004-agentic-orchestration

004-agentic-orchestration is an agent for coding agents from paulbreuler/limps. It costs 0 tokens per session (2,477 once invoked), scanned A, original, MIT.

A file-watching service that reindexes changed files, checks for conflicts, and reports problems in a knowledge graph as changes happen.

In plain words
What is it for?
Use it to monitor a plans directory, update affected graph entries, detect conflicts, and send results to the terminal, a file, a webhook, or a notification.
Why use it?
It finds issues proactively instead of waiting for someone to ask whether plans, files, or features conflict.

Agent

Install

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.

agentmods
npx agentmods add agents/paulbreuler/limps/004-agentic-orchestration
Clone the repo
git clone --depth 1 https://github.com/paulbreuler/limps

Wrote 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.

agentmods badge for 004-agentic-orchestration

README.md
[![agentmods](https://agentmods.dev/badge/agents/paulbreuler/limps/004-agentic-orchestration.svg)](https://agentmods.dev/agents/paulbreuler/limps/004-agentic-orchestration)
Your own site
<a href="https://agentmods.dev/agents/paulbreuler/limps/004-agentic-orchestration"><img src="https://agentmods.dev/badge/agents/paulbreuler/limps/004-agentic-orchestration.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,477 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02477
Opus 5 $0.00000 $0.01239
Sonnet 5 $0.00000 $0.00495
Haiku 4.5 $0.00000 $0.00248

Measured 4d ago against content hash 9d9fc73738e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

004-agentic-orchestration 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.

plans/0042-Knowledge Graph Foundation/agents/004-agentic-orchestration.agent.md · 367 lines

How it starts

The opening of the file, as written. The whole thing — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent 004: Proactive Watch Mode

Objective

Watch for file changes, auto-index, and surface conflicts proactively. No query needed — system detects problems automatically.

Context

This is the key differentiator from AI-dependent systems. Instead of waiting for AI to ask "are there conflicts?", the system:

  1. Watches for file changes
  2. Re-indexes affected entities
  3. Runs conflict detection
  4. Notifies (stdout, file, webhook, toast)

Tasks

1. File Watcher (src/watch/index.ts)

import chokidar from 'chokidar';

export class GraphWatcher {
  private watcher: chokidar.FSWatcher | null = null;
  
  constructor(
    private plansDir: string,
    private extractor: EntityExtractor,
    private storage: GraphStorage,
    private detector: ConflictDetector,
    private notifier: Notifier
  ) {}
  
  start(options: WatchOptions = {}): void {
    const {
      interval = 100,        // Debounce interval
      onConflict = 'log',    // 'log' | 'notify' | 'webhook'
      webhookUrl,
    } = options;
    
    this.watcher = chokidar.watch(this.plansDir, {
      ignored: /(^|[\/\\])\../, // Ignore dotfiles
      persistent: true,
      ignoreInitial: true,
      awaitWriteFinish: {
        stabilityThreshold: interval,
        pollInterval: 100,
      },
    });
    
    this.watcher
      .on('add', path => this.handleChange(path, 'add'))
      .on('change', path => this.handleChange(path, 'change'))
      .on('unlink', path => this.handleChange(path, 'delete'));
    
    console.log(`👁️  Watching ${this.plansDir} for changes...`);
  }
  
  stop(): void {
    this.watcher?.close();
    this.watcher = null;
  }
  
  private async handleChange(path: string, event: 'add' | 'change' | 'delete'): Promise<void> {
    // Only process plan/agent markdown files
    if (!path.endsWith('.md')) return;
    if (!path.includes('-plan.md') && !path.includes('.agent.md')) return;
    
    console.log(`📝 ${event}: ${path}`);
    
    // Re-index affected plan
    const planPath = this.getPlanPath(path);
    if (planPath) {
      const result = this.extractor.extractPlan(planPath);
      this.storage.bulkUpsertEntities(result.entities);
      this.storage.bulkUpsertRelationships(result.relationships);
    }
    
    // Run conflict detection
    const conflicts = this.detector.detectAll();
    
    // Notify if conflicts found
    if (conflicts.length > 0) {
      this.notifier.notify(conflicts);
    }
  }
  
  private getPlanPath(filePath: string): string | null {
    // Extract plan directory from file path
    const match = filePath.match(/(plans\/\d{4}[^\/]+)/);
    return match ? match[1] : null;
  }
}

Read the full file on GitHub · 367 lines

Changes

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.

  1. 4d ago First seen · 367 lines · 0 tokens per session scan A 9d9fc73738e9

Subscribe to this mod's changes

004-agentic-orchestration is an agent published in the GitHub repository paulbreuler/limps (10 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,477 tokens. 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.