Borrowing it
Nothing to install: this file belongs to NVlabs/ASPIRE. 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/NVlabs/ASPIRE/main/AGENTS.mdgit clone --depth 1 https://github.com/NVlabs/ASPIREWrote 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/nvlabs/aspire/agents-md)<a href="https://agentmods.dev/instructions/nvlabs/aspire/agents-md"><img src="https://agentmods.dev/badge/instructions/nvlabs/aspire/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/nvlabs/aspire/agents-md"><img src="https://agentmods.dev/badge/instructions/nvlabs/aspire/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 | $0.01500 | $0.01500 |
| Opus 5.5 | $0.00600 | $0.00600 |
| Sonnet 5.5 | $0.00300 | $0.00300 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
ASPIRE 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 21d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Real YAM System 2
These execution rules apply when operating the robot through an already configured ASPIRE CAP MCP session. For installation and service startup, use the operator runbook.
System 2 owns the operator goal, task-level reasoning, tool selection, supervision,
and recovery. Act through registered native mcp__cap__* tools; never bypass them
with source edits, ad-hoc robot code, or shell-wrapped motion.
Instruction priority and skills
The user's instructions take precedence over guidelines provided in a skill. If explicit user instructions conflict with a skill's instructions, prioritize the user's instructions. Use this file for shared execution rules; skills add task- and tool-specific procedures.
Infer routine details. Ask for input when a missing choice materially changes the physical outcome or no safe registered recovery remains.
At fresh-session startup, read cap-tool-usage once before the first robot command. For a cube task, read manipulation-tasks and its linked task context and cube guide before acting. Do not reread an unchanged skill later.
For bottle/pill or cup-stacking tasks, read the matching recipe linked from manipulation-tasks before acting; do not load unrelated recipes.
Native MCP schemas are authoritative for tool names and arguments. Discover the capability graph once per runtime and reuse it. Do not inspect implementation source or invent a tool when a contract is already exposed.
When using low-level cap action tools like move_to_pose, reduce the pauses between action tool calling.
The system need more continous execution without significant delay.
Initiative and follow-through
When the user expresses intent to perform new work or fix an existing issue, persist until the user's intended goal is complete. Progress autonomously towards the user's goal unless they are clearly destructive or irreversible.
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.
- 21d ago Changed · +51 lines · +499 tokens per session 69553407139f
- 2mo ago First seen · 81 lines · 1,001 tokens per session scan A 7b2159f29a46
ASPIRE AGENTS.md is an instructions file published in the GitHub repository NVlabs/ASPIRE (959 stars, last pushed 22d ago), licensed Apache-2.0. It adds 1,500 tokens to every session, about $0.0060 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 2026-08-30.
ASPIRE AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ASPIRE AGENTS.mdNVlabs/ASPIRE | Instructions file | 959 | 22d ago | Apache-2.0 | A | 1,500 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |