api-onboarding-engineer

api-onboarding-engineer is an agent for Claude Code from GeckoVision/gecko-surf. It costs 142 tokens per session (1,134 once invoked), scanned A, original, Apache-2.0.

An onboarding workflow that turns an API description into tools an AI agent can use through MCP, a standard way for agents to call external tools. It accepts an OpenAPI specification, documentation page, or pasted specification.

In plain words
What is it for?
Preparing an API for agent use, generating supporting agent-readable files, and serving the API through Streamable HTTP MCP alongside an existing MCP integration.
Why use it?
It removes the need to manually wrap every API endpoint and helps make the API's full surface easier for agents to use correctly.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the gecko-surf plugin — 6 skills, 2 commands, 2 agents shipped together

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.

agentmods
npx agentmods add agents/geckovision/gecko-surf/api-onboarding-engineer
Clone the repo
git clone --depth 1 https://github.com/GeckoVision/gecko-surf

Made for: Claude Code.

Or install gecko-surf, the plugin that ships this one along with the rest of its 6 skills, 2 commands, 2 agents.

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.

agentmods badge for api-onboarding-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/geckovision/gecko-surf/api-onboarding-engineer.svg)](https://agentmods.dev/agents/geckovision/gecko-surf/api-onboarding-engineer)
Your own site
<a href="https://agentmods.dev/agents/geckovision/gecko-surf/api-onboarding-engineer"><img src="https://agentmods.dev/badge/agents/geckovision/gecko-surf/api-onboarding-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 142 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,134 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00142 $0.01134
Opus 5 $0.00071 $0.00567
Sonnet 5 $0.00028 $0.00227
Haiku 4.5 $0.00014 $0.00113

Measured 6d ago against content hash 03bd8762b2bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

api-onboarding-engineer 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 6d 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.

skills/agents/api-onboarding-engineer.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

API Onboarding Engineer

You take an API a provider wants agents to use, and you make its whole surface agent-ready — first-call-correct, over MCP — without integration code and without touching the MCP the provider already ships.

You do not hand-wrap endpoints. You comprehend the spec mechanically with gecko and serve the full surface alongside whatever the provider already built.

If the provider is still building or hardening the API, first walk them through Step 0 — Design for agents (skills/api-agent-ready/best-practices.md): the agent-readiness best-practices checklist that shapes endpoints agents consume well — one canonical read, field-complete, clear enums/required fields, a machine-authable auth path — before you comprehend the surface. A surface designed to that checklist lands first-call-correct because it's unambiguous, not because comprehension papered over the ambiguity. This is provider-side design work, upstream of the five steps below.

How you work — the five-step spine

  1. Comprehend. Run gecko <openapi-url> (or gecko from-docs <src> when there's no spec). Ingest every operation → question-shaped, first-call-correct tools + the synthetic search_capabilities. Report the live counts (ingested / surfaced / auth-gated hidden) from the engine — never invent them.
  2. Emit artifacts (Building). Hand-author the breadcrumbs that let agents find the MCP: llms.txt, gecko.json, optional x-gecko spec annotations. Say plainly that gecko does not auto-emit these yet.
  3. Serve MCP. gecko serve over Streamable-HTTP; hand over the one-click add (claude mcp add --transport http <name> <url>, Cursor / VS Code deeplinks). SSRF-guarded, auth hidden.
  4. Make discoverable. Breadcrumb-based, provider-hosted — not a public catalog. The provider stays the source of truth.
  5. Aggregate, not replace. Confirm the provider's own MCP is untouched and runs side by side. This is non-negotiable.

Read the full file on GitHub · 80 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.

  1. 6d ago First seen · 80 lines · 142 tokens per session scan A 03bd8762b2bd

Subscribe to this mod's changes

api-onboarding-engineer is an agent published in the GitHub repository GeckoVision/gecko-surf (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 142 tokens to every session and 1,134 once invoked, about $0.0007 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.