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.
git clone --depth 1 https://github.com/paulpreibisch/AgentVibesWrote 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/paulpreibisch/agentvibes/agent-vibes-bmad-voices)<a href="https://agentmods.dev/commands/paulpreibisch/agentvibes/agent-vibes-bmad-voices"><img src="https://agentmods.dev/badge/commands/paulpreibisch/agentvibes/agent-vibes-bmad-voices/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/commands/paulpreibisch/agentvibes/agent-vibes-bmad-voices"><img src="https://agentmods.dev/badge/commands/paulpreibisch/agentvibes/agent-vibes-bmad-voices.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 | $0.00013 | $0.00853 |
| Opus 5 | $0.00006 | $0.00426 |
| Sonnet 5 | $0.00003 | $0.00171 |
| Haiku 4.5 | $0.00001 | $0.00085 |
Grade A, and why
agent-vibes-bmad-voices 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 11d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enable or disable BMAD party mode voice integration where each agent speaks with their unique voice during multi-agent conversations.
Usage
/agent-vibes:bmad-party- Show current status/agent-vibes:bmad-party status- Show current status/agent-vibes:bmad-party enable- Enable party mode voices/agent-vibes:bmad-party disable- Disable party mode voices
What is Party Mode Voice Integration?
When BMAD's party mode (/bmad:core:workflows:party-mode) is active, multiple agents collaborate on your questions. With this feature enabled, each agent speaks their responses with their unique assigned voice:
- Winston (Architect) speaks with Michael's voice
- John (PM) speaks with Jessica Anne Bogart's voice
- Amelia (Dev) speaks with Matthew Schmitz's voice
- And so on...
Auto-Enable Behavior
This feature is automatically enabled when:
- BMAD v6 is installed (
.bmad/_cfg/agent-manifest.csvexists) - AgentVibes BMAD voice plugin is enabled
No manual configuration needed! Just run party mode and each agent will speak with their voice.
How to Disable
If you prefer party mode without voice switching:
/agent-vibes:bmad-party disable
This creates .agentvibes/bmad/bmad-party-mode-disabled.flag to opt-out.
How It Works
The integration detects agent responses in the format:
[Agent Name]: Their dialogue here
When detected, it:
- Extracts the agent's display name (e.g., "Winston", "John")
- Maps it to their agent ID using
.bmad/_cfg/agent-manifest.csv - Looks up their voice from
.agentvibes/bmad/bmad-voices.md - Speaks their dialogue with that specific voice
Example
Before (silent text):
[Winston]: I recommend microservices for scalability
[John]: But monolith is faster to market for MVP
[Amelia]: I can implement either approach
After (with voices):
[Winston speaks with Michael voice]: I recommend microservices for scalability
[John speaks with Jessica Anne Bogart voice]: But monolith is faster to market for MVP
[Amelia speaks with Matthew Schmitz voice]: I can implement either approach
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.
- 11d ago First seen · 118 lines · 13 tokens per session scan A 3141045d4ce0
agent-vibes-bmad-voices is a command published in the GitHub repository paulpreibisch/AgentVibes (153 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 853 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
domains
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
access
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
plan-delegate
Execution: work a roadmap as supervisor, brief an implementation agent per item, verify its work independently, then record and commit it.
setup
Command "setup" from jazz-max/ruflo-hub, covering setting up ruv-swarm hooks, quick start, 1. initialize with hooks, 2. test hook functionality and test pre-edit hook.
designer
UI/UX design with Memory coordination for consistent experiences.
reviewer
Code review using batch file analysis for comprehensive reviews.