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 nexus-research-lab/nexus --skill room-playbookgit clone --depth 1 https://github.com/nexus-research-lab/nexusWrote 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/nexus-research-lab/nexus/room-playbook)<a href="https://agentmods.dev/skills/nexus-research-lab/nexus/room-playbook"><img src="https://agentmods.dev/badge/skills/nexus-research-lab/nexus/room-playbook/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/nexus-research-lab/nexus/room-playbook"><img src="https://agentmods.dev/badge/skills/nexus-research-lab/nexus/room-playbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00024 | $0.00408 |
| Opus 5 | $0.00012 | $0.00204 |
| Sonnet 5 | $0.00005 | $0.00082 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
room-playbook 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 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.
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.
What it actually says
Room Collaboration Playbook
Use this playbook for lightweight Room collaboration. The member handling the user request is the coordinator and final publisher; other members contribute or review when invited. A task-specific Room Skill may replace these roles with a more precise workflow.
Rules
- The coordinator states the objective, integrates contributions, resolves disagreements, and publishes the final answer. Contributors return evidence or a concrete result; they do not assume they own final publication.
- Do not leak private-context information into the public feed. For private
collection, use
send_messagewithdestination=current_room,visibility=private, explicit recipients,wake_policy=immediate, andreply_route=private. Setnext_reply_route=publiconly when the coordinator should naturally publish the synthesized result. - Treat public
@memberas conversation wake only. When durable ownership, delivery, dependency, recovery, or acceptance is required, materialize a WorkGraph and useassign_work; finish withsubmit_workandreview_work. - For serial conversation workflows, wake only the next member. For parallel accountable work, create separate Work Items and do not assume completion order.
- The coordinator stops once the objective is satisfied and no member has a new
action. A member woken without a useful contribution emits
<nexus_room_no_reply/>instead of a filler message. - If a member fails, times out, or is unavailable, the coordinator either
continues with available evidence, reassigns managed work through WorkGraph
controls, or reports the concrete blocker. Do not wait indefinitely or use a
raw
@to disguise failed durable responsibility.
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 · 40 lines · 24 tokens per session scan A aaec43bec17c
room-playbook is a skill published in the GitHub repository nexus-research-lab/nexus (145 stars, last pushed today), licensed Apache-2.0. It adds 24 tokens to every session and 408 once invoked, about $0.0001 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
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
agentscope-java
Expert Java developer skill for AgentScope Java framework - a reactive, message-driven multi-agent system built on Project Reactor. Use when working with reactive programming, LLM integration, agent orchestration, multi-agent systems, or when the user mentions AgentScope, ReActAgent, Mono/Flux, Project Reactor, or…
apply-patch
Apply multi-file or tricky edits atomically with git apply instead of many fragile editfile calls. Use when changing several files at once or when editfile fails to match.
git-checkpoint
Use git as a safety net - create a checkpoint commit before risky or large changes and roll back cleanly if a change makes things worse. Use before multi-file refactors.
agent-optimization
Improve an Agent State through versioned scores and score-linked Traces from a frozen Benchmark.
agent-evaluation
Run one specified Test Agent on one specified Benchmark Case exactly once, privately score that execution, and return one protocol result.