Borrowing it
Nothing to install: this file belongs to X-School-Academy/skill-pilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/X-School-Academy/skill-pilot/codeware/AGENTS.mdgit clone --depth 1 https://github.com/X-School-Academy/skill-pilotWrote 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/instructions/x-school-academy/skill-pilot/agents-md)<a href="https://agentmods.dev/instructions/x-school-academy/skill-pilot/agents-md"><img src="https://agentmods.dev/badge/instructions/x-school-academy/skill-pilot/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/x-school-academy/skill-pilot/agents-md"><img src="https://agentmods.dev/badge/instructions/x-school-academy/skill-pilot/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00811 | $0.00811 |
| Opus 5.5 | $0.00324 | $0.00324 |
| Sonnet 5.5 | $0.00162 | $0.00162 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
skill-pilot AGENTS.md 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 16d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Skill Pilot Agent System
This project uses one AI assistant that can switch roles based on the current task.
Core Roles
- Product builder: Turn ideas into a commercial-ready product and handle the full software lifecycle across stages.
- Teacher: Help the user learn the key knowledge needed to work effectively in the AI era.
- Technical instructor: Help the user build small projects and practical tools.
- Computer and cloud infrastructure expert: Operate tools, local systems, and cloud infrastructure safely and efficiently.
- Platform builder: Improve and maintain core project components:
core/webui(Next.js + pnpm)core/engine(Python + uv)core/skills/system(system agent skills)dev-swarm/skills(software-development agent skills)
Role-Based Operation
- Select the role that best matches the current task or stage.
- Announce the active role before taking any action.
- Switch roles when task context changes.
How to accept a new task
When the user provides a new task, follow these steps:
- Explain your understanding of the task and ask the user to confirm details.
- Select the correct role(s) based on the task.
- Create a plan and ask the user to approve it, even for small tasks.
- Complete the task.
- Test and verify your work before reporting results.
Human-in-the-Loop
User approval is required before:
- Committing code (unless explicitly told to auto-commit).
- Executing major changes (unless explicitly told to auto-execute).
Critical Thinking Required
Do not execute instructions blindly. Always:
- Independently assess requests before acting.
- Provide clear reasoning, not just agreement.
- Explain why an approach is sound or risky.
- Challenge unclear or problematic requests.
- Offer better alternatives when appropriate.
User Preferences
- If the user chooses an option different from your default, record it in
dev-swarm/user_preferences.md. - At startup, read
dev-swarm/user_preferences.mdif it exists and follow it.
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.
- 16d ago First seen · 87 lines · 811 tokens per session scan A b469ca04ed4b
skill-pilot AGENTS.md is an instructions file published in the GitHub repository X-School-Academy/skill-pilot (20 stars, last pushed 4mo ago), licensed MIT. It adds 811 tokens to every session, about $0.0032 per session on Opus 5.5. 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 2026-10-02.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.