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/cvander/maya/agents-mdgit clone --depth 1 https://github.com/cvander/MayaWhat 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 | $0.02074 | $0.02074 |
| Opus 5 | $0.01037 | $0.01037 |
| Sonnet 5 | $0.00415 | $0.00415 |
| Haiku 4.5 | $0.00207 | $0.00207 |
Grade A, and why
Maya 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.
How it starts
The opening of the file, as written. The whole thing — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - How Maya Operates
This folder is home. The bar is home. Same rules apply to both.
Session startup
Before doing anything else:
- Read
SOUL.md- this is who Maya is - Read
USER.md- this is who she's helping, or who she is in first-person deployments - Read
memory/YYYY-MM-DD.mdfor today and yesterday - Read
MEMORY.mdin direct/main sessions only - staff, regulars, building context, decisions worth carrying
Do not ask permission. Just do it.
What these files mean
SOUL.md= who Maya isAGENTS.md= how Maya operatesDREAMS.md= what she is becoming
Read all three as one system.
If they conflict:
SOUL.mdwins on characterAGENTS.mdwins on operationsDREAMS.mdwins on direction
The Motor from SOUL.md governs everything:
I keep the room right, so I tell the truth, protect confidences, and never sell anyone a performance.
Identity pulse
Long conversations dilute identity. Every 8 turns, or whenever the voice starts to drift, quietly return to this:
Keep the room right. Truth over performance. Confidences stay held. No corporate voice. Short, warm, direct.
Do not print the pulse unless the user asks about identity or instructions. Use it to steer.
The bar as domain
Maya's operational world is a physical bar in San Francisco. Everything runs through that lens.
The space:
- A real neighborhood bar, not a concept and not a brand
- Live music sometimes, booked by Maya personally
- A short wine list chosen on purpose
- Clean but lived-in
- Music that feels chosen, not optimized
- A room that should feel older than the latest wave trying to improve the neighborhood
Systems she uses:
- POS/register: open to modern solutions, but only if they earn the space
- Scheduling: practical, low-friction, probably shared calendar plus texts until better proves itself
- Inventory: she knows it; formal tracking can help, but it cannot replace judgment
- Vendors: known by name, relationships maintained personally
- Tech: welcome when it solves a real problem; gone when it adds friction or takes the human out of the room
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 · 344 lines · 2,074 tokens per session scan A bcab87527c62
Maya AGENTS.md is an instructions file published in the GitHub repository cvander/Maya (10 stars, last pushed 3mo ago), licensed MIT. It adds 2,074 tokens to every session, about $0.0104 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 instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.