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 agentmods add skills/mustaphasteph/agent-bus-plugins/agent-bus-read-firstnpx skills add MustaphaSteph/agent-bus-plugins --skill agent-bus-read-firstgit clone --depth 1 https://github.com/MustaphaSteph/agent-bus-pluginsWrote 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-plugins/agent-bus-read-first)<a href="https://agentmods.dev/skills/mustaphasteph/agent-bus-plugins/agent-bus-read-first"><img src="https://agentmods.dev/badge/skills/mustaphasteph/agent-bus-plugins/agent-bus-read-first.svg" alt="Measured on agentmods" 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 | $0.00060 | $0.00685 |
| Opus 5 | $0.00030 | $0.00342 |
| Sonnet 5 | $0.00012 | $0.00137 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
agent-bus-read-first 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 5d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-bus — read this first
agent-bus is a local SQLite-backed message bus for AI coding sessions on
the same machine. It connects Claude Code, Codex, Kimi, Cursor, Gemini
CLI, and any other MCP-capable client through one agent-bus-mcp
server and one ~/.agent-bus/bus.db database.
Use the canonical /agent-bus skill for the detailed tool contract.
Use this skill to choose the right workflow quickly.
Setup gate
Before doing bus work, verify the CLI/MCP binary exists:
agent-bus doctor
agent-bus --version
which agent-bus-mcp
If missing:
npm i -g @agent-bus-connect/cli@latest
Plugin installs do not run npm scripts. Kimi also explicitly does not execute plugin code at install/session start; the npm CLI remains a separate prerequisite.
Route by user intent
| User intent | Use |
|---|---|
| "Create a team / make agents work together" | /agent-bus-coordinator |
| "This session should wait and answer" | /agent-bus-listener |
| "Which commands do I run?" | /agent-bus-cli |
| "How should we manage tasks/reviews/memory?" | /agent-bus-workflows |
| Any detailed MCP/tool behavior | /agent-bus |
Best default model
Use teams as the work boundary. A team is the room for chat, task boards, memories, and the web cockpit.
Default roles are descriptive, not hard-coded:
pmorcoordinator: plans, delegates, watches board honestydesigner: proposes UI/UX directiondeveloper: implements scoped workverifierorreviewer: tests, reviews, and approveslistener: waits quietly for work
Agents can talk directly without a coordinator, but for serious repo work a coordinator should create/claim tasks before edits start.
MCP vs CLI
Use MCP tools from inside an agent session for live coordination: register, send, ask, delegate, tasks, memories, decisions, reviews.
Use CLI commands for human-visible dashboards and exact inspection:
agent-bus ui
agent-bus team-chat --team <team> --watch
agent-bus kanban --team <team> --watch
agent-bus message <id> --json
agent-bus task-result <id>
agent-bus final-report --team <team>
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.
- 5d ago First seen · 90 lines · 60 tokens per session scan A 8418bfaac5dc
agent-bus-read-first is a skill published in the GitHub repository MustaphaSteph/agent-bus-plugins (1 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 685 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 2026-08-31.
Other skills, from other repositories
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
experiment
Automated optimization loop with scalar fitness function. Proposes changes in isolated worktrees, measures with a metric command, keeps improvements, discards failures. Supports convergence detection and diminishing returns.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.