Borrowing it
Nothing to install: this file belongs to runvendo/vendo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/runvendo/vendo/main/CLAUDE.mdgit clone --depth 1 https://github.com/runvendo/vendoWrote 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/runvendo/vendo/claude-md)<a href="https://agentmods.dev/instructions/runvendo/vendo/claude-md"><img src="https://agentmods.dev/badge/instructions/runvendo/vendo/claude-md/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/instructions/runvendo/vendo/claude-md"><img src="https://agentmods.dev/badge/instructions/runvendo/vendo/claude-md.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 | $0.02968 | $0.02968 |
| Opus 5.5 | $0.01187 | $0.01187 |
| Sonnet 5.5 | $0.00594 | $0.00594 |
| Haiku 4.5 | $0.00297 | $0.00297 |
Grade A, and why
vendo 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 1mo 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vendo
Vendo is a devtool that lets a company's users customize its product: an embedded agent that acts through the host's own API as the user and renders generated UI in a sandboxed, brand-native surface.
Layout
packages/— two published packages: the@vendoai/vendoumbrella and thevendoaialias. The ten blocks are no longer packages of their own — they folded into the umbrella and survive as its subpath exports (/core,/ui,/store,/actions,/guard,/apps,/automations,/knowledge,/mcp,/telemetry), backed by directories underpackages/vendo/src/. The behavior contract is the exported types/zod schemas and the test suites — there are no prose contract docs; layering enforced byscripts/dependency-guard.mjsinpnpm lintexamples/— the demo hostdemo-bank(Maple) and the framework integration examples (ai-sdk-agent,mastra-agent,claude-code-plugin)corpus/— init-extraction corpus harness (pnpm corpus)docs-site/— the public docs site
Commands
pnpm install·pnpm typecheck·pnpm lint(turbo-cached) — the local looppnpm build·pnpm test·pnpm test:affected(changed packages only) — on demand, not required before a PR- Demo:
pnpm --filter demo-bank dev(Maple)
Vendo Cloud
- Cloud sells exactly two categories: infrastructure that is painful to run yourself (sandbox, inference, persistence, brokers, hosted automations) and inherently multi-party coordination (sharing, registry, orgs, SSO, billing, console). Everything else stays OSS.
- Hard BYO rule: every single-player capability keeps a no-key bring-your-own path (own Postgres, sandbox account, model key, OAuth apps).
- Adapter rule: one adapter interface per block; Cloud is just another
implementation shipped in OSS.
VENDO_API_KEYsets Cloud defaults only for adapter slots the host left unset; an explicitly passed adapter always wins; no hidden key-conditional branches. Reference implementation:selectConnectionsinpackages/vendo/src/compose-selection.ts. - Gating is valid key + meter, nothing else: no capability booleans, no entitlement protocol, no validate endpoint, no client-side checks. Key problems surface on the first real service call.
- Managed inference rides the console's Anthropic-compatible model gateway
through the stock
@ai-sdk/anthropicprovider, so inference traffic does not carry the deployment-identity headers and does not feed the deployment inventory (known, accepted).
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.
- 1mo ago Changed · +38 lines · +718 tokens per session 909a5971714b
- 1mo ago First seen · 141 lines · 2,250 tokens per session scan A 69652081bda5
vendo CLAUDE.md is an instructions file published in the GitHub repository runvendo/vendo (633 stars, last pushed 11d ago), licensed Apache-2.0. It adds 2,968 tokens to every session, about $0.0119 per session on Opus 5.5. 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 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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.