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 agents/paulbreuler/limps/004-agentic-orchestrationgit clone --depth 1 https://github.com/paulbreuler/limpsWrote 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/agents/paulbreuler/limps/004-agentic-orchestration)<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>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 | $0.00000 | $0.02477 |
| Opus 5 | $0.00000 | $0.01239 |
| Sonnet 5 | $0.00000 | $0.00495 |
| Haiku 4.5 | $0.00000 | $0.00248 |
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.
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:
- Watches for file changes
- Re-indexes affected entities
- Runs conflict detection
- 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;
}
}
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 · 367 lines · 0 tokens per session scan A 9d9fc73738e9
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.
Other agents, from other repositories
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
issue-tracker
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…