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/release-openshell/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/release-openshell)<a href="https://agentmods.dev/skills/nvidia/openshell/release-openshell"><img src="https://agentmods.dev/badge/skills/nvidia/openshell/release-openshell/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/release-openshell"><img src="https://agentmods.dev/badge/skills/nvidia/openshell/release-openshell.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 | $0.00031 | $0.01192 |
| Opus 5.5 | $0.00012 | $0.00477 |
| Sonnet 5.5 | $0.00006 | $0.00238 |
| Haiku 4.5 | $0.00003 | $0.00119 |
Grade A, and why
release-openshell 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 2d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release OpenShell
For the intended release version and branch, inspect the latest passing prerelease and changes since the previous stable release. Present the candidate to the maintainer. Once approved, dispatch Release from that branch:
gh workflow run release.yml --ref main
Without tag, Release detects the highest prerelease version reachable from the
selected branch, then selects its highest-numbered passing candidate. It stops
if that version has no qualified candidate or already has a stable tag. Supply
-f tag=vX.Y.Z to select a version explicitly or retry a stable release.
Use the support branch instead of main for a previous minor version. That
branch must contain the updated release workflows. Release selects the
highest-numbered vX.Y.Z-pre.N reachable from that branch with a
successful Pre-release run triggered by that tag or dispatched on the same branch,
and matching passing release-tag-v1 qualification evidence. Missing or expired evidence blocks
promotion. Inspect the selected candidate in the promotion job summary.
The entire Pre-release run must succeed, including publication. If qualification
passed but publication failed, rerun the failed jobs before promoting the candidate.
Release creates vX.Y.Z at that exact commit, then rebuilds and publishes all
stable artifacts without rerunning qualification. Embedded versions change, so
stable artifacts are not byte-identical to the qualified prerelease. An existing
stable tag may be retried only if it already points to the selected commit. A retry
publishes only missing artifacts; published images, charts, release assets, npm,
and PyPI versions are kept, while the snap is uploaded again.
Stable images are saved as OCI archives during the build and pushed under the
stable version tags during publication. Their SBOMs are verified before updating
latest; the qualified prerelease's commit-SHA image tags remain unchanged.
If no prerelease exists, agree on the version and source commit, then create and
push vX.Y.Z-pre.1. Prerelease tag pushes start Pre-release. If the tag was
created using GITHUB_TOKEN, dispatch Pre-release explicitly on the intended branch:
gh workflow run release-prerelease.yml --ref main -f tag=vX.Y.Z-pre.1
Once the first tag seeds a series, omit tag to create the next candidate at
the selected branch's dispatch commit:
gh workflow run release-prerelease.yml --ref main
This selects the highest release series reachable from that branch and requires
its -pre.1 seed there. It stops if that version is already stable. New version
series always need an explicit seed. Manual runs create a new candidate even
without new commits; pass an existing tag explicitly to retry that candidate.
Candidate creation is serialized with Release Auto-Tag, which still skips
unchanged commits and inactive series on main.
For example, start a support patch series by tagging its intended branch commit
as v0.4.4-pre.1. Subsequent candidates and promotion use the support branch:
gh workflow run release-prerelease.yml --ref release/0.4
gh workflow run release.yml --ref release/0.4
Replace release/0.4 with the actual support branch. Use explicit tag inputs if
its history also contains a higher version series.
Wait for the entire Pre-release run to pass before promoting it. Stable tag pushes do not
start Release. Release Auto-Tag creates and dispatches prereleases on main.
Stable releases serialize across branches. A release older than the highest
stable Git tag publishes versioned artifacts without moving GHCR latest, the
GitHub latest release, npm latest, or snap latest/stable. Its npm package
uses release-X.Y; snap files remain available in its GitHub Release rather than
updating a Snap Store support track. Docs retain an
immutable version and advance latest only for a newer version.
Watch the stable release run and report its result.
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.
- 2d ago Changed · +15 lines 507a06c07a19
- 3d ago Changed · +2 lines 4c5853515c2c
- 10d ago Changed · +31 lines 329c1d028396
- 18d ago Changed · +31 lines 886e1db05d35
- 22d ago Changed · +1 lines 83eb314aec41
- 24d ago First seen · 21 lines · 31 tokens per session scan A 5708f105f6fc
release-openshell is a skill published in the GitHub repository NVIDIA/OpenShell (21,172 stars, last pushed yesterday), licensed Apache-2.0. It adds 31 tokens to every session and 1,192 once invoked, about $0.0001 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 2026-10-14.
release-openshell compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| release-openshellNVIDIA/OpenShell | Skill | 21k | yesterday | Apache-2.0 | A | 31 | Claude Code, 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 |