Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sthamann/nyx-local-ainpx agentmods add skills/sthamann/nyx-local-ai/release-nyxWrote 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/sthamann/nyx-local-ai/release-nyx)<a href="https://agentmods.dev/skills/sthamann/nyx-local-ai/release-nyx"><img src="https://agentmods.dev/badge/skills/sthamann/nyx-local-ai/release-nyx/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/sthamann/nyx-local-ai/release-nyx"><img src="https://agentmods.dev/badge/skills/sthamann/nyx-local-ai/release-nyx.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 | $0.00072 | $0.00661 |
| Opus 5 | $0.00036 | $0.00331 |
| Sonnet 5 | $0.00014 | $0.00132 |
| Haiku 4.5 | $0.00007 | $0.00066 |
Grade A, and why
release-nyx 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 11d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Releasing nyx-local-ai
Follow this checklist in order. Abort on the first failed step.
Release progress:
- [ ] 1. Bump version everywhere
- [ ] 2. Quality gates
- [ ] 3. Package + local install
- [ ] 4. Commit, tag, push
- [ ] 5. Verify CI release
1. Bump version everywhere
Three places must always carry the same version:
# package.json → "version": "X.Y.Z"
# README.md → status line **vX.Y.Z** and all nyx-local-ai-X.Y.Z.vsix mentions
# src/mcp/client.ts → clientInfo: { version: 'X.Y.Z' }
2. Quality gates
npm run typecheck # must exit 0
node .harness/smoke.mjs # must print ALL PASS
node .harness/readme-check.mjs # must print "README CHECK: ALL PASS"
npm run build # must print "[nyx] build complete"
The readme-check verifies all three version locations AND that every setting, command, and tool is documented in README.md — fix any FAIL before continuing (update the README, don't weaken the check).
If parser/edit logic changed in this release, confirm .harness/smoke.mjs
covers it before proceeding.
3. Package + local install
npm run package # check the reported size stays ≈4–6 MB
bash install.sh --editor=cursor --vsix=./nyx-local-ai-X.Y.Z.vsix
Remind the user to run Developer: Reload Window to activate the build.
4. Commit, tag, push
Only commit when the user asked for it. Then:
git tag vX.Y.Z && git push origin main vX.Y.Z
The tag triggers .github/workflows/release.yml, which attaches
nyx-local-ai.vsix (stable name), the versioned .vsix, and checksums.txt
to the GitHub release — exactly what install.sh/install.ps1 download.
5. Verify CI release
gh run list --repo sthamann/nyx-local-ai --limit 3
gh release view vX.Y.Z --repo sthamann/nyx-local-ai --json assets -q '.assets[].name'
Expected assets: nyx-local-ai.vsix, nyx-local-ai-X.Y.Z.vsix,
checksums.txt. If the run failed, read the log
(gh run view <id> --log-failed) and fix before announcing the release.
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.
- 11d ago First seen · 76 lines · 72 tokens per session scan A 99573d37e97c
release-nyx is a skill published in the GitHub repository sthamann/nyx-local-ai (137 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 661 once invoked, about $0.0004 per session on Opus 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.
Other skills, from other repositories
github-repo-management
Clone/create/fork repos; manage remotes, releases.
publish-site
Versioned site deploys to GitHub/Cloudflare/Netlify Pages.
release-jetbrains
Use when releasing the Kilo JetBrains plugin -- resolve a version ("next rc" or explicit), run the prepare workflow, edit and commit a filtered human-readable changelog on the release PR, then watch publish to completion.
updater_guide
Guidance for checking for and installing Row-Bot updates.
github-auth
GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.
github-issue-to-pr
Carry a GitHub issue to a verified PR with honest CI state.