multi-agent-room

multi-agent-room is a skill for Claude Code from Goldziher/basemind. It costs 51 tokens per session (1,833 once invoked), scanned A, original, MIT.

A coordination setup for several named coding agents working in shared discussion threads. Each agent has its own identity and inbox, while an orchestrator manages the group.

In plain words
What is it for?
Use it for code reviews, audits, independent investigations, peer verification, and other tasks where multiple agents need to see and build on one another’s work.
Why use it?
It keeps parallel work, handoffs, and cross-checks in one shared history instead of scattering findings across separate agent sessions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the basemind plugin — 15 skills, 10 commands, 6 agents, 2 hooks, 1 MCP server shipped together

Good fit Use it for code reviews, audits, independent investigations, peer verification, and other tasks where multiple agents need to see and build on one another’s work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/goldziher/basemind/multi-agent-room
Install

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.

Any agent
npx skills add Goldziher/basemind --skill multi-agent-room
Clone the repo
git clone --depth 1 https://github.com/Goldziher/basemind

Made for: Claude Code.

Or install basemind, the plugin that ships this one along with the rest of its 15 skills, 10 commands, 6 agents, 2 hooks, 1 MCP server.

Wrote 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.

agentmods badge for multi-agent-room

README.md
[![agentmods](https://agentmods.dev/badge/skills/goldziher/basemind/multi-agent-room.svg)](https://agentmods.dev/skills/goldziher/basemind/multi-agent-room)
Your own site
<a href="https://agentmods.dev/skills/goldziher/basemind/multi-agent-room"><img src="https://agentmods.dev/badge/skills/goldziher/basemind/multi-agent-room.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,833 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.01833
Opus 5 $0.00026 $0.00916
Sonnet 5 $0.00010 $0.00367
Haiku 4.5 $0.00005 $0.00183

Measured 7d ago against content hash d1cba8de02d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

multi-agent-room 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 7d 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.

.codex-plugin/skills/multi-agent-room/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-agent thread orchestration

Run a team of NAMED subagents that coordinate in shared THREADS, all driven by one orchestrator. Each subagent has its own identity and inbox, and posts to threads the relevant peers are members of.

When to use it

Orchestrate subagents when:

  • Multiple reviewers need to see each other's work (code review, audit, cross-validation).
  • A subagent should hand off findings to a peer for verification.
  • The team needs a shared narrative (all readable in one thread history).
  • You want to parallelize independent work (each agent runs concurrently) and then synthesize.

Setup

  1. Start a thread and name its members. A thread is addressed by at least two of three coordinates — {subject, path-glob, members}. For a private team, list the members explicitly so only they see it; discovery is scoped, never global, so unrelated agents never surface it.

    agents {mode: "thread_start", subject: "review-pr-42", members: ["security", "perf"]}
    
  2. Assign each subagent a short name. Pass as_agent to every tool call the subagent makes. Names like "security", "perf", "correctness" are clearer than defaults. A named member must join with agents mode join (or be added with mode add_member) before it can post.

  3. Distribute the subagent contract. Each subagent's prompt should include:

    • Its assigned as_agent name (e.g. "security").
    • The shared thread's subject (e.g. "review-pr-42").
    • Instructions to:
      • Call agents {mode: "register", as_agent: "security", name: "Security Reviewer", …} once.
      • Call agents {mode: "join", thread: "review-pr-42", as_agent: "security"} to participate.
      • Call agents mode post with as_agent: "security" to share findings.
      • Call agents mode inbox with as_agent: "security" to see addressed messages.

Broadcast vs targeted hand-off

  • Thread post (agents mode post + as_agent): everyone on the thread sees it. Use for:
    • Announcing a finding the whole team should see.
    • Replying to a peer's discovery (reply_to: <id> keeps it linked).
    • Summarizing your work.

Read the full file on GitHub · 163 lines

Changes

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.

  1. 7d ago First seen · 163 lines · 51 tokens per session scan A d1cba8de02d9

Subscribe to this mod's changes

multi-agent-room is a skill published in the GitHub repository Goldziher/basemind (98 stars, last pushed 5d ago), licensed MIT. It adds 51 tokens to every session and 1,833 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

projectatlas

Use ProjectAtlas as the atlas-first orientation layer before broad source reads, with MCP-first task startup, short-alias worktree registration and routing, safe targeted initialization, ranked navigation, exact or federated graph evidence, purpose curation, health, lint, and repository-wide token reporting.

styler-ai/ProjectAtlas · 60 tokens

codex-coding-plugin

Build, review, or fix ProjectAtlas plugin/runtime installer integration for Codex, Claude Code, and OpenCode, especially version convergence, stale ProjectAtlas cache repair, MCP config generation, skill artifacts, host smoke tests, and fake-host tests for ProjectAtlas releases.

styler-ai/ProjectAtlas · 59 tokens

research

Performs deep research on a topic via deepresearch. Simulates a multi-step research process and returns a comprehensive research result as a string.

study8677/repobrain · 32 tokens

lsp-refactor

End-to-end safe refactor workflow — blast-radius analysis, speculative preview, apply to disk, verify build, run affected tests. Inlines lsp-impact + lsp-safe-edit + lsp-verify + lsp-test-correlation into one coordinated sequence.

blackwell-systems/agent-lsp · 57 tokens

trace-mcp-refactoring

Safe refactoring workflow using trace-mcp — assess risk, find candidates, check impact, and rename symbols across all files without missing import sites or cross-file references.

nikolai-vysotskyi/trace-mcp · 39 tokens

lsp-explore

Tell me about this symbol": hover + implementations + call hierarchy + references in one pass — for navigating unfamiliar code.

blackwell-systems/agent-lsp · 0 tokens