review-triage-queue
Skill17k starsChanged 18 days agoApache-2.0View on GitHub
Create a read-only, local triage queue report from OpenShell GitHub intake. Use to review the triage queue, scan incoming issues and community PRs, check main-branch CI failures, or resume a triage pass.
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Create a decision-focused, local Markdown report.
- Very specific: line 14
Use these ignored local paths under .agents/triage-duty/:
- Distinctive: line 29
Follow Label Discovery, retrieving all pages of current label definitions.
- Distinctive: line 31
All open GitHub issues in the triage queue, ordered by most recently updated.
- Distinctive: line 39
Do not scan GitHub Discussions or a dedicated security-reporting source in v1.
- Very specific: line 45
Use repository-scoped object IDs: I<number> for issues, P<number> for PRs, and C<run_id> for GitHub Actions runs.
- Very specific: line 63
Create a dated immutable report using the report template.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Review Triage Queue
Create a decision-focused, local Markdown report. Do not write to GitHub.
Local state
Use these ignored local paths under .agents/triage-duty/:
- Checkpoint:
state.local.yml - Reports:
reports/<UTC timestamp>.md - Action records:
actions/<UTC timestamp>.md - Inbox:
inbox.md
Record first-run coverage. Update cursors only after a complete report; partial reads must not skip unread items. Search with overlap and deduplicate source items.
Keep the checkpoint minimal: repository, last successful scan, source and backlog cursors, explicit dispositions, and next triage issue. Action records are authoritative; reconcile the checkpoint from them before proceeding. Reports are immutable. Never store credentials, personal data, private reasons, or vulnerability details; never stage duty files.
Read unchecked inbox entries at the start of every review. Treat them as local follow-up prompts, not as independent evidence or authorization for an external action. When an entry materially informs the review, include it in the report's Local inbox follow-up section. After the dated report is written, mark that entry complete in the inbox with the report filename. Leave entries unchecked when they were not yet actionable or were not considered.
Gather intake
Follow Label Discovery, retrieving all pages of current label definitions. Identify the triage queue by its description. Read all pages of each source:
- All open GitHub issues in the triage queue, ordered by most recently updated.
- Newly opened community issues with no
state:*label; exclude maintainer/core-contributor issues and already-routed work from label recommendations. This includes stale lifecycle labels. - Older open community issues meeting the same eligibility rule: measure first; audit all when there are at most 20, otherwise inspect the five oldest remaining candidates per run. Use a separate
(created_at, number)backlog cursor, advanced only after inspection and reporting; wrap at the end. Advancing it must not drop pending recommendations. Age sets ordering only and never justifies closure. - Open non-draft Dependabot pull requests. Surface these explicitly so they do not age out or go stale while waiting for maintainer attention.
- Newly opened non-draft community pull requests.
- Failed CI runs on
main. - Published repository documentation for applicable public answers.
Do not scan GitHub Discussions or a dedicated security-reporting source in v1. Route suspected vulnerabilities through SECURITY.md.
Treat an unlabelled issue as already routed when it has roadmap placement, a milestone, a Project item, or an explicit maintainer comment that assigns, schedules, or otherwise intentionally removes it from triage. Report that signal as context; never recommend adding the triage-queue label to it. If authorship or routing is uncertain, report the uncertainty instead of recommending a label.
Analyze and rank
Use repository-scoped object IDs: I<number> for issues, P<number> for PRs, and C<run_id> for GitHub Actions runs. Link each ID to its canonical source; attempts share the run ID. PRs are informational in v1.
Detect related signals across sources. Preserve each source as linked provenance. Group similar evidence into one recommendation; do not count a global fixed number of occurrences as the only evidence of repetition.
Recommend work for repeated questions, defects, documentation/support gaps, requested product changes, or likely duplicates. Treat documentation and support improvements as bug-fix or feature work when they address a demonstrated user need.
Classify recommendations as bug, feature, documentation/support improvement, duplicate, intake-gap routing, release blocker, or security finding. The agent may infer a release blocker only with concrete evidence, source links, and confidence. Keep critical for security findings and release blockers; use high, normal, or low for all other items. Set confidence to high, medium, or low, and explain uncertainty unless it is high.
Give new and carried pending/deferred recommendations separate five-item budgets. Preserve carried priorities and recheck live sources outside scan windows. Keep excess findings in overflow; only security findings and release blockers may exceed either cap. Never mark recommendations processed merely because they were reviewed; carry pending/deferred items until applied or rejected through apply-triage-action.
Resume an in-progress triage pass
When the on-duty engineer asks for the “next issue” without asking for a new queue review, resume from the latest local report's Triage queue order. Select the first item that has not been explicitly dispositioned in local duty state. Do not query live GitHub data to silently reorder an in-progress pass: newly opened or newly updated issues belong in the next queue review. Use triage-issue for assessment.
An engineer can explicitly request a refresh or the newest live issue; either request supersedes the continuation order. If the report has no remaining listed candidate, say so and offer a fresh queue review rather than choosing an item from an older overflow list.
Write the report
Create a dated immutable report using the report template. Use links and short paraphrases only. Record its first listed triage issue as next_triage_issue in the checkpoint.
Trending
Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data
Who's talking about NVIDIA/OpenShell
- NVIDIA Developer“How to Secure & Run AI Agents with NVIDIA OpenShell”YouTube · Sep 28, 2026 · 60k views
- Zen van Riel“The Safest Way To Use Hermes & OpenClaw (OpenShell)”YouTube · Sep 13, 2026 · 14k views
- Signal Coders“NVIDIAOpenShell — OpenShell is the safe, private runtime for autonomous AI agents”YouTube · Oct 1, 2026 · 2.1k views
- Drift Intel “NVIDIA OpenShell Closes an AI Agent Loophole (Your Setup Still Has It)”YouTube · Sep 29, 2026 · 1.4k views
- NewsDoc“NVIDIA OpenShell: Deny-by-Default Agents #Shorts”YouTube · Oct 16, 2026 · 1k views
The biggest 5 of 77 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 77
Talked about on Bluesky, YouTube, the web and Hacker News (77 times).
On Bluesky · 41
- Sep 29, 2026When you feel you need a head-inducing list of configurable ACL for your shell/VM, to run your AI agents. github.com/NVIDIA/OpenS... — @sungkim.bsky.social23 likes and reposts
- Oct 12, 2026AIエージェントをsandbox環境で分離するNVIDIA製ツール。ネットワークレベルのアクセス許可も設定可。Linux, macOS, WSL2などで動作。Rust実装だが各言語用SDKが用意されておりプログラムで制御可。brew install openshellでok — @matsuu.bsky.social7 likes and reposts
- Oct 23, 2026🚀 Skyrocketing! 🚀 (200+ new stars) 📦 NVIDIA / OpenShell ⭐ 18,266 (+211) 🗒 Rust OpenShell is the safe, private runtime for autonomous AI… — @github-trending.bsky.social5 likes and reposts · 1 reply
- Oct 24, 2026OpenShell – A safe, private runtime for fleets of autonomous AI agents https://github.com/NVIDIA/OpenShell comments #github.com — @hnbest.bsky.social4 likes and reposts
- Oct 24, 2026OpenShell – 自律型AIエージェント群のための、安全でプライベートな実行環境 OpenShell – A safe, private runtime for fleets of autonomous AI agents 🔺 489 💬 65 🔗 HN Post… — @hacker-news-jp.bsky.social4 likes and reposts · 1 reply
36 more on Bluesky
- Oct 22, 2026OpenShell – A safe, private runtime for fleets of autonomous AI agents https://github.com/NVIDIA/OpenShell… — @hn100.atproto.rocks4 likes and reposts
- Mar 23, 2026hmm, openshell looks pretty interesting: github.com/NVIDIA/OpenS... basically just runs your agent in an OCI container (like we already do)… — @cboettig.bsky.social4 likes and reposts · 1 reply
- Sep 29, 2026🎉 Celebrating! 🎉 (500+ new stars) 📦 NVIDIA / OpenShell ⭐ 9,944 (+978) 🗒 Rust OpenShell is the safe, private runtime for autonomous AI… — @github-trending.bsky.social3 likes and reposts · 1 reply
- Sep 1, 2026NVIDIA / OpenShell: OpenShell is the safe, private runtime for autonomous AI agents. ★8466 https://github.com/NVIDIA/OpenShell — @rusttrending.bsky.social3 likes and reposts
- Jul 10, 2026🔥 Hot Repo! 🔥 (100+ new stars) 📦 NVIDIA / OpenShell ⭐ 7,607 (+108) 🗒 Rust OpenShell is the safe, private runtime for autonomous AI… — @github-trending-rs.bsky.social3 likes and reposts
- Oct 25, 2026OpenShell – A safe, private runtime for fleets of autonomous AI agents https://github.com/NVIDIA/OpenShell… — @newsyc500.bsky.social2 likes and reposts · 1 reply
- Oct 23, 2026OpenShell – A safe, private runtime for fleets of autonomous AI agents View Article | Discussion + AI Summary Summary of HN discussion 🧵👇 — @hncompanion.com2 likes and reposts · 1 reply
- Oct 23, 2026OpenShell – A safe, private runtime for fleets of autonomous AI agents https://github.com/NVIDIA/OpenShell [comments] [318 points] — @hnfeed.bsky.social2 likes and reposts
- Oct 23, 2026OpenShell – A safe, private runtime for fleets of autonomous AI agents https://github.com/NVIDIA/OpenShell… — @betterhn300.e-work.xyz2 likes and reposts
- Oct 22, 2026OpenShell – A safe, private runtime for fleets of autonomous AI agents https://github.com/NVIDIA/OpenShell… — @newsyc250.bsky.social2 likes and reposts
- Oct 22, 2026OpenShell is the safe, private runtime for fleets of autonomous AI agents. Agents are most useful when they can read files, install… — @ytroncal.bsky.social2 likes and reposts
- Oct 22, 2026Nvidia OpenShell https://github.com/NVIDIA/OpenShell https://news.ycombinator.com/item?id=50198675 — @hn100.atproto.rocks2 likes and reposts
- Oct 15, 2026NVIDIA / OpenShell: OpenShell is the safe, private runtime for autonomous AI agents. ★16335 https://github.com/NVIDIA/OpenShell — @rusttrending.bsky.social2 likes and reposts
- Sep 29, 2026今日のGitHubトレンド NVIDIA/OpenShell OpenShellは、自律型AIエージェント向けの安全でプライベートな実行環境です。 エージェントにファイル操作やAPI利用などの機能を提供しつつ、ポリシーによってデータやネットワークへのアクセスを制限します。… — @dailygithubtrends.bsky.social2 likes and reposts
- May 13, 2026NVIDIA / OpenShell: OpenShell is the safe, private runtime for autonomous AI agents. ★5863 https://github.com/NVIDIA/OpenShell — @rusttrending.bsky.social2 likes and reposts
- Oct 29, 2026NVIDIA / OpenShell: OpenShell is the safe, private runtime for autonomous AI agents. ★20681 https://github.com/NVIDIA/OpenShell — @rusttrending.bsky.social1 likes and repost
- Oct 26, 2026Nvidia OpenShell: your agents never see real credentials! Open source OpenShell sandboxes agents. Creds reach approved endpoints only.… — @goldenrod8888.bsky.social1 likes and repost
- Oct 23, 2026今日のGitHubトレンド NVIDIA/OpenShell OpenShellは、自律型AIエージェント向けの安全でプライベートなランタイムです。 エージェントにファイル操作やAPI呼び出しなどの権限を与えつつ、データや秘密情報、ネットワークへの無制限なアクセスを制限します。… — @dailygithubtrends.bsky.social1 likes and repost
- Oct 23, 2026OpenShell – A safe, private runtime for fleets of autonomous AI agents https://github.com/NVIDIA/OpenShell… — @hn.rbrt.fr1 likes and repost · 1 reply
- Oct 22, 2026OpenShell – A safe, private runtime for fleets of autonomous AI agents https://github.com/NVIDIA/OpenShell… — @newsyc200.bsky.social1 likes and repost
- Oct 22, 2026Nvidia OpenShell — @hackernewsrobot.bsky.social1 likes and repost
- Oct 22, 2026Nvidia OpenShell https://github.com/NVIDIA/OpenShell (https://news.ycombinator.com/item?id=50198675) — @betterhn50.e-work.xyz1 likes and repost
- Oct 22, 2026Nvidia OpenShell Discussion | hackernews | Author: niemandhier #AI — @news.karthihegde.dev1 likes and repost
- Oct 22, 2026Nvidia OpenShell https://github.com/NVIDIA/OpenShell (https://news.ycombinator.com/item?id=50198675) — @betterhn20.e-work.xyz1 likes and repost
- Oct 22, 2026Nvidia OpenShell | Discussion — @hackernewsbot.bsky.social1 likes and repost
- Oct 22, 2026🚀 Skyrocketing! 🚀 (200+ new stars) 📦 NVIDIA / OpenShell ⭐ 17,116 (+221) 🗒 Rust OpenShell is the safe, private runtime for autonomous AI… — @github-trending-rs.bsky.social1 likes and repost · 1 reply
- Oct 16, 2026GitHub - NVIDIA/OpenShell: OpenShell is the safe, private runtime for autonomous AI agents. · GitHub — @fluid.sublimer.me1 likes and repost
- Oct 6, 2026maybe something like openshell? for the file pervert part anyway github.com/NVIDIA/OpenS... — @ninachaubal.com1 likes and repost
- Oct 2, 2026AI news - Oct 2, 2026 1. Cloudflare Releases Open-Source Clef Decision Models LINK 2. NVIDIA OpenShell enforces agent security via… — @hackobar.bsky.social1 likes and repost · 1 reply
- Oct 1, 2026NVIDIA / OpenShell: OpenShell is the safe, private runtime for autonomous AI agents. ★13657 https://github.com/NVIDIA/OpenShell — @rusttrending.bsky.social1 likes and repost
- Jul 22, 2026NVIDIA / OpenShell: OpenShell is the safe, private runtime for autonomous AI agents. ★7733 https://github.com/NVIDIA/OpenShell — @rusttrending.bsky.social1 likes and repost
- Jun 2, 2026🔥 Hot Repo! 🔥 (100+ new stars) 📦 NVIDIA / OpenShell ⭐ 6,582 (+142) 🗒 Rust OpenShell is the safe, private runtime for autonomous AI… — @github-trending-rs.bsky.social1 likes and repost
- May 14, 2026📦 NVIDIA / OpenShell ⭐ 5,866 (+46) 🗒 Rust OpenShell is the safe, private runtime for autonomous AI agents. — @github-trending-rs.bsky.social1 likes and repost
- Mar 21, 2026NVIDIA OpenShell: safe, private runtime for autonomous AI agents https://github.com/NVIDIA/OpenShell — @nono2357.bsky.social1 likes and repost · 1 reply
- Oct 27, 2026#OpenShell - The safe, private runtime for fleets of autonomous AI agents github.com/NVIDIA/OpenS... #AI — @joeingeno.bsky.social0 likes and reposts · 1 reply
- Sep 29, 2026🎉 Celebrating! 🎉 (500+ new stars) 📦 NVIDIA / OpenShell ⭐ 9,944 (+978) 🗒 Rust OpenShell is the safe, private runtime for autonomous AI… — @github-trending-rs.bsky.social0 likes and reposts · 1 reply
On YouTube · 25
- Sep 28, 2026How to Secure & Run AI Agents with NVIDIA OpenShell — NVIDIA Developer60k views · 50 comments
- Sep 13, 2026The Safest Way To Use Hermes & OpenClaw (OpenShell) — Zen van Riel14k views · 19 comments
- Oct 1, 2026NVIDIAOpenShell — OpenShell is the safe, private runtime for autonomous AI agents — Signal Coders2.1k views · 1 comment
- Sep 29, 2026NVIDIA OpenShell Closes an AI Agent Loophole (Your Setup Still Has It) — Drift Intel 1.4k views · 4 comments
- Oct 16, 2026NVIDIA OpenShell: Deny-by-Default Agents #Shorts — NewsDoc1k views
20 more on YouTube
- Jun 18, 2026I Tested NVIDIA OpenShell To see if the Coding Agent stops Leaking Credentials — DevAndACupsays it tested it740 views · 1 comment
- Sep 29, 2026OpenShell Setup: Sandbox Your AI Agents with NVIDIA's Free Runtime (Full Tutorial) — GENZ TECH 726 views
- Oct 7, 2026OpenShell: How to set it up free in 7 minutes — OverClocked439 views
- Oct 3, 2026NVIDIA OpenShell Explained: Secure Sandboxes for Autonomous AI Agents — Alex Hitt422 views
- Oct 24, 2026OpenShell: NVIDIA's Free Agent Jail With 4 Policy Walls — Prism Labs383 views
- Oct 8, 2026NVIDIA OpenShell: lock your AI agent in a sandbox (free) #nvidia #aiagents #opensource — Kiran CK380 views · 1 comment
- Oct 18, 2026NVIDIA OpenShell lets AI agents work for you without touching your secrets — bestatAI286 views · 1 comment
- Oct 1, 2026What is NVIDIA OpenShell ? Secure AI Agent Runtime Explained — Open Projects246 views · 1 comment
- Sep 30, 2026NVIDIA/OpenShell — Agents, on a leash. 🟡 Watchlist #Shorts — ForkCast224 views
- Oct 1, 2026OpenShell: safe private runtime for autonomous AI agents — Next Horizon164 views · 1 comment
- Sep 30, 2026NVIDIA OpenShell — AI & Tech News152 views · 1 comment
- Sep 30, 2026GitHub - NVIDIA/OpenShell: OpenShell is the safe, private runtime for autonomous AI agents. — GitHub Daily Trend AI Podcast134 views · 2 comments
- Sep 30, 2026NVIDIA/OpenShell is an open-source, Apache 2.0 runtime for safer, private autonomous AI agents, — Nexbit Studio115 views
- Oct 25, 2026NVIDIA's OpenShell: A Kernel-Level Sandbox for AI Agents — Hidden Repos - GitHub gems nobody talks about114 views
- Oct 3, 2026Your AI Agent Needs a Sandbox | NVIDIA OpenShell — Cemong84 views
- Oct 10, 2026An idle Nvidia OpenShell sandbox woke 890 times a second — Agent Audit83 views
- Oct 4, 2026NVIDIA OpenShell on AWS: Real Sandbox & AI Agent Walkthrough | Software Sushi — Software Sushi - David69 views
- Oct 4, 2026NVIDIA OpenShell Live Walkthrough: Dashboard, AI Agent & Policy Enforcement | Software Sushi — Software Sushi - David29 views
- Sep 30, 2026NVIDIA OpenShell — The Safe Runtime for AI Agents | Repo of the Day — TECH NOW & NEXT27 views
- Oct 23, 2026Caging Autonomous Agents: NVIDIA OpenShell in Production — In Prod.4 views
On the web · 6
- Oct 24, 2026OpenShell by NVIDIA: Sandbox for AI Agents Explained — activepieces.com
- Oct 1, 2026What Is NVIDIA OpenShell? Sandbox, Supervisor and Sentry — ackuity.ai
- Sep 30, 2026OpenShell is the safe, private runtime for autonomous AI ... — spreaker.com
- Sep 29, 2026Nvidia OpenShell — en.wikipedia.org
- Apr 3, 2026NVIDIA OpenShell and Agent Toolkit: Deploy Secure ... — spheron.network
1 more on the web
- Mar 30, 2026How NVIDIA OpenShell Puts a Control Plane Around Your AI ... — kenhuangus.substack.com
On Hacker News · 5
- Oct 22, 2026OpenShell – A safe, private runtime for fleets of autonomous AI agents507 points · 218 comments
- Mar 16, 2026OpenShell: Nvidia's sandbox for AI agents like OpenClaw4 points · 1 comment
- Oct 2, 2026Nvidia/OpenShell: Safe, private runtime for autonomous AI agents2 points
- Apr 21, 2026Nvidia OpenShell: safe, private runtime for autonomous AI agents2 points
- Mar 17, 2026OpenShell – private runtime for autonomous AI agents2 points
In this repository28 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- apply-triage-actionSkill
- build-from-issueSkill
- build-openshell-mxc-windowsSkill
- create-github-issueSkill
- create-github-prSkill
- create-rfcSkill
- create-spikeSkill
- fix-security-issueSkill
- helm-dev-environmentSkill
- launch-openshell-gatorSkill
- release-openshellSkill
- review-github-prSkill
- review-security-issueSkill
- sbomSkill
- sync-agent-infraSkill
- test-release-canarySkill
- triage-issueSkill
- tui-developmentSkill
- update-docs-from-commitsSkill
- watch-github-actionsSkill
- openshell-policy-advisorSkill
- gator-gateSkill
- debug-inferenceSkill
- debug-openshell-clusterSkill
- generate-sandbox-policySkill
- openshell-cliSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

