A software-development method for turning a growing list of team requests into planned, reviewed, tested, documented, and released work. It describes a project structure with a repository, design notes, task tracking, continuous integration, and agent collaboration.

Use it to start a project, define milestones, organize team work, require review and checks before merging, prepare releases, hand work to others, and record operational feedback.

It reduces lost requirements and unclear ownership by keeping requests traceable from planning through release and follow-up. It is intended for ongoing apps, services, and larger features rather than one-off research or prototypes.

b3os-sf — Skill for Claude Code and Codex by b3rys/b3rys-team-os

Install

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.

Any agent

npx skills add b3rys/b3rys-team-os --skill b3os-sf

Clone the repo

git clone --depth 1 https://github.com/b3rys/b3rys-team-os

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/b3rys/b3rys-team-os/b3os-sf/github.svg)](https://agentmods.dev/skills/b3rys/b3rys-team-os/b3os-sf)

Your own site

<a href="https://agentmods.dev/skills/b3rys/b3rys-team-os/b3os-sf"><img src="https://agentmods.dev/badge/skills/b3rys/b3rys-team-os/b3os-sf/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/b3rys/b3rys-team-os/b3os-sf"><img src="https://agentmods.dev/badge/skills/b3rys/b3rys-team-os/b3os-sf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 164 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,329 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00164	$0.01329
Opus 5.5	$0.00066	$0.00532
Sonnet 5.5	$0.00033	$0.00266
Haiku 4.5	$0.00016	$0.00133

Measured 2d ago against content hash b6c514b2bc5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

b3os-sf 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 2d 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.

skills/b3os-sf/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

b3os SF (Software Factory) — 프로젝트 방법론

목적

SF는 결과물 품질·과제 수행 시간·과제 수행 토큰량을 함께 잰다. RSI(반복적 자기개선)를 위한 환경·프로세스·라이브러리를 구축해 세 지표를 계속 개선한다. 10-05 개발 배포 검사는 19분에서 4분 46초로 줄었다(시간 지표). 측정법: references/knowledge-and-handoff.md

언제 작동?

팀장 요구가 여러 번 쌓이는 앱·서비스·긴 기능과 그 프로젝트의 킥오프, 마일스톤, 배포본 전달, 인계에 쓴다. 단발 리서치·프로토는 b3os-task-loop 카드 하나로 관리한다.

단계 지도

시작 ──> 개발 ──> 출시 ──> 운영
  ^        │        │        │
  └────────┴── 지식 <────────┘

★ 팀장 확인: 첫 기능 목록 · 초기 설계 · 머지 승인 · 실사용 확인.

1. 시작

요구 원문을 목록으로 잡고 바꾸기 비싼 구조만 설계한 뒤, 저장소·문서·지속적 통합(CI)·칸반·에이전트 팀의 최소 뼈대를 만든다. 상세: references/start.md

2. 개발

요청마다 요청 → 만들기 → 검사 → 리뷰 → 머지 승인 → 내보내기 → 보고 → 배우기를 돈다. 구조 가드와 진행 점검은 개발 순환 안에서 함께 적용한다. 상세: references/development.md

개발 속도는 구조화와 변경 영향 범위에 맞춘 검사 단계로 확보한다. 공유 기계에서는 검사 순번과 자동 재검사를 제어하고, 기다리는 동안 헤드리스 작업을 겹쳐 돌린다. 상세: references/dev-mode-operations.md

AI 팀이 기능을 만들 때 지키는 11개 코딩 원칙과 점검법: references/ai-team-coding-guidelines.md

상태 × 입력 조합이 많은 기능(편집기 키 처리, 화면 모드, 동기화 상태)은 처음부터 "판정 함수 하나 + 상태표 + 작은 실행 함수"로 짠다. 고쳤더니 다른 곳이 깨지면 증상을 더 막지 말고 같은 판단을 하는 곳이 몇 군데인지부터 센다. 상태표는 만능이 아니다 — 판정 함수 하나·표 밖 if 금지·칸마다 시험과 함께 써야 효과가 난다. 방법·장단점: b3os-ai-code-safety 의 "상태 × 입력이 많으면 상태표로".

구조 정리(리팩터링)는 신호가 보일 때 앱 전체 지도로 재고, 위험 순으로 옮기고, 래칫으로 지킨다. 구현 첫날부터 지킬 구조 규칙은 시작 단계에 둔다. 상세: references/structure-refactor.md · references/start.md

3. 출시

검사·리뷰를 통과한 산출물만 내보내고, 요구사항별로 자동 시험·앱 화면·못 본 것을 나눠 보고한다. 채널별 형식과 빌드 전달 절차를 따른다. 상세: references/release.md

4. 운영

가용성·성능·오류를 감시하고, 장애는 영향 제한과 복구를 먼저 한 뒤 수정 요청으로 개발 순환에 돌려보낸다. 정비와 사용자 피드백도 같은 순환으로 관리한다. 상세: references/operations.md

5. 지식·종료

TODO·기능·설계·검증 근거를 정본에 갱신하고, 재사용 가능한 교훈을 프로젝트와 팀 지식에 남긴다. 인계와 종료 때 잰 것과 못 잰 것을 구분한다. 상세: references/knowledge-and-handoff.md

Read the full file on GitHub · 66 lines

Files

What ships with it

11 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.

Changes

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.

2d ago Changed · +2 lines b6c514b2bc5d
9d ago Changed · +2 lines 6e0743303599
10d ago Changed · -167 lines 912da6854e4a
11d ago Changed · +11 lines a82db5610dfa
12d ago First seen · 218 lines · 164 tokens per session scan A 874958d8fd24

Subscribe to this mod's changes

b3os-sf is a skill published in the GitHub repository b3rys/b3rys-team-os (14 stars, last pushed yesterday), licensed Apache-2.0. It adds 164 tokens to every session and 1,329 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-10-04.

Claude Code Multi-Agent Planning Project management agent-orchestration ai-agents harness loop-engineering

board

Read and write the workspace BOARD.md (shared task board for agents + Val). Wraps bin/board, a small Python CLI that preserves the markdown schema and appends to the activity log automatically. Use this whenever an agent proposes, claims, or finishes work that should be visible to the rest of the roster.

OpenCoven/coven · 66 tokens

b3os-sf