agent-bus-collab
Use when the user asks Codex to coordinate with Grok or another local peer agent through Agent Bus MCP, mentions agent-bus, bus topics, readiness handshakes…
Skill by zfifteen
Chalk Labs
Need help deploying agent-bus-collab?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/zfifteen-agent-bus-collab
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agent-bus-collab
What's inside
- Skill name
agent-bus-collab- Description
- Use when the user asks Codex to coordinate with Grok or another local peer agent through Agent Bus MCP, mentions agent-bus, bus topics, readiness handshakes, shared MCP coordination, peer handoffs, or asks to send/read messages through the bus.
- License
- MIT
- Instructions
- 161 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Agent Skills spec issues
- body: contains an absolute path from the author's machine
Files (2)
- SKILL.md
- agent_bus.py · scripts/
SKILL.md (first lines)
# Agent Bus Collab Use this skill when Codex needs to coordinate with Grok or another local agent through Agent Bus MCP. ## Session Persistence When the user invokes this skill, continue using it for the rest of the current session unless the user explicitly turns it off or redirects away from bus coordination. While active: - check the relevant bus topic before making shared-area claims or edits; - post meaningful status, handoffs, and blockers to the bus; - read peer replies from the bus before treating them as durable coordination state; - keep using the repository, not the bus, for durable artifacts. ## Contract Agent Bus is a coordination ledger. The repository remains the source of truth for durable research artifacts, code, evidence, and claims. Use the bus for: - status; - task claims; - handoffs; - objections; - readiness checks; - coordination questions; - paths to repo artifacts. Do not use the bus as the durable location for research evidence, proofs, experiment output, or final reports. Put those in the repo and link the path from the bus. ## Identities Use stable agent names: - Codex: `codex` - Grok: `grok` Runtime and model details belong inside the message body when relevant, not in the bus identity. ## Message Shape Use this lightweight structure unless the message is genuinely tiny: ```markdown agent: codex runtime: Codex Desktop model: GPT-5 ## Status ... ## Claim / Observation ... ## Evidence ... ## Request / Handoff ... ## Boundary ... ``` For questions and replies, use Agent Bus `message_type='question'` and `message_type='answer'` when the tool exposes that field. Use `reply_to` when answering a specific bus message. ## Start Of Session Before claiming or editing work in an active shared area: 1. Resolve or create the relevant topic. 2. Join as `codex`. 3. Replay from sequence 0 or from the last known cursor. 4. Check for recent claims, blockers, or handoffs. 5. Post a short claim/status before making overlapping edits. For the standing readiness topic: ```text topic name: agent-bus-readiness topic id: 2f6aae70cd ``` ## Tool Use Prefer native Agent Bus MCP tools when they are exposed in the current Codex session: - `ping` - `topic_create` - `topic_list` - `topic_resolve` - `topic_join` - `cursor_reset` - `sync` - `topic_presence` - `messages_search` If the native Agent Bus tools are not surfaced but the local server is installed, use the bundled helper script as the explicit transport to the same MCP server. This is not a substitute protocol; it calls the installed Agent Bus MCP server over stdio. Helper: ```bash python /Users/velocityworks/.codex/skills/agent-bus-collab/scripts/agent_bus.py --help ``` The helper uses: ```text uvx --from agent-bus-mcp==0.5.0 agent-bus AGENT_BUS_DB=/Users/velocityworks/.agent_bus/agent_bus.sqlite ``` ## Common Commands Replay a topic: ```bash python /Users/velocityworks/.codex/skills/agent-bus-collab/scripts/agent_bus.py history agent-bus-readiness
From zfifteen/skills-catalog, MIT.
More from zfifteen/skills-catalog
- 0.502score
30-30-30-technical-note
zfifteen
Turn a PGS research finding into a three-layer technical note bundle: (1) Grade-10 plain prose, (2) embedded SVG infographic with concise figures, (3)…
SkillCFreshness: C★ 1Claude Code +9 - 0.501score
aiq-deploy
NVIDIA AI-Q Blueprint Team <aiq-blueprint@nvidia.com>
Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.
SkillCFreshness: C★ 1Claude Code +9 - 0.501score
aiq-research
NVIDIA AI-Q Blueprint Team <aiq-blueprint@nvidia.com>
Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.
SkillCFreshness: C★ 1Claude Code +9 - 0.499score
agent-vision
zfifteen
CRITICAL WHILE ARMED: (1) capture (2) read_file NEW JPEG (3) USE pixels in reasoning (4) turn-gate record + ready.
SkillCFreshness: C★ 1Claude Code +9 - 0.498score
agy-cli-collab
zfifteen
Sticky Grok→Gemini collaboration via direct local Antigravity CLI (`agy`) subprocess calls only.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
airtable-overview
airtable
Explains what Airtable is and how data is structured — bases, tables, fields, records, views, automations, and interfaces.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
actualize
zfifteen
Reduce reasoning friction and produce the most direct, high-fidelity answer or artifact possible.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
airtable-cli
zfifteen
Lists bases, reads and writes records, manages tables and fields, filters and searches data in Airtable via the `airtable-mcp` CLI.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
ai-generation-persistence
zfifteen
AI generation persistence patterns — unique IDs, addressable URLs, database storage, and cost tracking for every LLM generation
SkillCFreshness: C★ 1Claude Code +9 - 0.493score
agents-sdk
zfifteen
Build, run, deploy, and evaluate OpenAI Agents SDK apps from Codex.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
alpha
zfifteen
Alpha fixture skill.
SkillCFreshness: C★ 1Claude Code +9 - 0.472score
airtable-filters
airtable
Use this skill when the user wants to find, filter, or narrow down Airtable records by field values, even when they don't explicitly say "filter."
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Jul 19, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/zfifteen/skills-catalog
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from zfifteen
- 0.502score
30-30-30-technical-note
zfifteen
Turn a PGS research finding into a three-layer technical note bundle: (1) Grade-10 plain prose, (2) embedded SVG infographic with concise figures, (3)…
SkillCFreshness: C★ 1Claude Code +9 - 0.499score
agent-vision
zfifteen
CRITICAL WHILE ARMED: (1) capture (2) read_file NEW JPEG (3) USE pixels in reasoning (4) turn-gate record + ready.
SkillCFreshness: C★ 1Claude Code +9 - 0.498score
agy-cli-collab
zfifteen
Sticky Grok→Gemini collaboration via direct local Antigravity CLI (`agy`) subprocess calls only.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
actualize
zfifteen
Reduce reasoning friction and produce the most direct, high-fidelity answer or artifact possible.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
airtable-cli
zfifteen
Lists bases, reads and writes records, manages tables and fields, filters and searches data in Airtable via the `airtable-mcp` CLI.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
ai-generation-persistence
zfifteen
AI generation persistence patterns — unique IDs, addressable URLs, database storage, and cost tracking for every LLM generation
SkillCFreshness: C★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get agent-bus-collab running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
agent-bus-collab skill. Agent Mart. https://agentmart.dev/skills/zfifteen-agent-bus-collab (last updated 2026-10-24)