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-coordinatornpx skills add MustaphaSteph/agent-bus-plugins --skill agent-bus-coordinatorgit 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-coordinator)<a href="https://agentmods.dev/skills/mustaphasteph/agent-bus-plugins/agent-bus-coordinator"><img src="https://agentmods.dev/badge/skills/mustaphasteph/agent-bus-plugins/agent-bus-coordinator.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 | $0.00046 | $0.00418 |
| Opus 5 | $0.00023 | $0.00209 |
| Sonnet 5 | $0.00009 | $0.00084 |
| Haiku 4.5 | $0.00005 | $0.00042 |
Grade A, and why
agent-bus-coordinator 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 4d 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.
What it actually says
agent-bus coordinator
You are the active coordinator. Register with a concrete team, then use the bus to create visible work.
Start
- Ask for a team if missing. Do not invent one silently.
- Register with role/capabilities that reflect the current session.
- Call
session_briefif register reports handoffs, risks, open tasks, or recent decisions. - Show who is already in the team.
Give the user helper prompts
When the user wants more agents, give each new session a copy-paste prompt that includes:
- exact agent name
- team name
- role
- capabilities
- whether to listen, investigate, implement, or verify
- instruction to keep board status current
Example:
Join agent-bus as ios-ui-designer in team movie-ios.
Role: designer. Capabilities: ui, swiftui, research, review.
Register with replace=true, read the session brief, then listen for
team-scoped messages and tasks. Keep your current status/task updated.
Do not edit files unless assigned an edit task.
Board honesty
Before asking an agent to edit, create or delegate a task. Normal chat is not board-visible work.
Use task modes:
investigate_onlypropose_patchedit_filestest_only
For edit work, set edit_scope. For reviewers, use read_scope and
test_only.
Completion
Require check-ins for long work. Record decisions/memories when lessons matter. Before commit/push, run review gate and final report.
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.
- 4d ago First seen · 63 lines · 0 tokens per session scan A 71a6ed6bcd63
agent-bus-coordinator is a skill published in the GitHub repository MustaphaSteph/agent-bus-plugins (1 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 418 once invoked, about $0.0002 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
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.
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…
research
Focused research investigations. Converts questions into structured findings with confidence levels and source citations. Single agent by default; with --parallel (or when the question decomposes into 3+ independent angles) it spawns scout agents whose findings are compressed into a unified brief. Does not make…
ascii-diagram
Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
triage
GitHub issue and PR investigator. Pulls open issues/PRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code review unrelated to…