Agent skill

Multi Agent Room

Orchestrate a team of named subagents in shared threads. An agent skill from Goldziher/basemind.

Install Multi Agent Room

skills CLI

$ npx skills add Goldziher/basemind --skill multi-agent-room -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install Goldziher/basemind multi-agent-room --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/Goldziher/basemind.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/multi-agent-room .claude/skills/multi-agent-room && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "multi-agent-room" agent skill from https://github.com/Goldziher/basemind/tree/main/skills/multi-agent-room into .claude/skills/multi-agent-room/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multi-agent-room", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/Goldziher/basemind/tree/main/skills/multi-agent-room

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add Goldziher/basemind --skill multi-agent-room -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install Goldziher/basemind multi-agent-room --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Goldziher/basemind.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/multi-agent-room .agents/skills/multi-agent-room && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "multi-agent-room" agent skill from https://github.com/Goldziher/basemind/tree/main/skills/multi-agent-room into .agents/skills/multi-agent-room/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multi-agent-room", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add Goldziher/basemind --skill multi-agent-room -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install Goldziher/basemind multi-agent-room --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Goldziher/basemind.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/multi-agent-room .cursor/skills/multi-agent-room && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "multi-agent-room" agent skill from https://github.com/Goldziher/basemind/tree/main/skills/multi-agent-room into .cursor/skills/multi-agent-room/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multi-agent-room", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/Goldziher/basemind.git --path skills/multi-agent-room

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add Goldziher/basemind --skill multi-agent-room -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install Goldziher/basemind multi-agent-room --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Goldziher/basemind.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/multi-agent-room .gemini/skills/multi-agent-room && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "multi-agent-room" agent skill from https://github.com/Goldziher/basemind/tree/main/skills/multi-agent-room into .gemini/skills/multi-agent-room/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multi-agent-room", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install Goldziher/basemind multi-agent-room

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add Goldziher/basemind --skill multi-agent-room -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/Goldziher/basemind.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/multi-agent-room .github/skills/multi-agent-room && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "multi-agent-room" agent skill from https://github.com/Goldziher/basemind/tree/main/skills/multi-agent-room into .github/skills/multi-agent-room/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multi-agent-room", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add Goldziher/basemind --skill multi-agent-room -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install Goldziher/basemind multi-agent-room --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Goldziher/basemind.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/multi-agent-room .opencode/skills/multi-agent-room && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "multi-agent-room" agent skill from https://github.com/Goldziher/basemind/tree/main/skills/multi-agent-room into .opencode/skills/multi-agent-room/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multi-agent-room", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: multi-agent-room
GitHub stars: 108
Token cost: ~1.8k tokens
SKILL.md length: 611 words
Files: 1
Skills in repo: 10
Repo updated: Oct 8, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Orchestrate a team of named subagents in shared threads. An agent skill from Goldziher/basemind.

Works in 3 steps: Start a thread and name its members. A… → Assign each subagent a short name. Pass… → Distribute the subagent contract. Each…
Tasks that involve Subagents
SKILL.md covers When to use it, Setup, Broadcast vs targeted hand-off and Reading and synthesis, plus 3 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Multi Agent Room is an agent skill from Goldziher/basemind. Orchestrate a team of named subagents in shared threads. One orchestrator drives multiple peers with distinct identities; each subagent sees its own inbox and can cross-check findings by posting to a thread the peer is a member of.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Subagents, Multi-agent orchestration and Email management. The repository describes itself as: Full AI context and content layer for coding agents over one MCP server — tree-sitter code-map, document RAG, shared memory, multi-agent comms, web crawl, git history + blame… The licence is MIT.

When your agent uses it

Tasks that involve Subagents
Tasks that involve Multi-agent orchestration
Tasks that involve Email management

Example prompts

“/multi-agent-room”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

Start a thread and name its members. A thread is addressed by at least two of three
Assign each subagent a short name. Pass as_agent to every tool call the subagent makes.
Distribute the subagent contract. Each subagent's prompt should include

What it can do on your machine

Read from SKILL.md and the folder at commit 2f6da31. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Multi Agent Room loads about 1.8k tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 611 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~62
When it runs · the whole SKILL.md, loaded when a task matches: ~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Goldziher/basemind at commit 2f6da31, republished under its MIT licence (© Goldziher). 611 words, ~1,776 tokens.

Download SKILL.mdSave it as .claude/skills/multi-agent-room/SKILL.md (or your agent's skills folder).

name: multi-agent-room
description: Orchestrate a team of named subagents in shared threads. One orchestrator drives multiple peers with distinct identities; each subagent sees its own inbox and can cross-check findings by posting to a thread the peer is a member of.

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

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.
text
```
agents {mode: "thread_start", subject: "review-pr-42", members: ["security", "perf"]}
```
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.
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.
Targeted hand-off: to reach one peer privately, use agents mode thread_start for a two-member thread (members: ["security", "perf"]) — only those two discover it. Use for:
- Asking a peer to cross-check your finding.
- Sharing a detail not ready for the whole team.
- Hand-off: "I found X; can you validate my approach?".

Show full SKILL.md (274 more words)Show less

Reading and synthesis

As the orchestrator:

Let all subagents post to their threads (in parallel).
Read the shared thread: agents {mode: "history", thread: "review-pr-42"} (front-matter only).
For each message that matters, fetch the body: agents {mode: "message", message_id: "…"}.
Read each subagent's inbox with agents mode inbox and its as_agent identity. (Messages appear as front-matter; bodies come from mode message.)
Synthesize: combine the findings into a verdict, decision, or report.

Example: two-agent security + performance cross-check

Orchestrator setup:

text

agents {mode: "thread_start", subject: "review-auth-pr", members: ["security", "perf"]}

# Spawn agent "security"
# Prompt: "You are agent 'security' on thread 'review-auth-pr'. Register yourself,
# join the thread, analyze the diff for auth bugs, post findings, and start a
# two-member thread with 'perf' asking them to check your fix's perf implications."

# Spawn agent "perf"
# Prompt: "You are agent 'perf' on thread 'review-auth-pr'. Register yourself,
# join the thread, analyze the diff for performance regressions, post findings, and
# reply to 'security' with your take on their auth fix."

Agent "security" steps:

text

agents {
  mode: "register", as_agent: "security", name: "Security Reviewer", description: "Auth auditor"
}
agents {mode: "join", thread: "review-auth-pr", as_agent: "security"}
agents {
  mode: "post", thread: "review-auth-pr", as_agent: "security", subject: "SQL injection check",
  body: "Parameter X is quoted..."
}
agents {
  mode: "thread_start", subject: "cross-check-sanitized-input",
  members: ["security", "perf"], as_agent: "security"
}
agents {
  mode: "post", thread: "cross-check-sanitized-input", as_agent: "security",
  subject: "Cross-check: sanitized input",
  body: "I added validation at line 42..."
}
agents {mode: "inbox", as_agent: "security", mark_read: true}  # See perf's response

Agent "perf" steps:

text

agents {
  mode: "register", as_agent: "perf", name: "Performance Reviewer", description: "Latency auditor"
}
agents {mode: "join", thread: "review-auth-pr", as_agent: "perf"}
agents {
  mode: "post", thread: "review-auth-pr", as_agent: "perf", subject: "Cache impact check",
  body: "New validation adds ~2ms..."
}
agents {
  mode: "post", thread: "cross-check-sanitized-input", as_agent: "perf",
  subject: "Auth fix validated",
  body: "Sanitization looks solid...", reply_to: "msg-sec-2"
}

Orchestrator synthesis:

text

agents {mode: "history", thread: "review-auth-pr"}  # See front matter
agents {mode: "message", message_id: "msg-sec-1"}  # Get security's body
agents {mode: "message", message_id: "msg-perf-1"}  # Get perf's body
agents {mode: "history", thread: "cross-check-sanitized-input"}
agents {mode: "message", message_id: "msg-perf-2"}  # Get perf's hand-off body
# Synthesize: "Security + perf sign off. Ready to merge."

Recency and thread freshness

Reads default to RECENT so stale chatter never confuses an agent:

agents modes history / inbox return only the last 24 hours by default. Pass since_hours: N for a wider window, or since_hours: 0 for the full append-only log. Nothing is ever deleted — older history stays reachable explicitly.
Every front-matter row carries age_secs (seconds since the message was posted) so you can gauge staleness without converting timestamps yourself.
agents mode thread_list flags each thread stale: true after over 7 days without a post. The CLI renders this as an ACTIVE / STALE marker per thread. Idle threads auto-archive; skip stale ones unless you are intentionally reviewing old context.

Notes

A named member must join with agents mode join (or be added with add_member) before posting.
A private two-member thread reaches exactly one peer — only its members discover it.
Front-matter-only reads (history, inbox) are cheap. Fetch bodies only when needed.
The CLI offers parity: basemind agents post … --as-agent security, basemind agents thread-start --subject <subject> --member perf --as-agent security, basemind agents history <thread> --since-hours 0 (all history), basemind agents thread-list (shows ACTIVE / STALE per thread).

Files

Just SKILL.md in skills/multi-agent-room of Goldziher/basemind.

Open the folder on GitHubat commit 2f6da31

Compare with similar skills

Multi Agent Room next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Multi Agent Room compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Multi Agent Room this skillGoldziher/basemind	108	—	~1.8k	Automated safety check: Pass	MIT	yesterday
Clawteamwin4r/ClawTeam-OpenClaw	1.5k	—	~3.1k	Automated safety check: Pass	MIT	3 mo ago
Paseo Advisor Second Opiniongetpaseo/paseo	20k	1 repos	~756	Automated safety check: Pass	Custom licence	today
O2 Review Loopopenobserve/openobserve	22k	—	~3.7k	Automated safety check: Pass	AGPL-3.0	today
Harness Agent Team Designerrevfactory/harness	9.1k	—	~4.5k	Automated safety check: Pass	Apache-2.0	11 days ago
ClawTeam Multi-Agent Swarmwin4r/ClawTeam-OpenClaw	1.5k	1 repos	~2.9k	Automated safety check: Pass	MIT	3 mo ago

Similar skills

Clawteam
win4r/ClawTeam-OpenClaw
Multi-agent swarm orchestration. An agent skill from win4r/ClawTeam-OpenClaw.
1.5k GitHub stars~3.1k tokensUpdated 3 mo ago
Agent WorkflowsAuto-check passed
Paseo Advisor Second Opinion
getpaseo/paseo
Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.
20k GitHub starsUsed in 1 repo~756 tokens
Agent WorkflowsAuto-check passed
O2 Review Loop
openobserve/openobserve
Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.
22k GitHub stars~3.7k tokensUpdated today
Agent WorkflowsAuto-check passed
Harness Agent Team Designer
revfactory/harness
Designs a project-specific agent harness: defines specialist agents, writes the skills they follow, picks an execution mode and model for each, and keeps the setup maintained.
9.1k GitHub stars~4.5k tokensUpdated 11 days ago
Agent WorkflowsAuto-check passed
ClawTeam Multi-Agent Swarm
win4r/ClawTeam-OpenClaw
Launches a swarm of specialist Hermes agents in git-worktree-isolated tmux windows with a kanban board and file-based inboxes, using built-in templates like hedge-fund and code-review.
1.5k GitHub starsUsed in 1 repo~2.9k tokens
Agent WorkflowsAuto-check passed
Sub-Agent Delegation
codewhale-hq/Codewhale
Guides when and how to split multi-step coding, research or verification work into focused sub-agent runs while the parent keeps integration and final checks.
41k GitHub stars~790 tokensUpdated today
Agent WorkflowsAuto-check passed

More from Goldziher/basemind

All 10 skills in this repo

Basemind Usage Stats
Goldziher/basemind
Shows a markdown dashboard of basemind activity in the session: tool call counts, top operations and estimated tokens saved against a grep and Read baseline.
108 GitHub stars~558 tokensUpdated yesterday
Auto-check passed
Basemind Code Context
Goldziher/basemind
Answers structural questions about a repository, such as where a symbol is defined, what calls it and what changed recently, through the basemind MCP server.
108 GitHub stars~2.6k tokensUpdated yesterday
Auto-check passed
Basemind Index Scan
Goldziher/basemind
Builds or refreshes the basemind code index from the command line, for when basemind reports no index or its MCP server is not running.
108 GitHub stars~997 tokensUpdated yesterday
Auto-check: warnings
basemind CLI Codebase Navigator
Goldziher/basemind
Drives the basemind code-intelligence tool from the command line for symbol search, callers, git history and blame, document search and web crawling, sharing its cache with the MCP server.
108 GitHub stars~2k tokensUpdated yesterday
Auto-check passed
Basemind Code Search
Goldziher/basemind
Answers where code is defined, who calls it and what shape a file has from a pre-built index, returning paths and line numbers instead of file contents.
108 GitHub stars~1.3k tokensUpdated yesterday
Auto-check passed
Basemind Doctor
Goldziher/basemind
Diagnose and recover basemind when it isn't working — MCP tools missing or erroring, "no index" / "no indexed files", empty results that shouldn't be empty, or the MCP server seems dead.
108 GitHub stars~1.1k tokensUpdated yesterday
Auto-check passed

Questions about Multi Agent Room

What does Multi Agent Room do?

Orchestrate a team of named subagents in shared threads. An agent skill from Goldziher/basemind. Multi Agent Room is an agent skill from Goldziher/basemind. Orchestrate a team of named subagents in shared threads.

When should I use Multi Agent Room?

Multi Agent Room fits situations like: tasks that involve Subagents; tasks that involve Multi-agent orchestration; tasks that involve Email management.

How do I install Multi Agent Room in Claude Code?

Run `npx skills add Goldziher/basemind --skill multi-agent-room -a claude-code`. Or copy the skill folder (skills/multi-agent-room in Goldziher/basemind) into .claude/skills/multi-agent-room in your project. Claude Code loads it when a task matches its description.

How do I install Multi Agent Room in Codex?

Run `npx skills add Goldziher/basemind --skill multi-agent-room -a codex`. Or copy the skill folder (skills/multi-agent-room in Goldziher/basemind) into .agents/skills/multi-agent-room in your project. Codex loads it when a task matches its description.

Can I use Multi Agent Room in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Goldziher/basemind --skill multi-agent-room -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/multi-agent-room, .gemini/skills/multi-agent-room, .github/skills/multi-agent-room and .opencode/skills/multi-agent-room in your project.

What does Multi Agent Room need to run?

SKILL.md names no scripts, command-line tools or credentials: Multi Agent Room is instructions for the agent only.

Does Multi Agent Room access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Multi Agent Room safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Multi Agent Room use?

Multi Agent Room is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Multi Agent Room use?

About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Multi Agent Room?

Skills that share tags, products or a category with Multi Agent Room: Clawteam (win4r/ClawTeam-OpenClaw, 1.5k stars), Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars), O2 Review Loop (openobserve/openobserve, 22k stars) and Harness Agent Team Designer (revfactory/harness, 9.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Multi Agent Room?

Goldziher (a GitHub user) maintains it in Goldziher/basemind, which has 108 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 8, 2026.

Source: Goldziher/basemind on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Multi Agent Room

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Multi-agent thread orchestration

When to use it

Setup

Broadcast vs targeted hand-off

Reading and synthesis

Example: two-agent security + performance cross-check

Recency and thread freshness

Notes

Files

Compare with similar skills

Similar skills

More from Goldziher/basemind

Related

Questions about Multi Agent Room