kesha-voice-kit: Skill for Claude Code

.claude/skills/verify-pin-bump/SKILL.md

verify-pin-bump is a skill for Claude Code from drakulavich/kesha-voice-kit. It costs 96 tokens per session (1,692 once invoked), scanned C, original, MIT.

A safety procedure for changing the SHA-256 checksum recorded for downloaded Kesha voice models. SHA-256 is a fingerprint used to check that a downloaded file is the expected file.

In plain words
What is it for?
Use it when a model download fails its checksum check, model manifest tests fail, a mirror returns different weights, or an upstream Hugging Face model was republished.
Why use it?
It prevents a model download from being accepted after the file changes unexpectedly, including when a mirror may be unsafe. It guides deliberate verification before changing the recorded fingerprint.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

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 →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is KESHA_CACHE_DIR=/tmp/pin-bump ./rust/target/release/kesha-engine install --tts.

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/verify-pin-bump/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 verify-pin-bump

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/drakulavich/kesha-voice-kit/verify-pin-bump"><img src="https://agentmods.dev/badge/skills/drakulavich/kesha-voice-kit/verify-pin-bump.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,692 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00096 $0.01692
Opus 5 $0.00048 $0.00846
Sonnet 5 $0.00019 $0.00338
Haiku 4.5 $0.00010 $0.00169

Measured 7d ago against content hash 875ccdeab711, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

verify-pin-bump scanned grade C with 2 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 7d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf /tmp/pin-bump-cache

Makes network callslowCapability

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

# or, for a single file, curl directly from the URL in models/manifest.rs:
.claude/skills/verify-pin-bump/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

verify-pin-bump

Why this skill exists

CLAUDE.md "MODEL HASHES ARE PINNED" rule:

Every entry in rust/src/models/manifest.rs (ASR, lang-id, TTS) carries a pinned SHA-256. download_verified refuses to cache a file whose hash doesn't match. This makes KESHA_MODEL_MIRROR safe (a compromised mirror can't silently swap weights) and turns an upstream HuggingFace republish into a deliberate decision rather than a silent swap.

The pin exists because of incident #174 — a previous regression where verification was disabled "to get it working". Bumping the pin without confirming the new weights are intentional re-introduces that risk.

Hard NO

  • ❌ Do NOT comment out download_verified to "make it work".
  • ❌ Do NOT silently update the SHA without checking what changed upstream.
  • ❌ Do NOT use KESHA_MODEL_MIRROR= to bypass — the mirror produces the same hash check.

Procedure

Step 1: Identify which pin failed

The error message names the file. Find its ModelFile entry in rust/src/models/manifest.rs:

grep -n "sha256:" rust/src/models/manifest.rs | head -40
# locate the entry whose URL or rel_path matches the failing download

Step 2: Re-download cleanly

Wipe the existing cache for that file (it may be a partial / corrupted download), then re-download:

rm -f ~/.cache/kesha/models/<subdir>/<file>
KESHA_CACHE_DIR=/tmp/pin-bump ./rust/target/release/kesha-engine install --tts
# or, for a single file, curl directly from the URL in models/manifest.rs:
curl -fsSL "<url-from-models-manifest-rs>" -o /tmp/pin-bump-file

Step 3: Compute the actual hash

shasum -a 256 ~/.cache/kesha/models/<subdir>/<file>
# or
shasum -a 256 /tmp/pin-bump-file

Compare to:

  • The pin in rust/src/models/manifest.rs
  • The HuggingFace UI's reported SHA (open the file URL, click "Copy SHA")

Step 4: Decide intentional vs incident

Three possible scenarios:

A. Upstream legitimately re-published. Verify by checking the HF repo's commit history:

Read the full file on GitHub · 161 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. 7d ago Changed · -17 lines · +31 tokens per session 875ccdeab711
  2. 11d ago First seen · 178 lines · 65 tokens per session scan C 72b700f2d445

Subscribe to this mod's changes

verify-pin-bump is a skill published in the GitHub repository drakulavich/kesha-voice-kit (73 stars, last pushed yesterday), licensed MIT. It adds 96 tokens to every session and 1,692 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, 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

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

delive-transcript-analyzer

Analyze, summarize, and extract insights from DeLive transcription sessions. Use when: user mentions DeLive, transcription, meeting transcripts, live captions, audio transcription, AI correction, corrected transcript, or transcript analysis; user wants to search, retrieve, summarize, correct, or process recorded…

XimilalaXiang/DeLive · 98 tokens

whisper

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual…

davila7/claude-code-templates · 67 tokens

yw-transcribe

A workflow for transcribing one local audio or video file into a traceable Chinese or mixed Chinese-English transcript, with optional timestamps and subtitle files.

yuwen-cool/yw-transcribe · 131 tokens

gguf-quantization

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

synthetic-sciences/openscience · 48 tokens