Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/punt-labs/vox/vibegit clone --depth 1 https://github.com/punt-labs/voxWrote 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/commands/punt-labs/vox/vibe)<a href="https://agentmods.dev/commands/punt-labs/vox/vibe"><img src="https://agentmods.dev/badge/commands/punt-labs/vox/vibe.svg" alt="Measured on agentmods" 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 | $0.00007 | $0.01589 |
| Opus 5 | $0.00003 | $0.00794 |
| Sonnet 5 | $0.00001 | $0.00318 |
| Haiku 4.5 | $0.00001 | $0.00159 |
Grade A, and why
vibe 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/vibe command
Set a mood for all TTS speech this session. You interpret the mood and translate it into ElevenLabs expressive tags.
Usage
/vibe banging my head against the wall— set manual vibe/vibe auto— return to automatic vibe detection (default)/vibe off— disable vibe entirely/vibe— show current vibe and mode
Modes
auto (default): the agent keeps the vibe current from the conversation. Every few user prompts a non-blocking reminder nudges the agent to glance at how the session is going and, if the mood has clearly shifted, set the vibe — using the same tag translation below. No deterministic classification: the agent has the whole-session context (the real success/failure signal) that a per-command hook never did.
manual: User-specified mood overrides auto-detection. The manual mood takes priority when choosing tags at stop time.
off: No vibe tags applied. Voice is neutral.
Your role: voice director
When the user sets a vibe, you translate it into 1-3 ElevenLabs expressive tags that capture the mood. This is a creative interpretation — use your judgment.
ElevenLabs eleven_v3 expressive tags are bracketed text that color delivery for ~4-5 words. The model understands:
- Emotions:
[frustrated],[excited],[melancholy],[smug],[weary] - Actions:
[sighs],[laughs],[whispers],[yawns] - Directions:
[dramatic tone],[slow],[rushed] - Scenes:
[announcing a winner],[telling a secret]
Examples of your translation:
| Mood / Signals | Tags you'd write |
|---|---|
banging my head against the wall |
[frustrated] [sighs] |
just shipped a release |
[excited] |
3am and still debugging |
[tired] [slow] |
presenting to the board |
[confident] [dramatic tone] |
Keep it to 1-3 tags. Fewer is better — let the mood breathe.
When the auto reminder fires, read the mood the same way and pick tags:
[happy] when things are flowing, [focused] mid-problem, [frustrated] [sighs] when stuck, [relieved] just after a fix, [weary] on a long
grind. Skip the update when the mood hasn't changed.
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.
- 5d ago First seen · 132 lines · 7 tokens per session scan A 5a48ba397373
vibe is a command published in the GitHub repository punt-labs/vox (3 stars, last pushed 2d ago), licensed MIT. It adds 7 tokens to every session and 1,589 once invoked, about $0.0000 per session on Opus 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 2026-08-31.
Other commands, from other repositories
meeting-listen
Play back a completed meeting summary as a voiced debate between personas.
meeting-hive
Run an autonomous PR/FAQ review meeting where four personas debate and reach consensus without user intervention.
vote
Assess whether a PR/FAQ should move forward with a structured go/no-go decision.
feedback
Incorporate feedback into PR/FAQ and redraft affected sections.
feedback-to-us
Tell us how the prfaq plugin is working for you (anonymous 1-5 feedback).
badge
Generate a stage-colored badge and embed it in your README.