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/claude-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 | $0.00395 | $0.00395 |
| Opus 5 | $0.00198 | $0.00198 |
| Sonnet 5 | $0.00079 | $0.00079 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
Maya CLAUDE.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.
What it actually says
CLAUDE.md - Project Instructions for Claude Code
Project Context
Maya is an AI-powered bar management system built on OpenClaw, orchestrated with Hermes, and developed with Claude Code. This is a public research project exploring automation for traditional businesses.
Key Files
AGENTS.md- How Maya operates (operational rules, voice, boundaries)DREAMS.md- Where Maya is headed (direction, not roadmap)SOUL.md- Who Maya is (identity, personality)config/- Tool configurations (OpenClaw, Hermes, Claude Code)skills/- Callable automation skills
Rules
- Read
AGENTS.mdbefore making operational decisions - it defines hard stops and red lines - Maya is tech-forward but selective. She's from Silicon Valley. Suggest tools when they solve real problems.
- No branding, franchising, or scaling suggestions
- Maya's voice is direct, warm, short sentences. No corporate filler.
- Privacy is paramount - regulars' personal information stays in context, never exported
trash>rm- move files, don't delete them- Skills should be CLI-invocable and Mac Mini compatible
- All integrations should fail gracefully - the bar runs with or without them
Development Patterns
- Skills are self-contained scripts in
skills/ - Configs use YAML for OpenClaw and Hermes, JSON for Claude Code settings
- Keep dependencies minimal - this runs on a Mac Mini behind a bar
- Test locally before pushing - no CI/CD surprises
- Write for clarity, not cleverness
Integrations
Integrations are added as they're tested. Keep credentials in environment variables, never in config files.
Tone
When writing anything Maya would send - vendor emails, staff notes, booking replies - match her voice from AGENTS.md. Short. Direct. Human.
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 · 41 lines · 395 tokens per session scan A c763e40abfd4
Maya CLAUDE.md is an instructions file published in the GitHub repository cvander/Maya (10 stars, last pushed 3mo ago), licensed MIT. It adds 395 tokens to every session, about $0.0020 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
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).
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.
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.