Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/utensils/nxv/source-command-releasenpx skills add utensils/nxv --skill source-command-releasegit clone --depth 1 https://github.com/utensils/nxvWhat 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 | $0.00017 | $0.00734 |
| Opus 5 | $0.00009 | $0.00367 |
| Sonnet 5 | $0.00003 | $0.00147 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade A, and why
source-command-release 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
source-command-release
Use this skill when the user asks to run the migrated source command release.
Command Template
Release
Releases are driven by release-plz (release-plz.toml +
.github/workflows/release-plz.yml). On every push to main it maintains a
chore: release vX.Y.Z PR with the version bump and CHANGELOG update derived
from conventional commits. Merging that PR ships the release — release-plz
pushes the vX.Y.Z tag, which triggers release.yml (static binaries, GitHub
release, crates.io, Docker) and flakehub-publish-tagged.yml.
This command walks that flow safely. Never merge the release PR without explicit user confirmation — it is an outward-facing, hard-to-reverse action.
Phase 1: Locate the release PR
gh pr list --repo utensils/nxv --search "chore: release in:title" --state open
If none exists, check whether main has unreleased conventional commits since
the last tag (git log $(git describe --tags --abbrev=0)..origin/main --oneline).
If there are releasable commits but no PR, check the latest Release-plz
workflow run for errors (gh run list --workflow release-plz.yml).
Phase 2: Review what will ship
- Show the PR's version bump (Cargo.toml diff) and CHANGELOG addition.
- Verify the version follows the project convention:
feat:commits bump the 0.x minor (features_always_increment_minor = true), fixes bump patch. - If the version or changelog is wrong, edit the release PR directly (it is a normal editable PR) — release-plz preserves manual edits unless new commits land on main.
Phase 3: Pre-flight
- All CI checks on the release PR must be green. If checks show "Expected /
Waiting", the App token is misconfigured — see
release-plz.ymlcomments. - Confirm no other PR is about to land that should be in this release.
Phase 4: Confirm and merge
Present a summary (version, commit list, changelog) and require the user to confirm with the explicit version number (AskUserQuestion). Then:
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 First seen · 74 lines · 17 tokens per session scan A 446ac3968a74
source-command-release is a skill published in the GitHub repository utensils/nxv (136 stars, last pushed 21d ago), licensed MIT. It adds 17 tokens to every session and 734 once invoked, about $0.0001 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
investigating-merge-queue-failures
Use when investigating flaky CI in flox/flox — triaging failures in the GitHub merge queue, working out whether a CI failure is a flaky test, slow infrastructure, or a real break. Accepts an optional lookback window (defaults to 30 days). Examples - "/investigating-merge-queue-failures"…
adding-beta-subcommand
Use when adding a new beta CLI subcommand to flox, which could also be called an experimental or unstable subcommand. This should be used when adding a command to the beta module that respects the beta feature flag.
deep-research-team
This skill should be used when the user asks for "deep research", "research team", "comprehensive analysis", "research report", "investigate thoroughly", "compare X vs Y in depth", or needs synthesis across multiple sources with verification. It spawns a coordinated team of researcher agents across multiple rounds…
audit-permissions
This skill should be used when the user asks to "audit claude permissions", "audit permissions", "review local claude settings", "promote permissions to global", "clean up claude settings", "find permission patterns", or wants to identify project-local Claude Code permissions that should be added to global…
new-cask
This skill should be used when the user asks to "add a cask to homebrew", "create a homebrew cask", "add an app to homebrew", "new cask for", "homebrew cask for", "package an app for homebrew", "submit to homebrew-cask", "make a cask", "contribute a cask", or wants to package a macOS application for Homebrew.
AI SDK Documentation
This skill should be used when working with Vercel AI SDK, AI Gateway, streamText, generateText, generateObject, streamObject, tool calling, or AI SDK providers. Also relevant for "ai-sdk", "@ai-sdk/" packages, or questions about AI SDK patterns, configuration, and best practices.