NVIDIA/NemoClaw is an open-source reference stack for running supported AI agents inside NVIDIA OpenShell sandboxes with managed inference, network policies, integrations, snapshots, and lifecycle controls. It is used to run agents such as OpenClaw, Hermes, and LangChain Deep Agents with administrative and security controls. Catalogue add-ons guide coding agents through NemoClaw workflows.
Borrowing it
Nothing to install: this file belongs to NVIDIA/NemoClaw. 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/NemoClaw/main/.agents/skills/nemoclaw-maintainer-analyze-ci-performance/SKILL.mdgit clone --depth 1 https://github.com/NVIDIA/NemoClawWrote 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/nemoclaw/nemoclaw-maintainer-analyze-ci-performance)<a href="https://agentmods.dev/skills/nvidia/nemoclaw/nemoclaw-maintainer-analyze-ci-performance"><img src="https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-maintainer-analyze-ci-performance/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/nemoclaw/nemoclaw-maintainer-analyze-ci-performance"><img src="https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-maintainer-analyze-ci-performance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- 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 | $0.00030 | $0.00599 |
| Opus 5.5 | $0.00012 | $0.00240 |
| Sonnet 5.5 | $0.00006 | $0.00120 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
nemoclaw-maintainer-analyze-ci-performance scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze CI Performance
Run one read-only standalone analyzer from a NemoClaw checkout. Both commands use authenticated gh reads and print bounded JSON to stdout. They perform no GitHub writes.
Analyze recent CLI timings
Use retained cli-vitest-results artifacts to rank consistently slow tests and files. The CI workflow retains this historical input for 14 days:
node --no-warnings \
.agents/skills/nemoclaw-maintainer-analyze-ci-performance/scripts/analyze-recent-cli-timings.mts \
--workdir "$PWD"
Defaults preserve the former timing tool contract: repository NVIDIA/NemoClaw, 10 reports, 15 results, a 0.7 minimum sample ratio, and artifact name cli-vitest-results. Optional flags are --repo, --limit, --top, --min-sample-ratio, and --artifact-name.
The analyzer requires at least two usable retained reports. It rejects compressed artifacts above 25,000,000 bytes and bounds ZIP entries, expanded content, listings, and report content. It requires Bash, GNU dd and find, Info-ZIP zipinfo and unzip, awk, base64, mktemp, stat, and wc on Linux.
Analyze base-image publication
Compare main-push E2E runs that publish a same-commit base image with runs that reuse a prior publication:
node --no-warnings \
.agents/skills/nemoclaw-maintainer-analyze-ci-performance/scripts/analyze-base-image-publication-timings.mts \
--workdir "$PWD"
Defaults preserve the former timing tool contract: repository NVIDIA/NemoClaw, 300 E2E runs, 500 base-image runs, and up to 150 systematic samples per stratum. Optional flags are --repo, --e2e-limit, --base-limit, and --max-per-stratum.
Report the population window and stratum sizes before statistics. Treat atLeast30SuccessfulJobs: false as insufficient evidence for stable inference. Job execution, verifier, workflow completion, runner queue, and matrix-boundary measurements use successful publication jobs only.
What ships with it
5 files 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 · -26 tokens per session 9b3f5cb57a63
- 1mo ago Changed 43544a97d62a
- 1mo ago First seen · 45 lines · 56 tokens per session scan A 7af099adc733
nemoclaw-maintainer-analyze-ci-performance is a skill published in the GitHub repository NVIDIA/NemoClaw (22,871 stars, last pushed today), licensed Apache-2.0. It adds 30 tokens to every session and 599 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 2026-09-03.
Other skills, from other repositories
pentest-supply-chain
Software supply chain security — dependency confusion, CI/CD pipeline attacks, lockfile integrity, and build artifact verification.
fix-ci
Fix the failed CI checks for the current session. Use when the user requests a CI fix via the Fix Checks button in the Changes toolbar.
turborepo
Configure and troubleshoot Turborepo repositories. Use when working with turbo.json, task pipelines, caching, Remote Cache, the turbo CLI, filtering, environment variables, package boundaries, monorepo structure, or CI workflows.
om-setup-ci
Set up or refresh CI for a standalone Open Mercato app in one command — GitHub Actions with dependency audit, secret scan (Gitleaks), SAST (Semgrep with Open Mercato rules), workflow security (zizmor), lint, generate + clean-tree check, typecheck, design-system check, unit tests, build, ephemeral integration tests…
diagnosing-ci-and-merge-bottlenecks
Diagnoses CI and pull-request pipeline health for a GitHub repo using the engineering analytics MCP tools — pull-requests (PR list with CI status), workflow-health (per-workflow CI trends), and pr-lifecycle (a single PR's timeline). Use when asked whether CI is getting faster or slower, which GitHub Actions workflow…
investigating-ci-failures
Investigates a specific CI failure to a verdict: whose fault, which commit, who wrote it, and whether it's fixed. Use for "who broke master", "why did this test fail in CI", "is this failure my PR's fault or everyone's", "is this test flaky or actually broken", "when did this failure start". Works from the…