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 3338902669-ops/agent-orchestra --skill agent-team-osgit clone --depth 1 https://github.com/3338902669-ops/agent-orchestraWrote 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/3338902669-ops/agent-orchestra/agent-team-os)<a href="https://agentmods.dev/skills/3338902669-ops/agent-orchestra/agent-team-os"><img src="https://agentmods.dev/badge/skills/3338902669-ops/agent-orchestra/agent-team-os/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/3338902669-ops/agent-orchestra/agent-team-os"><img src="https://agentmods.dev/badge/skills/3338902669-ops/agent-orchestra/agent-team-os.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 | $0.00148 | $0.01073 |
| Opus 5.5 | $0.00059 | $0.00429 |
| Sonnet 5.5 | $0.00030 | $0.00215 |
| Haiku 4.5 | $0.00015 | $0.00107 |
Grade A, and why
agent-team-os 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Team OS
A complete operating pattern for a small team of AI agents coordinated by one hub, designed so that work is remembered, verifiable, and never silently lost — and so that a human stays in charge of anything irreversible.
The four layers
-
Layered memory — what the team knows. A curated long-term memory file, daily logs, person/group profiles, a temporal knowledge graph, shared rule fragments distributed to every seat, and periodic digests. Each layer has strict rules for what belongs in it. →
references/memory-model.md -
Governance — how the team is allowed to act. One coordinator is the human's single entry point. A roster assigns one owner (single writer) per resource. Cross-agent relays must carry evidence anchors (path / hash / raw output); no artifact = no conclusion. The verifier is never the implementer. Passing a review gate is not delivery: outward or irreversible actions (send, publish, delete, deploy, pay, change settings) need per-item human approval. →
references/governance.md -
Identity mailbox — how seats communicate durably. Every seat has a fixed mail identity. Messages carry ids, threads, delivery receipts, and acknowledgements; landed mail is never lost (store-and-forward). File reservations stop two seats editing the same file. Non-MCP seats use a thin helper script. →
references/comms-mail.md, template:templates/scripts/mail-helper.ps1 -
Event-driven doorbell — how seats hear about new mail in real time. No polling anywhere. A watcher on the mailbox storage fires on writes, consumes durable per-recipient delivery events through persistent cursors, and dispatches each recipient's native wake (CLI round, bridge task, task-card CLI, GUI paste, coordinator marker file). →
references/doorbell-event-driven.md, template:templates/scripts/doorbell.ps1
Modes
- Multi-agent mode — several different agents hold the seats.
- Single-agent mode — one agent runs several sessions, each session plays
one seat with the same roster, mailbox, memory layers, and governance. The
doorbell simplifies to a session-level trigger. Everything else is identical,
so scaling from one agent to many replaces seats, not the system.
→
references/single-agent-mode.md
What ships with it
31 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.
- .gitignore 84 B
- CHANGELOG.md 5.3 KB
- denylist.example.txt 541 B
- LICENSE 11 KB
- NOTICE 153 B
- QUICKSTART.md 4.7 KB
- README.md 4.5 KB
- references/adapters-compatibility.md 8.5 KB
- references/bootstrap-from-zero.md 7.5 KB
- references/comms-mail.md 9.3 KB
- references/doorbell-event-driven.md 12 KB
- references/error-handling.md 7.7 KB
- references/governance.md 6.1 KB
- references/mail-server-interface.md 10 KB
- references/memory-model.md 9.0 KB
- references/single-agent-mode.md 6.2 KB
- references/verification.md 12 KB
- scripts/check.py 44 KB runs code
- templates/commons-fragments/approval-gates.md 959 B
- templates/commons-fragments/evidence-anchors.md 928 B
- templates/commons-fragments/single-writer.md 747 B
- templates/commons-fragments/verifier-independence.md 1012 B
- templates/daily-log.md 1017 B
- templates/group.md 716 B
- templates/MEMORY.md 1.2 KB
- templates/person.md 1009 B
- templates/PLACEHOLDERS.md 4.3 KB
- templates/roster.md 1.9 KB
- templates/scripts/doorbell.ps1 15 KB runs code
- templates/scripts/mail-helper.ps1 3.2 KB runs code
- templates/task-registry.md 1.3 KB
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 First seen · 94 lines · 148 tokens per session scan A 4b6620c8064c
agent-team-os is a skill published in the GitHub repository 3338902669-ops/agent-orchestra (93 stars, last pushed 2d ago), licensed Apache-2.0. It adds 148 tokens to every session and 1,073 once invoked, about $0.0006 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 2026-10-23.
Other skills, from other repositories
memory
Persistent agent memory — store, recall, search across sessions.
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
lore
Curating cross-agent knowledge and institutional memory: extracts patterns from agent journals into METAPATTERNS.md, detects knowledge decay, propagates best practices. Use for memory curation.
squads-learn
Capture learnings after completing work. Use when finishing a task, fixing a bug, discovering a pattern, or learning something worth remembering for future sessions. Helps build institutional memory.
novel-writing-assets
A manager for reusable writing preferences, such as recurring objects, mistaken assumptions, realistic details, pacing, and dialogue style.
agent-engineering-expert
Build LLM agents that use tools safely: tool design, the agent loop, memory, MCP servers, multi-agent orchestration, sandboxing and prompt-injection defence. Use when the user mentions AI agents, tool use or function calling, MCP or Model Context Protocol, autonomous workflows, multi-agent systems, LangChain or…