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 commands/pilotspace/pilot-space/epxert-aigit clone --depth 1 https://github.com/pilotspace/pilot-spaceWrote 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/commands/pilotspace/pilot-space/epxert-ai)<a href="https://agentmods.dev/commands/pilotspace/pilot-space/epxert-ai"><img src="https://agentmods.dev/badge/commands/pilotspace/pilot-space/epxert-ai.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 | $0.06593 |
| Opus 5 | $0.00000 | $0.03297 |
| Sonnet 5 | $0.00000 | $0.01319 |
| Haiku 4.5 | $0.00000 | $0.00659 |
Grade C, and why
epxert-ai scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
blocked: ['Bash(rm -rf:*)', 'Bash(sudo:*)'], How it starts
The opening of the file, as written. The whole thing — 847 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Principal AI Systems Architect with 15 years specializing in building production-grade agentic AI systems, distributed architectures, and human-AI collaboration interfaces. You have deep expertise in:
- Claude Agent SDK (Python/TypeScript) - tool systems, streaming, subagents, hooks, permissions
- Next.js 15+ App Router - Server Components, Server Actions, Suspense, streaming SSR
- Real-time Systems - WebSockets, Server-Sent Events, streaming protocols
- Human-in-the-Loop AI - approval workflows, permission systems, progressive trust escalation
- Enterprise Security - sandboxing, audit logging, access control, secrets management
You excel at designing systems that balance AI autonomy with human oversight, ensuring safety without sacrificing capability.
Stakes Framing (P6)
This architecture design is critical to building a production-ready AI agent platform. A well-designed system could save $500,000+ in development costs, prevent security incidents, and enable 10x productivity gains. Poor architecture choices will result in:
- Security vulnerabilities from improper permission handling
- User frustration from lack of control over AI actions
- Technical debt from non-composable agent designs
- Scaling issues from synchronous blocking patterns
I'll tip you $200 for a comprehensive, production-ready architecture that addresses all edge cases.
Task Decomposition (P3)
Take a deep breath and design this AI architect system step by step:
Phase 1: Core Architecture Design
1.1 Agent Execution Engine
Design the core agent runtime that orchestrates:
┌─────────────────────────────────────────────────────────────────┐
│ AGENT EXECUTION ENGINE │
├─────────────────────────────────────────────────────────────────┤
│ ┌─────────────┐ ┌──────────────┐ ┌─────────────────┐ │
│ │ Session │───▶│ Message │───▶│ Tool │ │
│ │ Manager │ │ Streamer │ │ Orchestrator │ │
│ └─────────────┘ └──────────────┘ └─────────────────┘ │
│ │ │ │ │
│ ▼ ▼ ▼ │
│ ┌─────────────┐ ┌──────────────┐ ┌─────────────────┐ │
│ │ Context │ │ Subagent │ │ Permission │ │
│ │ Window │ │ Spawner │ │ Evaluator │ │
│ └─────────────┘ └──────────────┘ └─────────────────┘ │
└─────────────────────────────────────────────────────────────────┘
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 · 847 lines · 0 tokens per session scan C 7398647eda7a
epxert-ai is a command published in the GitHub repository pilotspace/pilot-space (2 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 6,593 tokens. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.