agentmods.dev

kesha-voice-kit: Skill for Claude Code

.claude/skills/release/SKILL.md

release is a skill for Claude Code from drakulavich/kesha-voice-kit. It costs 91 tokens per session (2,018 once invoked), scanned A, original, MIT.

A release procedure for publishing the Kesha CLI and Engine. It covers version updates, tags, release workflows, package publishing, and checks for the resulting release.

In plain words
What is it for?
Use it to create stable, beta, or alpha versions and verify what the release workflow publishes and in what order.
Why use it?
It reduces mistakes when preparing releases across several package and build files. Publishing remains an explicit maintainer action.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

This is drakulavich/kesha-voice-kit's own configuration. It tells Claude Code how to work on kesha-voice-kit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kesha-voice-kit configures →

not rated 79repo changed 14d ago A scan 91 tokens original MIT
View source ↗ drakulavich/kesha-voice-kit drakulavich.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to drakulavich/kesha-voice-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/drakulavich/kesha-voice-kit/main/.claude/skills/release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/drakulavich/kesha-voice-kit

Made for: Claude Code.

Wrote 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.

agentmods badge for release

README.md
[![agentmods](https://agentmods.dev/badge/skills/drakulavich/kesha-voice-kit/release/github.svg)](https://agentmods.dev/skills/drakulavich/kesha-voice-kit/release)
Your own site
<a href="https://agentmods.dev/skills/drakulavich/kesha-voice-kit/release"><img src="https://agentmods.dev/badge/skills/drakulavich/kesha-voice-kit/release/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.

agentmods 80×15 button for release

Your own site · 80×15
<a href="https://agentmods.dev/skills/drakulavich/kesha-voice-kit/release"><img src="https://agentmods.dev/badge/skills/drakulavich/kesha-voice-kit/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,018 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00091 $0.02018
Opus 5.5 $0.00036 $0.00807
Sonnet 5.5 $0.00018 $0.00404
Haiku 4.5 $0.00009 $0.00202

Measured 14d ago against content hash de241f012c1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 14d 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.

.claude/skills/release/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

release

Cuts a release. Never auto-runs: the maintainer invokes /release vX.Y.Z (stable), /release beta X.Y.Z-beta.N or /release alpha. Pushing a tag and dispatching release.yml publish immediately and permanently; an agent does neither unless the maintainer asks in this conversation.

The model

  • One version. package.json#version names the CLI and the Engine; rust/Cargo.toml, rust/Cargo.lock and both server.json versions mirror it (bun run check:versions). main carries the next unreleased version: the post-release job opens a PR that leads it to the next minor after every stable release.
  • One workflow. .github/workflows/release.yml classifies the trigger (release-classify.ts). plan gates the run; build has three rows, one Cargo profile each, followed by darwin-synthesis-smoke and roundtrip-smoke. The stable-only packages job runs alongside those jobs. assemble waits for the build, smokes, and (on stable) packages; then github-release and npm packaging can run in parallel. npm-publish waits for both, followed by npm-smoke. Stable homebrew and docker jobs start after github-release and can overlap the npm smoke; stable post-release waits for both the GitHub release and npm smoke. A pull request that touches it runs the build and smoke rehearsal and publishes nothing.
  • The Engine pin is injected, never committed. npm writes package.json#kesha.engine = { version, sha256, size } from the release's SHA256SUMS and asset list (engine-pin.ts); kesha install refuses a download that does not match it. A source checkout carries no pin and verifies against the release's own SHA256SUMS.
  • Releases are immutable and tag names one-use. A release is published once, with every asset, by github-release; nothing is drafted. A broken release is fixed by the next patch, never by reusing its tag. Never tag to test: open a PR that touches release.yml for a rehearsal.
  • npm Trusted Publishing names release.yml. It is the only workflow that publishes, and the package trusts exactly one workflow; a second entry point 404s at the registry (#732).

Read the full file on GitHub · 64 lines

Changes

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.

  1. 14d ago Changed de241f012c1f
  2. 1mo ago Changed 50fa5d9a2198
  3. 1mo ago Changed 6b910b1f3739
  4. 1mo ago First seen · 64 lines · 91 tokens per session scan A 7e8af204b579

Subscribe to this mod's changes

release is a skill published in the GitHub repository drakulavich/kesha-voice-kit (79 stars, last pushed 3d ago), licensed MIT. It adds 91 tokens to every session and 2,018 once invoked, about $0.0004 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 2026-09-28.

Apple SiliconGit and workflowReleasesasrbuncoremlopenclawspeech-to-text
Related

release compared with skills from other repositories

release next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
releasedrakulavich/kesha-voice-kitSkill793d agoMITA91Claude Code
benchmarksoniqo/speech-swiftSkill1.3kyesterdayApache-2.0A0Claude Code
review-prsoniqo/speech-swiftSkill1.3kyesterdayApache-2.0A71Claude Code
commit-prZaxbyHub/opencode-swarmSkill518todayMITA100Codex
shipGCWing/BitFunSkill2.1k2mo agoMITA105Claude Code, Codex
contributingZaxbyHub/opencode-swarmSkill518todayMITA44Codex
release-aurFirstp1ck/pi-coding-agent-forgeSkill937d agoMITA57Claude Code, Codex