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-slack-formatgit 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-slack-format)<a href="https://agentmods.dev/skills/b3rys/b3rys-team-os/b3os-slack-format"><img src="https://agentmods.dev/badge/skills/b3rys/b3rys-team-os/b3os-slack-format/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-slack-format"><img src="https://agentmods.dev/badge/skills/b3rys/b3rys-team-os/b3os-slack-format.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 Data Exfiltration · line 62 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00135 | $0.01786 |
| Opus 5 | $0.00068 | $0.00893 |
| Sonnet 5 | $0.00027 | $0.00357 |
| Haiku 4.5 | $0.00014 | $0.00179 |
Grade A, and why
b3os-slack-format scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST http://127.0.0.1:7878/team/api/slack/post \ How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
b3os-slack-format — 슬랙 메시지 포맷
언제 작동? (트리거 규율)
- 슬랙에 길거나 단계가 있는 메시지(실행 절차·검증·인수인계·보고·체크리스트)를 올리기 직전.
- "슬랙 포맷 해줘 / 정리해서 슬랙에 / slack 메시지 다듬어".
- 단발 한 줄 채팅·텔레그램은 대상 아님(슬랙 게시물 전용). 보고서는
b3os-report, 슬라이드는b3rys-make-ppt.
왜? (the team lead 2026-06-25)
팀원이 슬랙에 평문(plain text)으로 길게 올리면 읽기 나쁘다. 슬랙은 마크다운과 문법이 달라서 **볼드**·## 헤더가 그대로 노출된다. 이 스킬로 Slack mrkdwn + 운영 보고 구조를 입혀 일관되게 읽히게 한다.
Slack mrkdwn 핵심 (마크다운과 다름 — 꼭 기억)
- 볼드 =
*text*(별 1개.**text**아님) - 이탤릭 =
_text_· 취소선 =~text~ - 헤더(
#,##) 없음 →*볼드 줄*로 섹션 제목 - 불릿 =
•(-/*를•로) - 링크 =
<url|텍스트>([텍스트](url)아님) - 코드
`x`/ 코드블록```x```은 그대로 - 줄바꿈은 실제 개행(
\n). 섹션 사이 빈 줄로 숨 쉬게.
일반 메시지 포맷 (briefing agent 스타일 — 읽기 좋은 기본)
briefing-agent 스타일처럼 가볍고 읽히는 일반 메시지 패턴. Block Kit 컬러바 없이 mrkdwn만으로 충분히 깔끔:
*제목*(또는*01. 섹션*) — 볼드 헤더로 구분> 핵심 한 줄— 인용 블록(슬랙이 왼쪽 세로 바로 강조 — briefing agent의 그 바 느낌)• 불릿— 핵심만 짧게*라벨:* 내용— 'the team lead 관점:' 같은 볼드 라벨 + 설명`용어`/`명령`— 인라인 코드(주황 하이라이트)- 섹션 사이 빈 줄로 숨 쉬게
→ md-to-slack.py 가
##→*볼드*,>유지,-→•,**→*, 코드 보존을 전부 처리하므로 마크다운으로 쓰고 변환만 하면 이 모양이 나온다. (briefing agent의 섹션별 컬러 세로바·"자세히 표시" 접기는 Slack Block Kit/attachment(color) 가 필요 — 리치 버전은 별도 옵션. 일반 메시지엔 위 mrkdwn>·볼드로 충분.)
운영 보고 구조 (길거나 단계 있는 메시지)
단순 "예쁘게"가 아니라 검증 가능한 형태로. 권장 골격:
*[제목]* — 무엇을 하는지 1줄
*목적:* 왜 하는지 1~2줄
*절차:*
• 1단계 …
• 2단계 …
*통과 기준:* 무엇이면 OK
*실패 시:* 단계·증상·다음 액션
*owner:* 담당자 · *ETA:* 예상 완료 · *근거:* evidence(있으면)
- 단계는 번호/불릿으로 끊어 한 줄씩. 코드·명령은 코드블록.
- 짧은 메시지는 골격 강요하지 말고 mrkdwn(볼드·불릿)만 입혀도 됨.
사용법 (다듬기 → 변환 → 게시)
- 한국어 윤문 패스(선택): 길거나 공유·게시용 본문은 게시 전에 번역투·기계적 병렬·영어 라벨 남발을 줄인다. 단 긴급·짧은 ack·기계 출력·로그 원문은 예외. 산문을 다듬는 단계이므로 아래 mrkdwn 변환 전에 한다.
★
humanize-korean스킬은 이 저장소에 포함되어 있지 않고install.sh가 설치하지도 않는다★(외부 스킬 — MIT, 원저자 epoko77-ai). 이미 설치해 둔 사람만 그 스킬로 돌리고, 없으면 이 단계는 직접 읽어보며 다듬는 것으로 갈음한다. 이 단계가 없다고 게시가 막히지는 않는다. - 마크다운/평문으로 내용 작성(+0의 윤문 결과) → 변환:
python3 skills/b3os-slack-format/scripts/md-to-slack.py <input.md> # 또는 stdin
(**볼드**→*볼드*, ##헤더→*헤더*, -불릿→•, [텍스트](url)→<url|텍스트>, 코드/코드블록 보존)
2) 변환 결과를 슬랙에 게시:
curl -s -X POST http://127.0.0.1:7878/team/api/slack/post \
-H "Content-Type: application/json" \
-d "$(python3 -c 'import json,sys;print(json.dumps({"agent_id":"<나>","channel":"<채널>","text":sys.stdin.read()}))' < slack.txt)"
(스레드 댓글이면 body 에 "thread_ts":"<부모 ts>" 추가)
What ships with it
8 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 · 83 lines · 135 tokens per session scan A 94d69ff1217b
b3os-slack-format is a skill published in the GitHub repository b3rys/b3rys-team-os (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 135 tokens to every session and 1,786 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
skill-creator
Generates Anthropic Skills with complete workflow including GitHub PR creation and local download verification.
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.
Research Synthesis Workflow
A step-by-step guide to synthesizing research from multiple sources into a coherent summary.