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/AGENTS.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/instructions/thewh1teagle/vibe/agents-md)<a href="https://agentmods.dev/instructions/thewh1teagle/vibe/agents-md"><img src="https://agentmods.dev/badge/instructions/thewh1teagle/vibe/agents-md/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/instructions/thewh1teagle/vibe/agents-md"><img src="https://agentmods.dev/badge/instructions/thewh1teagle/vibe/agents-md.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 | $0.00368 | $0.00368 |
| Opus 5.5 | $0.00147 | $0.00147 |
| Sonnet 5.5 | $0.00074 | $0.00074 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
vibe AGENTS.md 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 1mo 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.
What it actually says
Claude Development Notes
Tooling
- Tasks:
chore— seechore list - JS:
pnpmonly; Python:uvstandalone scripts (uv run)
Validation
Plan validation scripts: plans/<name>/<name>_001.py (+ .md), standalone uv scripts.
Skills
Custom skills live in .claude/skills/<name>/SKILL.md.
Execution Mindset
Agent mode: parallel moves, instant iteration, speed by default. Split heavy work until obvious. Estimate by output size — 300 lines = minutes. Correct over easy: rework is slower than doing it right once. Plan resolved → execute, don't re-analyze.
Working in parallel
Split large work across ~4–5 subagents, one disjoint module-group each — no shared files; only the coordinator touches shared/root config. Fix contracts (interfaces, design docs) up front. Throughput is per-agent (~100 tok/s, no global limit), so N agents ≈ N× speed — delegate bulk implementation to strong subagents (e.g. Opus 5 for correctness-sensitive code); keep the main loop for planning, contracts, and integration.
ETA rule
Quote minutes, never days: single tasks 1–10 min, multi-agent work tens of minutes.
minutes ≈ (LOC × 40) / (6000 × N_agents) + ~2 min per stage
File size
700 lines max. On hitting it, ask before splitting.
Split by responsibility into halves — find where the file does two jobs and move one out whole. Not a line-count cut, not a utils skim. Keep the public API where callers expect it; move tests with their code.
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.
- 1mo ago Changed · +8 tokens per session e92d5e6009fb
- 2mo ago First seen · 37 lines · 360 tokens per session scan A 58acc07f789c
vibe AGENTS.md is an instructions file published in the GitHub repository thewh1teagle/vibe (8,009 stars, last pushed 8d ago), licensed MIT. It adds 368 tokens to every session, about $0.0015 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 2026-08-30.
vibe AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vibe AGENTS.mdthewh1teagle/vibe | Instructions file | 8.0k | 8d ago | MIT | A | 368 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |