A setup guide for adding Vendo, an agent that works inside an existing product as its signed-in user, to a code repository. It covers installation, configuration, and checks that the setup works.

Use it to install Vendo, run its initialization and diagnostic commands, connect its handler or provider, and troubleshoot the integration.

It removes the need to work out the package installation, authentication choices, generated files, and verification steps by hand.

vendo-setup — Skill for Claude Code and Codex by runvendo

Install

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.

Any agent

npx skills add runvendo/vendo --skill vendo-setup

Clone the repo

git clone --depth 1 https://github.com/runvendo/vendo

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/runvendo/vendo/vendo-setup.svg)](https://agentmods.dev/skills/runvendo/vendo/vendo-setup)

Your own site

<a href="https://agentmods.dev/skills/runvendo/vendo/vendo-setup"><img src="https://agentmods.dev/badge/skills/runvendo/vendo/vendo-setup.svg" alt="Measured on agentmods" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,047 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 13 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Privilege Escalation · line 90
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
medium MCP Rug Pull · line 26
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 36
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 37
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 100
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 106
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 112
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 124
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 128
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 141
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 142
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 147
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 157
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00056	$0.02047
Opus 5	$0.00028	$0.01024
Sonnet 5	$0.00011	$0.00409
Haiku 4.5	$0.00006	$0.00205

Measured 8d ago against content hash 6db81a72d8d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

vendo-setup 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 8d 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.

packages/vendo/skills/vendo-setup/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vendo setup

Vendo embeds an agent inside a host product: it extracts the host's API as tools, renders generated UI in a sandboxed brand-native surface, and acts as the signed-in user. This skill installs and verifies Vendo in a host repo.

The canonical agent playbook lives at https://vendo.run/agents.md — fetch it when you need more detail than this skill carries.

Stage 1 — base install

Install the umbrella package (either name; vendoai is a thin alias):
```
npm install @vendoai/vendo
```
Run init. It asks first, then writes:
```
npx vendo init --agent
```
Init detects the stack and prints ONE JSON object. {"status": "questions", …} means it wrote nothing: relay every prompt to the user VERBATIM in chat, with its options. Each option carries the literal thing you do to pick it, a flag for the re-run or a command to run first. Then re-run with every answer:
```
npx vendo login --wait 90                          # only if they picked the free Cloud key
npx vendo init --agent --use-case embedded --auth clerk --byo
```
That run writes, narrates itself, and ends on the receipt, the LAST JSON object it prints: {"status": "written", …} with wrote (the files it created), detected (framework, auth, package manager, port), guardPosture, continueUrl (the ONE page carrying the instructions for the use case you picked), keptUncertain, pendingLoosenings, and judgment. judgment is graded with the file it wrote when a judgment engine resolved on this machine, and delegated with a checklist that is yours to work through when none did — read it, do not assume either. Both runs exit 0, so branch on status, never on the exit code. All answers on the first call and it writes in one pass.

Never relay a mechanical question. The zod floor and the theme slots are never asked: they take their defaults and show up in the diff. The one question about SPENDING — may a coding agent read this codebase — is asked up front with the others, never mid-run, so a run that has started writing will not stop to ask you anything.

Read the full file on GitHub · 160 lines

Changes

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.

8d ago First seen · 160 lines · 56 tokens per session scan A 6db81a72d8d2

Subscribe to this mod's changes

vendo-setup is a skill published in the GitHub repository runvendo/vendo (608 stars, last pushed 6d ago), licensed Apache-2.0. It adds 56 tokens to every session and 2,047 once invoked, about $0.0003 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 2026-08-30.

Building agents agents ai ai-agents automation devtools embedded-ai

jk

Manage Jenkins controllers with jk, including jobs, runs, logs, artifacts, credentials, nodes, queues, and plugins.

avivsinai/jenkins-cli · 26 tokens

ios-simulator

Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.

callstack/agent-device · 69 tokens

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens

openocd

A toolkit for programming and debugging microcontrollers through hardware probes such as ST-Link or CMSIS-DAP. OpenOCD can act as a GDB Server, allowing a debugger to inspect source code, registers, memory, breakpoints, and program execution.

zhinkgit/embeddedskills · 247 tokens

web-research-workflow

Unified decision tree for web research and competitive monitoring. Auto-selects WebFetch, Tavily, or agent-browser based on target site characteristics and available API keys. Includes competitor page tracking, snapshot diffing, and change alerting. Use when researching web content, scraping, extracting raw markdown…

yonatangross/orchestkit · 72 tokens

review

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use…

stevesolun/ctx · 95 tokens