kesha-voice-kit: Skill for Claude Code

.claude/skills/release-engine/SKILL.md

release-engine is a skill for Claude Code from drakulavich/kesha-voice-kit. It costs 97 tokens per session (2,380 once invoked), scanned A, original, MIT.

A controlled procedure for releasing the Kesha engine with a version tag, pre-release checks, validation, publishing, and post-release verification. It is separate from the CLI release line, which uses a different tag format.

In plain words
What is it for?
Use it to release a specified engine version, audit the repository, bump only the engine version, validate downloads, publish the release, and verify the result.
Why use it?
It catches release problems before tagging and accounts for the fact that a tagged workflow uses the workflow file stored at that tag. It requires the user to explicitly start the release.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions CLAUDE.md; positional $N argument.

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 →

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-engine/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-engine

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/drakulavich/kesha-voice-kit/release-engine"><img src="https://agentmods.dev/badge/skills/drakulavich/kesha-voice-kit/release-engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,380 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00097 $0.02380
Opus 5 $0.00048 $0.01190
Sonnet 5 $0.00019 $0.00476
Haiku 4.5 $0.00010 $0.00238

Measured 5d ago against content hash 4452bff19364, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

release-engine scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Draft asset URLs return **404 to unauthenticated clients**, so `curl` and `just smoke-test` can false-green through a stale global install. Download with `gh`:
.claude/skills/release-engine/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

release-engine

Cuts a kesha-engine release. NEVER auto-runs — user invokes via /release-engine vX.Y.Z.

For a CLI release (vX.Y.Z-cli, npm) use the release-cli skill instead. The two are independent version lines; a full ship is usually /release-engine then /release-cli.

Inputs

  • $1: target tag, e.g. v1.24.9. Bare — no -cli suffix. -beta.N / -alpha.N are prerelease shapes; alphas are dispatched, not tagged by hand (see release-mechanics).

THE TRAP THAT COSTS A TAG

The workflow GitHub runs for a tag is the one stored at that tag. A fix merged to main afterwards cannot rescue it, and re-running the failed job re-runs the broken definition. If the release job fails for a reason living in the workflow itself, that tag is dead — tag names are one-use, so you bump the patch and cut a new one. (v1.24.8 was lost exactly this way.)

Corollary: when the workflow on main is already fixed but a tag is not, release via workflow_dispatch --ref main, which runs main's definition:

gh workflow run "🔨 Build Engine" -R drakulavich/kesha-voice-kit \
  -f tag=vX.Y.Z -f ref=main -f notes="$(cat notes.md)"

Pre-flight (run BEFORE bumping versions)

# 1. Root checkout clean, on main, up to date. Edit in a worktree, never here.
git fetch origin main && git status -sb | head -3

# 2. Every additive cargo default in every matrix row — v1.1.0 shipped without TTS when this drifted.
grep -E '^\s+features:' .github/workflows/build-engine.yml
grep '^default =' rust/Cargo.toml

# 3. CI green on main
gh run list --workflow ci.yml --branch main --limit 1
gh run list --workflow rust-test.yml --branch main --limit 1

# 4. Local sanity — fmt is checked here because preflight formats in place and cannot fail on it
cargo fmt --check --manifest-path rust/Cargo.toml
just ALL=1 preflight

If anything fails, STOP. Do not bump versions. A failure that does not reproduce on a second run is still a failure — confirm against CI on the same SHA rather than chasing it.

Read the full file on GitHub · 154 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. 5d ago Changed · -3 lines 4452bff19364
  2. 10d ago First seen · 157 lines · 97 tokens per session scan A 1eb1d9982b4d

Subscribe to this mod's changes

release-engine is a skill published in the GitHub repository drakulavich/kesha-voice-kit (73 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 2,380 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

ship

Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", "merge and push", or "get it deployed". Proactively invoke this skill (do NOT push/PR directly) when the user says code is…

GCWing/BitFun · 105 tokens

github-repo-management

Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.

moltis-org/moltis · 47 tokens

benchmark

Run performance + quality benchmarks. ASR reports WER, RTF, process memory, and throughput across engines/variants. Arguments include asr, tts, vad, diarize, asr-quick.

soniqo/speech-swift · 0 tokens

review-pr

Review a pull request for conceptual fit, architecture impact, adversarial failure modes, security risk, docs impact, regression risk, test coverage, and merge readiness. Use when asked to review a PR, check whether a PR is safe to merge, decide if more tests are needed, perform adversarial or security review, or…

soniqo/speech-swift · 71 tokens

commit-pr

Mandatory Codex/Copilot publication adapter for opencode-swarm. Use for every GitHub issue assignment that results in code changes, commits, pushes, draft PRs, PR body edits, PR readying, release notes, or CI closeout. Must be loaded before git push, gh pr create, gh pr edit, or gh pr ready. Routes to the single…

ZaxbyHub/opencode-swarm · 100 tokens

contributing

Codex adapter for the opencode-swarm contribution checklist. Use when preparing user-visible changes, release note fragments, local validation, branch hygiene, PR checklist items, or contribution-policy compliance before publishing work.

ZaxbyHub/opencode-swarm · 44 tokens