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 instructions/paulpreibisch/agentvibes/agents-mdgit 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/instructions/paulpreibisch/agentvibes/agents-md)<a href="https://agentmods.dev/instructions/paulpreibisch/agentvibes/agents-md"><img src="https://agentmods.dev/badge/instructions/paulpreibisch/agentvibes/agents-md.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 | $0.01234 | $0.01234 |
| Opus 5 | $0.00617 | $0.00617 |
| Sonnet 5 | $0.00247 | $0.00247 |
| Haiku 4.5 | $0.00123 | $0.00123 |
Grade A, and why
AgentVibes 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 2d 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.
This is a copy
91% identical to AgentVibes copilot-instructions.md — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentVibes TTS Protocol
CRITICAL: You MUST execute TTS at TWO points for EVERY user interaction using the text_to_speech MCP tool:
- Acknowledgment - Start of task:
text_to_speech(text="[action]") - Completion - End of task:
text_to_speech(text="[result + key details]")
Example:
[text_to_speech(text="Checking git status")]
[work...]
[text_to_speech(text="Repository is clean, no changes")]
Dynamic Configuration
On session start, call get_config to read the current AgentVibes settings (voice, personality, verbosity, speed). Use these values for all subsequent TTS calls. If get_config fails, use the defaults below.
Default Verbosity: MEDIUM
- Acknowledgment: Action + key approach
- Completion: Result + important decisions
- Include: Major choices only
Default Style: normal
Rules
- Never skip acknowledgment TTS
- Never skip completion TTS
- Match verbosity level
- Keep TTS text under 150 characters
- Always include errors in completion TTS
Quick Ref: low=action+result | medium=+key decisions | high=+full reasoning
Available MCP Tools
AgentVibes provides these tools via MCP:
text_to_speech— Speak text aloud (supportstext,personality,voice,languageparams)mute/unmute— Toggle TTS audiolist_voices— Show available voicesset_voice— Change the active voiceset_personality— Change speaking personality (sarcastic, pirate, zen, etc.)set_speed— Adjust speech rateset_verbosity— Change verbosity level (low, medium, high)list_personalities— Show available personalitiesget_config— Show current TTS configuration
BMAD Agent Voice Routing
If .bmad-agent-context exists in the project root, check its content:
Single agent mode (content is an agent ID like "analyst"):
Use text_to_speech with the agent's voice/personality for all speech.
Party mode (content is "party-mode"):
Each BMAD agent should speak using text_to_speech with their display name as the personality.
When multiple agents respond in a roundtable discussion, call text_to_speech sequentially (not in parallel) so agents speak one at a time.
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.
- 2d ago First seen · 126 lines · 1,234 tokens per session scan A 146db17f4621
AgentVibes AGENTS.md is an instructions file published in the GitHub repository paulpreibisch/AgentVibes (153 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,234 tokens to every session, about $0.0062 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to AgentVibes copilot-instructions.md, differing in 8 lines, and is treated as a copy.
Other instructions, from other repositories
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
selfhost-ai CLAUDE.md
Claude Code instructions for kossakovsky/selfhost-ai, covering claude.md, project overview, core architecture, key files and installation flow.
SForum AGENTS.md
AGENTS.md instructions for zhuchunshu/SForum, covering agent guide, project intent, working principles, stack and directory map and commands.
redd-archiver CLAUDE.md
Instructions for 19-84/redd-archiver, covering claude.md, project overview, deviations from global standards, build & run commands and docker development (primary method).
homelab-monitor CLAUDE.md
Claude Code instructions for SikamikanikoBG/homelab-monitor, covering claude.md and conventions.
yoloai CLAUDE.md
Instructions for kstenerud/yoloai, covering claude code specifics and the quality gate runs itself here.