OpenShell is a runtime for autonomous AI agents that executes them in sandboxed environments governed by declarative policies. It is used to restrict agents' access to files, credentials, data, and network resources, and the catalogue includes skills and workflows for operating and contributing to it.
Borrowing it
Nothing to install: this file belongs to NVIDIA/OpenShell. 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/NVIDIA/OpenShell/main/.agents/skills/create-rfc/SKILL.mdgit clone --depth 1 https://github.com/NVIDIA/OpenShellWrote 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/skills/nvidia/openshell/create-rfc)<a href="https://agentmods.dev/skills/nvidia/openshell/create-rfc"><img src="https://agentmods.dev/badge/skills/nvidia/openshell/create-rfc/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/skills/nvidia/openshell/create-rfc"><img src="https://agentmods.dev/badge/skills/nvidia/openshell/create-rfc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00067 | $0.00567 |
| Opus 5.5 | $0.00027 | $0.00227 |
| Sonnet 5.5 | $0.00013 | $0.00113 |
| Haiku 4.5 | $0.00007 | $0.00057 |
Grade A, and why
create-rfc 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 1mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create RFC
Workflow
Create RFCs by following rfc/README.md and rfc/0000-template/README.md.
Keep the template as the source of truth for section guidance.
- Read
rfc/README.mdto confirm when an RFC is appropriate, how to choose the RFC number, and how the lifecycle works. - Read
rfc/0000-template/README.mdbefore drafting. Follow its section guidance, including scope, expected detail, and suggested section length. - Choose the next available
NNNNfrom the existingrfc/NNNN-*directories unless the user provided a specific number. - Create
rfc/NNNN-short-title/README.mdby copying the template and replacing placeholders. Use a short hyphenated folder title. - Fill in front matter with the RFC author,
state: draft, and any related links the user provided. If the author is unknown, use the requesting user's GitHub handle when available or leave the template placeholder. - Draft each section from the user's design context. Keep Summary concise, Motivation readable by anyone, Non-goals explicit, Proposal focused on what is being proposed, and Alternatives focused on credible competing approaches.
- Preserve uncertainty in Open questions instead of silently deciding unknowns. If a missing decision blocks a coherent RFC, ask the user for that decision.
- Check the completed RFC against the template once more before finishing.
Writing Standards
- Prefer concrete design statements over placeholder language.
- Link to relevant issues, prior RFCs, and published docs when they provide needed context.
- Keep rejected or left-out designs in Alternatives, not Proposal.
- Use Mermaid diagrams for architecture or data flow when a diagram would make the proposal easier to review.
- Do not update published docs just because an RFC was drafted. Those updates belong with implementation or with an accepted RFC when the user asks for them.
Validation
Before handing the RFC back to the user:
- Verify the folder name and RFC number match the process in
rfc/README.md. - Verify every template section is present or intentionally marked as not applicable.
- Run a Markdown formatting or lint check only if the repo already provides one for Markdown-only changes.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed 14ee63d4254d
- 2mo ago Changed · +2 lines 7d9f57231cb2
- 2mo ago First seen · 52 lines · 67 tokens per session scan A 5c064e20a159
create-rfc is a skill published in the GitHub repository NVIDIA/OpenShell (21,172 stars, last pushed yesterday), licensed Apache-2.0. It adds 67 tokens to every session and 567 once invoked, about $0.0003 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.
create-rfc compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| create-rfcNVIDIA/OpenShell | Skill | 21k | yesterday | Apache-2.0 | A | 67 | Codex |
| imagegenopenai/codex | Skill | 133k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |