 때 보고"로 오해해 그냥 기다림.)
What ships with it
4 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 · 117 lines · 193 tokens per session scan A fa28467e013a
b3os-bwf is a skill published in the GitHub repository b3rys/b3rys-team-os (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 193 tokens to every session and 2,839 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.
Other skills, from other repositories
fable-commander
A planning and review workflow in which one model prepares decisions while selected models handle research and execution. It is written for Fable and Claude Code, tools for coordinating multi-step software work.
takt
A workflow engine that runs a task through a sequence of steps defined in a YAML file, using separate coding agents for the work.
company-product-context
Compiles comprehensive company product context from PDF documents, web research, and industry knowledge.
codebase-context-extractor
This skill provides a comprehensive context extraction system for large codebases. It intelligently analyzes code structure, dependencies, and relationships to extract relevant context for understanding, debugging, or modifying code.
skill-creator
Generates Anthropic Skills with complete workflow including GitHub PR creation and local download verification.
Research Synthesis Workflow
A step-by-step guide to synthesizing research from multiple sources into a coherent summary.