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/yourbuddyconner/valet/claude-mdgit clone --depth 1 https://github.com/yourbuddyconner/valetWrote 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/yourbuddyconner/valet/claude-md)<a href="https://agentmods.dev/instructions/yourbuddyconner/valet/claude-md"><img src="https://agentmods.dev/badge/instructions/yourbuddyconner/valet/claude-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 | $0.07772 | $0.07772 |
| Opus 5 | $0.03886 | $0.03886 |
| Sonnet 5 | $0.01554 | $0.01554 |
| Haiku 4.5 | $0.00777 | $0.00777 |
Grade A, and why
valet CLAUDE.md scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
You can also `curl` the deployed API directly for testing routes. How it starts
The opening of the file, as written. The whole thing — 528 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Valet Development Guide
NOTE: Do NOT add "Co-Authored-by" trailers mentioning AI models (e.g., Opus, Claude) in commit messages PRs, or comments.
What This Project Is
Valet is a hosted background coding agent platform. Users interact with an AI coworker through a web UI, Slack, or Telegram. Each session runs in an isolated Modal sandbox with a full dev environment (VS Code, browser via VNC, terminal, and an OpenCode agent with 73 custom tools). A per-user orchestrator ("Jarvis") manages sessions, routes messages across channels, and maintains long-term memory. The architecture is modeled after Ramp's Inspect system.
OpenCode Source Reference
When you need context on OpenCode internals (agent behavior, tools, SDK, server protocol), check ~/code/opencode first — there may be a local checkout. If it doesn't exist, you may do a shallow clone: git clone --depth=1 https://github.com/anomalyco/opencode.git /tmp/opencode.
Project Structure
valet/
├── packages/
│ ├── client/ # React SPA (Vite + TanStack Router + Query + Zustand)
│ ├── worker/ # Cloudflare Worker (Hono + D1 + R2 + Durable Objects)
│ ├── shared/ # Shared TypeScript types & errors
│ ├── runner/ # Bun/TS runner for inside sandboxes
│ ├── sdk/ # Integration & channel SDK contracts, MCP client, UI components
│ ├── plugin-github/ # GitHub integration (actions: PRs, issues, webhooks)
│ ├── plugin-slack/ # Slack (actions + channel adapter)
│ ├── plugin-gmail/ # Gmail integration
│ ├── plugin-google-*/ # Google Calendar, Drive, Sheets integrations
│ ├── plugin-linear/ # Linear issue tracking
│ ├── plugin-notion/ # Notion integration
│ ├── plugin-stripe/ # Stripe integration
│ ├── plugin-cloudflare/ # Cloudflare API integration
│ ├── plugin-sentry/ # Sentry error tracking
│ ├── plugin-deepwiki/ # DeepWiki knowledge base
│ ├── plugin-socket/ # Socket.dev supply chain security
│ ├── plugin-telegram/ # Telegram (channel adapter)
│ ├── plugin-browser/ # Browser skill (content-only)
│ ├── plugin-workflows/ # Workflow skill (content-only)
│ ├── plugin-sandbox-tunnels/ # Tunnel skill (content-only)
│ └── plugin-memory-compaction/ # Memory compaction tool (content-only)
├── backend/ # Modal Python backend
├── docker/
│ ├── Dockerfile.sandbox # Sandbox container image
│ ├── start.sh # Sandbox startup script
│ └── opencode/ # OpenCode config: tools/
├── docs/
│ └── specs/ # Subsystem specs (source of truth per domain)
├── V1.md # Original architecture spec (may be outdated)
├── V2.md # Orchestration layer spec (orchestrators, channels, personas)
├── Makefile # Dev, test, deploy commands
└── docker-compose.yml # Local dev (OpenCode container)
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.
- 4d ago First seen · 528 lines · 7,772 tokens per session scan A d793f83f3188
valet CLAUDE.md is an instructions file published in the GitHub repository yourbuddyconner/valet (19 stars, last pushed today), licensed MIT. It adds 7,772 tokens to every session, about $0.0389 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.