Borrowing it
Nothing to install: this file belongs to MarkDonish/round-table-workspace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MarkDonish/round-table-workspace/main/.codex/skills/room-skill/SKILL.mdgit clone --depth 1 https://github.com/MarkDonish/round-table-workspaceWrote 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/markdonish/round-table-workspace/room-skill)<a href="https://agentmods.dev/skills/markdonish/round-table-workspace/room-skill"><img src="https://agentmods.dev/badge/skills/markdonish/round-table-workspace/room-skill/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/markdonish/round-table-workspace/room-skill"><img src="https://agentmods.dev/badge/skills/markdonish/round-table-workspace/room-skill.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 | $0.00036 | $0.02173 |
| Opus 5.5 | $0.00014 | $0.00869 |
| Sonnet 5.5 | $0.00007 | $0.00435 |
| Haiku 4.5 | $0.00004 | $0.00217 |
Grade A, and why
room-skill 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 2mo 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/room 房间模式调度 skill
/room 不是新的名人人格，而是状态化多 Agent 房间的上层调度器。
它的职责不是替任何一个 Agent 发言，而是负责：
- 识别
/room相关命令 - 维护
/room的状态边界 - 按协议调用 selection / chat / summary / upgrade prompt
- 确保 orchestrator 是状态唯一写者
- 在成立时把 handoff packet 交给
debate-roundtable-skill
只在显式触发时生效
只有当用户明确进入 /room，或已经处于某个 /room 上下文并继续推进时，才使用本 skill。
允许的显式命令：
/room <topic>/focus <focus text>/summary/upgrade-to-debate/add <agent>/remove <agent>
如果用户没有显式进入 /room：
- 不主动切到
/room - 不把普通对话伪装成房间状态机
- 不覆盖
/debate或单个 skill 的原有行为
Source Of Truth
执行与维护时优先遵循这些仓库内文件：
AGENTS.mddocs/protocol-spec.mddocs/room-runtime-status.mddocs/room-runtime-bridge.mddocs/room-chat-contract.mddocs/agent-registry.mddocs/DECISIONS-LOCKED.mddocs/room-architecture.mddocs/room-selection-policy.mddocs/room-to-debate-handoff.mdschemas/room-session.schema.jsonschemas/room-to-debate-handoff.schema.jsonprompts/room-selection.mdprompts/room-chat.mdprompts/room-summary.mdprompts/room-upgrade.md.codex/skills/room-skill/WORKFLOW.md
路径与环境自包含规范
本 skill 保证 100% 自包含与环境可移植：
- 首选仓库相对路径（如
docs/...、prompts/...、schemas/...） - 规范绝对路径回退（Canonical Absolute Fallback）：当在宿主外部或非仓库根目录下调用时，统一回退解析到
/Users/markdonish/round-table-workspace/（例如/Users/markdonish/round-table-workspace/docs/protocol-spec.md、/Users/markdonish/round-table-workspace/prompts/room-selection.md） - 跨宿主执行时所有引用的 protocol spec、schemas、prompts 均由本仓库完整提供，无需外部未声明依赖。
如历史报告与以上文件冲突，以上文件优先。
运行入口
当 /room 生效时：
- 先读取本文件
- 再读取
.codex/skills/room-skill/WORKFLOW.md - 若需要 checked-in host bridge，使用
.codex/skills/room-skill/runtime/room_runtime.py - 需要命令示例和产物路径时，读取
.codex/skills/room-skill/runtime/README.md - 只在需要解释协议边界时再回到
docs/room-runtime-bridge.md与相关 prompts
WORKFLOW.md 是当前 checked-in 的 runtime playbook。
命令语义
/room <topic>
- 首次进入时：创建房间
- 已有房间上下文时：按宿主行为决定是继续当前房间还是显式新建；如果语义不清，优先保持当前房间，不擅自重置状态
What ships with it
43 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.
- references/current-implementation-boundary.md 1.3 KB
- runtime/agent_consumer_self_check.py 25 KB runs code
- runtime/agent_host_inventory.py 7.6 KB runs code
- runtime/chat_completions_executor.py 10 KB runs code
- runtime/chat_completions_live_validation.py 9.2 KB runs code
- runtime/chat_completions_readiness.py 6.1 KB runs code
- runtime/chat_completions_regression.py 16 KB runs code
- runtime/claude_code_live_validation.py 16 KB runs code
- runtime/development_checkpoint.py 16 KB runs code
- runtime/extract_github_release_body.py 6.3 KB runs code
- runtime/fixtures/canonical/focus_turn.chat.json 1.4 KB
- runtime/fixtures/canonical/focus_turn.selection.json 3.5 KB
- runtime/fixtures/canonical/initial_turn.chat.json 1.5 KB
- runtime/fixtures/canonical/initial_turn.selection.json 3.5 KB
- runtime/fixtures/canonical/room_full.selection.json 4.0 KB
- runtime/fixtures/canonical/summary.json 1.6 KB
- runtime/fixtures/canonical/upgrade.json 3.9 KB
- runtime/generic_agent_adapter_validation.py 7.2 KB runs code
- runtime/generic_agent_executor.py 24 KB runs code
- runtime/generic_agent_json_wrapper_validation.py 4.1 KB runs code
- runtime/generic_agent_json_wrapper.py 11 KB runs code
- runtime/generic_fixture_agent.py 7.2 KB runs code
- runtime/github_release_publication_check.py 44 KB runs code
- runtime/host_recipes_consistency_check.py 4.3 KB runs code
- runtime/live_lane_evidence_report.py 21 KB runs code
- runtime/local_agent_host_validation_matrix.py 19 KB runs code
- runtime/local_codex_cross_machine_validation.py 20 KB runs code
- runtime/local_codex_executor.py 107 KB runs code
- runtime/local_codex_regression.py 24 KB runs code
- runtime/local_codex_second_host_validation.py 20 KB runs code
- runtime/mock_chat_completions_server.py 7.2 KB runs code
- runtime/opencode_agent_wrapper.py 6.7 KB runs code
- runtime/post_release_consumer_audit.py 19 KB runs code
- runtime/README.md 28 KB
- runtime/release_candidate_report.py 13 KB runs code
- runtime/release_readiness_check.py 29 KB runs code
- runtime/room_debate_e2e_validation.py 12 KB runs code
- runtime/room_e2e_validation.py 29 KB runs code
- runtime/room_runtime.py 57 KB runs code
- runtime/secret_redaction.py 353 B runs code
- runtime/source_boundary_audit.py 7.0 KB runs code
- runtime/wrapper_fixture_agent.py 2.7 KB runs code
- WORKFLOW.md 7.7 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.
- 2mo ago First seen · 263 lines · 36 tokens per session scan A 5f73b0750352
room-skill is a skill published in the GitHub repository MarkDonish/round-table-workspace (2 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 2,173 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
requirements-writer
Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies.
refocusing
Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.
orchestration-team
Use when coordinating assignments, selected review boundaries, or blocked work across a rig.
oversight-team
Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn), the intervention…