🚌 Agent Skill Bus

The missing runtime for Agent Skills — health monitoring, self-improvement, and dependency management for any AI agent framework.

Your agent skills silently break. Agent Skill Bus detects it, diagnoses the root cause, and fixes it automatically.

Built by 合同会社みやび (LLC Miyabi) — Running 42 AI agents in production daily.

Looking for the full ecosystem? This repo is the core runtime. For 110+ production-ready skills, marketplace, and the complete Miyabi Agent Society platform, visit agentskills.bath.me.

What is this?

Agent Skill Bus is a framework-agnostic runtime for AI agent skill health — orchestrating, monitoring, and self-improving agent skills across any framework. Think of it as the operational backbone that keeps your agent skills healthy over weeks and months, not just during a single run. It consists of three integrated modules:

They work independently, but together they form a closed-loop self-improving agent system:

External Changes ──→ Knowledge Watcher ──→ Prompt Request Bus ──→ Execute
                                                ↑                    │
                                                │                    ↓
                                          Self-Improving ←── Skill Runs Log
                                             Skills

Why?

Most agent frameworks handle execution (LangGraph, CrewAI, AutoGen). None handle operational health:

• 🔴 Skills silently degrade — An API changes, a model updates, auth expires. Nobody notices until it fails in production.
• 🔴 Tasks collide — Two agents edit the same file simultaneously. Data corruption.
• 🔴 No dependency management — Complex tasks need A→B→C ordering. Most systems just run everything in parallel.
• 🔴 No learning loop — Failures repeat because there's no feedback mechanism.

Agent Skill Bus solves all four.

Quick Start

# One command to set up everything
npx agent-skill-bus init

# Log a skill execution
npx agent-skill-bus record-run --agent my-agent --skill api-caller --task "fetch data" --result success --score 1.0

# Check what needs attention
npx agent-skill-bus flagged

# Queue a task
npx agent-skill-bus enqueue --source human --priority high --agent dev --task "Fix auth bug"

# See what's ready to dispatch
npx agent-skill-bus dispatch

# See which data files this project is actually using
npx agent-skill-bus daths

For Claude Code / Codex users

Add this to your AGENTS.md:

After completing any task, log the result:
npx agent-skill-bus record-run --agent claude --skill <skill-name> --task "<task>" --result <success|fail|partial> --score <0.0-1.0>

That's it. The self-improving loop runs automatically.

Dashboard

Get a real-time overview of all your agent skills with a single command:

npx agent-skill-bus dashboard

╔══════════════════════════════════════════════════════════╗
║              🚌 Agent Skill Bus Dashboard               ║
╚═══════════════════════════════════════════════════════╝

📊 Queue: 3 queued │ 1 running │ 12 completed │ 0 failed

 Status   Skill               Score  Trend  Health
────────────────────────────────────────────────────────
 ● ALERT  api-caller           0.42   ↓     ██░░░░░░░░░░
 ● OK     code-review          0.95   ↑     ███████████░
 ● OK     deploy-pipeline      0.88   ─     ██████████░░

âš  Flagged Skills:
  api-caller — score_drop: dropped from 0.91 to 0.42 (drift: -53.8%)

Options: --days N (default: 7), --no-color for CI/piping.

Modules

📬 Prompt Request Bus

A JSONL-based task queue with:

• DAG dependency resolution — Tasks specify dependsOn other tasks. Automatic topological execution.
• File-level locking — Prevent two agents from editing the same file. TTL-based deadlock prevention.
• Priority routing — critical > high > medium > low. Critical tasks bypass the queue.
• Multi-source ingestion — Human commands, cron jobs, GitHub webhooks, internal triggers all use the same format.
• Deduplication — Same task won't be queued twice.

{
  "id": "pr-001",
  "ts": "2026-03-18T08:00:00Z",
  "source": "human",
  "priority": "high",
  "agent": "dev-agent",
  "task": "Fix authentication bug in auth.ts",
  "status": "queued",
  "dependsOn": [],
  "affectedFiles": ["myapp:src/auth.ts"],
  "dagId": null
}

Full documentation →

🔄 Self-Improving Skills

A 7-step quality loop inspired by Cognee's self-improving agents:

OBSERVE → ANALYZE → DIAGNOSE → PROPOSE → EVALUATE → APPLY → RECORD

• Automatic failure detection — Score drops, trend analysis, consecutive failure alerts.
• LLM-powered diagnosis — Reads the failing skill + error logs, identifies root cause.
• Safe auto-repair — Low-risk fixes applied automatically. High-risk changes need human approval.
• Drift detection — Catches silent degradation (score drops >15% week-over-week).

Full documentation →

👁️ Knowledge Watcher

Monitors external changes and triggers improvement requests:

• Tier 1 (every check): Dependency versions, API changes, config drift
• Tier 2 (daily): Community patterns, user feedback, platform changes
• Tier 3 (weekly): Industry trends, competitor releases, best practice updates

When a change is detected:

1. Assess impact on existing skills
2. Generate a Prompt Request with severity rating
3. Route to Self-Improving Skills or human reviewer

Full documentation →

Documentation

Architecture

┌─────────────────────────────────────────────────────┐
│                  Agent Skill Bus                     │
│                                                     │
│  ┌──────────────┐  ┌──────────────┐  ┌───────────┐ │
│  │   Knowledge   │  │    Prompt    │  │   Self-   │ │
│  │   Watcher     │──│   Request    │──│ Improving │ │
│  │   (detect)    │  │   Bus (route)│  │  (repair) │ │
│  └──────────────┘  └──────────────┘  └───────────┘ │
│         │                  │                │       │
                                               : 0¶»§q«^