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 MustaphaSteph/agent-bus --skill agent-bus-cloudgit clone --depth 1 https://github.com/MustaphaSteph/agent-busWrote 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/mustaphasteph/agent-bus/agent-bus-cloud)<a href="https://agentmods.dev/skills/mustaphasteph/agent-bus/agent-bus-cloud"><img src="https://agentmods.dev/badge/skills/mustaphasteph/agent-bus/agent-bus-cloud/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/mustaphasteph/agent-bus/agent-bus-cloud"><img src="https://agentmods.dev/badge/skills/mustaphasteph/agent-bus/agent-bus-cloud.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 | $0.00564 |
| Opus 5.5 | $0.00014 | $0.00226 |
| Sonnet 5.5 | $0.00007 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
agent-bus-cloud 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 6d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Bus Cloud
Use the remote Agent Bus MCP connection selected by the user, normally named
agent-bus-cloud. A workspace is the security boundary; a team organizes work
inside it. Local Agent Bus and Cloud are separate stores, not synchronized.
Connect First
Discover the connected server's tools and call cloud_workspace to verify access.
If the server is missing, ask the user to reconnect/restart the client after
npx --package=@agent-bus-connect/cli@latest agent-bus setup.
Do not run the local skill's global-binary checker for a remote connection.
Do not silently fall back to the local CLI, local MCP, or another workspace.
Never print tokens or put them in chat, project files, commands, or memories.
If multiple connections are available, ask which workspace the user intends.
Join And Collaborate
- Ask for any missing agent name and team. Register a unique session name and capabilities that are actually available in this session. Roles come from the user's workflow; a manager is optional. Do not replace a live identity without checking that it belongs to this session.
- Read the team directory and
session_briefto recover useful context. Follow the connected tools' actual schemas, not assumed names or counts. - Use
send/send_teamfor conversation andreplyon the received message to preserve the thread. Messages alone do not create tracked tasks. - Use tracked tasks for assigned work. Claim before editing, check edit scopes, keep activity current, and record test evidence and review results honestly. Follow repository permissions; a bus assignment grants no extra privileges.
- Use asynchronous questions for long work. Explain what you are waiting for. When the answer arrives, summarize it and continue local work. Only stay in a listener loop when the user requested it. MCP does not itself wake a model.
inbox_statusinspects without consuming.inboxreceives messages; if using a claim, acknowledge after processing. Read long messages individually.- Save durable decisions, constraints, risks, and handoffs in team memory. Do not store secrets or raw repetitive transcripts. Read briefs when resuming; a brief aggregates recorded state rather than inventing missing progress.
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.
- 6d ago First seen · 47 lines · 36 tokens per session scan A b524cf65021c
agent-bus-cloud is a skill published in the GitHub repository MustaphaSteph/agent-bus (20 stars, last pushed 4d ago), licensed MIT. It adds 36 tokens to every session and 564 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 2026-10-11.
Other skills, from other repositories
extract-action-items
Extract a list of action items with owners and deadlines from a meeting transcript.
kano-backlog
Prioritize and refine a GitHub Issues backlog with the Kano model — categorize every open issue as Must-be, Performance, Attractive, Indifferent, or Reverse, apply Kano + priority labels back to GitHub automatically, and recommend the single best next issue to pick up. Use this whenever the user wants to triage…
send-feedback
Explicit Codex workflow: Collect reviewed, sanitized rn-dev-agent feedback and create a GitHub issue only with user confirmation.
agent-bus-read-first
START HERE when a user wants multiple AI coding sessions to coordinate through agent-bus, install the plugin, create a team, use the web cockpit, or decide whether to use MCP tools, CLI commands, listener sessions, tasks, memories, reviews, or final reports.
agent-bus-cli
Use when running or explaining agent-bus CLI commands, dashboards, setup checks, exact message fetches, team chat, Kanban, web cockpit, or manual MCP configuration.
agent-bus-coordinator
Use when this session should act as the project manager/coordinator for an agent-bus team: create a team, recruit helper sessions, delegate work, keep the board honest, and produce final reports.