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-team-inboxgit 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-team-inbox)<a href="https://agentmods.dev/skills/b3rys/b3rys-team-os/b3os-team-inbox"><img src="https://agentmods.dev/badge/skills/b3rys/b3rys-team-os/b3os-team-inbox/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-team-inbox"><img src="https://agentmods.dev/badge/skills/b3rys/b3rys-team-os/b3os-team-inbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Supply Chain · line 210 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
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 | $0.00152 | $0.04253 |
| Opus 5 | $0.00076 | $0.02126 |
| Sonnet 5 | $0.00030 | $0.00851 |
| Haiku 4.5 | $0.00015 | $0.00425 |
Grade A, and why
b3os-team-inbox 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 11d 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 http://127.0.0.1:7878/team/api/slack/status \ How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
b3os-team-inbox
the team lead AI Team message bus 의 클라이언트 도구.
언제 쓰는가
- 사용자가 Slack/Telegram 으로 thread_id 와 함께 메시지를 보내왔을 때 →
send.sh로 답
★답할 때는 --in-reply-to <그 메시지 id> 를 붙인다.★
그래야 서버가 "이 답이 ★어느 질문★ 에 대한 것인지" 를 안다. 안 붙이면 서버 눈엔 그냥 "누가 뭔가 보냈다" 로만 보이고,
답이 ★엉뚱한 주소로 갔는지조차 알 수 없다 (실측: 답의 3~4할이 이걸 안 달고 와서 관측이 안 됐다).
send.sh --to <물어본 사람> --thread <온 thread> --in-reply-to <그 메시지 id> --body "..."
- inbox 확인 ("새 메시지 있나?") →
inbox.sh - 다른 agent 와 토론 시작 →
send.sh --to <other_agent> --body "..." - 팀장께 최종 보고 →
send.sh --to <요청자> --thread <온 thread> --in-reply-to <그 메시지 id> --direct-to-gd --body "..."★--direct-to-gd는 '★내가★ 하는 최종 보고' 전용이다★ — 서버가 이 봉투의 본문을 팀장 1:1 DM 에 게시한다. ·--to와--in-reply-to가 둘 다 필요하다. 보고는 '받은 요청에 대한 답' 이라서다.--in-reply-to없이 붙이면 서버가 400(protocol_direct_to_gd_on_delegation)으로 거부한다. · 팀원에게 "팀장께 보고해줘" 를 시키는 위임이면 이 플래그를 쓰지 않는다 —--to <팀원>으로 보내고 본문에 그렇게 쓴다. 플래그는 그 팀원이 ★자기 답에★ 붙인다. - 메시지 읽음 처리 →
ack.sh - 팀버스 맥락 조회 ("팀버스 그거 어떻게 됐어?", "GD가 코덱스한테 뭐 시켰어?") →
bus-recall.sh(read-only, team.db 조회. 뒤지기 대신 요점 확인)
서버: http://127.0.0.1:7878/team/api/inbox (loopback).
자기 id 자동 감지
스크립트는 현재 tmux session 이름에서 agent id 를 자동 감지한다.
claude-maintainertmux 안 → agent_id =maintainerclaude-agent-c안 →agent-c- 다른 환경에선
GD_AGENT_ID환경변수 사용 - hermes/openclaw 세션은 tmux 자동감지가 안 된다 → 자기 id 가 필요한 스크립트(
bus-recall.sh등)에는--me <내 agent id>를 붙인다. (예:bus-recall.sh --me ames --with bill) 생략하면 id 미해석 → 결과 0건.
사용 예
inbox 확인
skills/b3os-team-inbox/scripts/inbox.sh
→ 자기 unread 메시지 JSON (id, from, body, thread_id).
메시지 보내기 (DM)
skills/b3os-team-inbox/scripts/send.sh \
--to agent-a \
--body "오늘 작업 분담 어떻게 할까?"
기존 thread 에 응답
skills/b3os-team-inbox/scripts/send.sh \
--to user \
--thread abc12345 \
--in-reply-to msg_id_here \
--body "Slack 에서 받은 질문에 답변..."
Slack 발신 thread 에 응답하면 서버가 자동으로 Slack 채널에 댓글 post.
팀장께 최종 보고하기 — --direct-to-gd
What ships with it
9 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.
- scripts/_me.sh 4.2 KB runs code
- scripts/ack.sh 1.2 KB runs code
- scripts/bus-recall.sh 6.9 KB runs code
- scripts/expect-report.sh 2.1 KB runs code
- scripts/inbox.sh 3.4 KB runs code
- scripts/reply.sh 3.1 KB runs code
- scripts/send.sh 28 KB runs code
- scripts/slack-post.sh 5.9 KB runs code
- scripts/thread.sh 1.7 KB runs code
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.
- 11d ago First seen · 259 lines · 152 tokens per session scan A 4b8fd638baab
b3os-team-inbox is a skill published in the GitHub repository b3rys/b3rys-team-os (13 stars, last pushed today), licensed Apache-2.0. It adds 152 tokens to every session and 4,253 once invoked, about $0.0008 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
orch
AI agent orchestrator — manage teams of AI agents that work on your codebase in parallel. Use when the user wants to: run multiple agents, coordinate AI work, deploy agent teams, manage tasks/goals/agents, check orchestrator status, or mentions 'orch', 'orchestry', 'agents team', 'agent orchestration'.
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.
ai-agent-job-marketplace
The job marketplace where bots hire bots. Post FREE or paid $WAGE jobs, with on-chain escrow, faucet rewards, referrals, judge staking, task inbox, smart matching, checkpoints, oversight, webhooks, onboarding, and human owner dashboard.
agent-freelance-bounty-marketplace
Earn USDC completing bounties, post jobs, join multi-agent raids, build reputation, rank up. AI agent freelance marketplace with x402 escrow on Solana. Free SOL airdrop on signup. Guilds, ranks, vouching, disputes, Castle Town, leaderboard.
agent-job-marketplace-with-bidding
Agent-to-agent marketplace MVP. Agents post jobs, bid, contract, submit deliverables, and leave reviews. Payments are off-platform (crypto) in v1.
dos-dispatch-loop
Run recurring dos-dispatch cycles, switching to dos-replan when the backlog drains and stopping on the kernel's loop verdict. Use for unattended dispatch->replan->dispatch work across disjoint lanes.