Vibe is a desktop application and command-line tool that transcribes audio and video locally on a user's device, turning speech into text and subtitle or document files. People use it for private transcription, translation, summaries, speaker labeling, and batch processing across supported desktop systems and models. The catalogue skill and instruction support working with Vibe.
Borrowing it
Nothing to install: this file belongs to thewh1teagle/vibe. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/thewh1teagle/vibe/main/.claude/skills/release/SKILL.mdgit clone --depth 1 https://github.com/thewh1teagle/vibeWrote 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/thewh1teagle/vibe/release)<a href="https://agentmods.dev/skills/thewh1teagle/vibe/release"><img src="https://agentmods.dev/badge/skills/thewh1teagle/vibe/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.
<a href="https://agentmods.dev/skills/thewh1teagle/vibe/release"><img src="https://agentmods.dev/badge/skills/thewh1teagle/vibe/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00071 | $0.01492 |
| Opus 5.5 | $0.00028 | $0.00597 |
| Sonnet 5.5 | $0.00014 | $0.00298 |
| Haiku 4.5 | $0.00007 | $0.00149 |
Grade A, and why
release scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl "$TUNNEL_URL/" # {"status":"ok"} How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release
Seven steps; stable comes later, when the user says so. Each has a gate — do not start the next one until the gate is green. Report the version, the run URLs and the gate results as you go; ask before skipping a step.
0. Preflight
git switch main && git pull --ff-only
git status --short # must be empty
1. Does server/ need a release first?
The desktop app downloads a pinned engine, so engine fixes only reach users through a new server release.
pin=$(cat .server-version) # e.g. v0.6.9
git log --oneline "server-${pin#v}"..main -- server/ 2>/dev/null ||
git log --oneline "server-$pin"..main -- server/
- No commits → skip to step 2, leave
.server-versionalone. - Only docs/comments → say so and ask whether to skip.
- Code changed → release the server first:
- If anything under
server/libs/changed (ggml-version,patches/,libs.chore,include/), bumpserver/libs/revisionin the same commit and runserver-libs.ymlfirst (~9 min);upload-libsrefuses a tag that exists for another tree. git tag server-vX.Y.Z && git push origin server-vX.Y.Zon main.- Gate:
server-release.ymlgreen (~8 min) and all 5 assets uploaded — the Intel Mac asset lands last. It publishes as a prerelease on purpose; leave it that way so Latest stays with the app.
- If anything under
2. Bump and write the notes
Three files, one commit:
desktop/src-tauri/tauri.conf.json→"version"..server-version→ the new server tag minusserver-(only if step 1 released one).i18n/changelog/<version>.md. release.yml fails without it.
If that file does not exist, write it. Read what actually shipped —
git log --oneline <previous tag>..main and the PR bodies — and write the entry
the way its neighbours are written: frontmatter (version, date, title), then
## New / ## Improved / ## Fixed sections of - 🎯 **Term** — what changed
bullets, keeping the (#1234) refs and @handle credits. Read the last two
entries first and match their voice: plain, concrete, user-visible. A refactor
nobody can see does not get a bullet.
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.
- 7d ago Changed · +12 lines 5edde3a9c5b0
- 1mo ago First seen · 133 lines · 71 tokens per session scan A 6b6d66b3a385
release is a skill published in the GitHub repository thewh1teagle/vibe (8,009 stars, last pushed 8d ago), licensed MIT. It adds 71 tokens to every session and 1,492 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-29.
release compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| releasethewh1teagle/vibe | Skill | 8.0k | 8d ago | MIT | A | 71 | Claude Code |
| land-and-deploygarrytan/gstack | Skill | 140k | today | MIT | A | 14 | Claude Code |
| publish-siteNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 19 | Claude Code, Codex |
| update-v8-versionopeninterpreter/openinterpreter | Skill | 69k | 2d ago | Apache-2.0 | A | 86 | Codex |
| codew-release-qa-sweepHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 31 | Claude Code, Codex |
| gh-credit-harvestHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 30 | Claude Code, Codex |
| release-publishrohitg00/ai-engineering-from-scratch | Skill | 77k | yesterday | MIT | A | 9 | Claude Code, Codex |