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 skills add GeckoVision/gecko-surf --skill use-any-apigit clone --depth 1 https://github.com/GeckoVision/gecko-surfWrote 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/skills/geckovision/gecko-surf/use-any-api)<a href="https://agentmods.dev/skills/geckovision/gecko-surf/use-any-api"><img src="https://agentmods.dev/badge/skills/geckovision/gecko-surf/use-any-api/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/skills/geckovision/gecko-surf/use-any-api"><img src="https://agentmods.dev/badge/skills/geckovision/gecko-surf/use-any-api.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 | $0.00000 | $0.00863 |
| Opus 5 | $0.00000 | $0.00432 |
| Sonnet 5 | $0.00000 | $0.00173 |
| Haiku 4.5 | $0.00000 | $0.00086 |
Grade A, and why
use-any-api 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 10d 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.
description: Use when an agent needs to CALL a new or unfamiliar API and get the first call right — when a first call fails (404 / 422 / wrong params / bad auth), when the docs are messy, human-shaped, or have no OpenAPI How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
use-any-api — make your agent first-call-correct on any API
Reach for this the moment you're about to integrate an API the agent doesn't already one-shot. Coding agents write a clean client for a well-documented API in an afternoon — so you don't need Gecko there. You need it on the painful ones: broken or missing specs, undocumented required params, an auth handshake the docs assume, a WAF that 403s your script, a field that renamed last week. That's where a raw spec makes the agent's first call a guess.
What it does
Point Gecko at the API and it turns the surface into question-shaped, first-call-correct MCP tools: the right endpoint for the intent, params placed correctly (path vs query vs body, units, enums), required fields validated before the call fires, and auth injected at call time, hidden from the agent and pinned to the API's host so a secret can't leak. Your agent calls the real API directly; Gecko is control-plane only — it never stores your responses or your keys.
Run it (one command)
# have an OpenAPI URL:
uvx --from "gecko-surf[serve]" gecko <openapi-url>
# → serves first-call-correct MCP tools at http://127.0.0.1:8000/mcp
# no spec, just docs? comprehend from the docs page instead:
uvx --from "gecko-surf[serve]" gecko from-docs <docs-url>
Then add it to your agent (Claude Code / Cursor / any MCP client):
claude mcp add --transport http myapi http://127.0.0.1:8000/mcp # Claude Code
# Cursor / others: add { "myapi": { "url": "http://127.0.0.1:8000/mcp" } } to your mcp config
Ask your agent the thing you actually wanted — it calls the API right, first try.
When the docs are JavaScript-rendered
If curl <docs-url> returns an empty shell, a spinner, or a 403, the page is a SPA — use
the [[read-js-docs]] skill first to render and extract the surface, then comprehend it.
Why it works (the honest claim)
A raw OpenAPI dump costs ~18,000 tokens for a small API and lowers tool-selection accuracy as it grows (43%→14%); Gecko projects the same surface to ~1,900 tokens (−89%) at equal-or-better first-call-correctness. Measured FCC lift: 10% → 65% on a painful API, ~0 on clean ones. Point it where agents actually fail.
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.
- 10d ago First seen · 53 lines · 0 tokens per session scan A 2e47b7639e77
use-any-api is a skill published in the GitHub repository GeckoVision/gecko-surf (6 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 863 tokens. 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 2026-08-31.
Other skills, from other repositories
data-leakage-detection
Detect sensitive information disclosure via escalating dialogue probes. Covers system prompt extraction, credential/API key leakage, PII, and internal configuration exposure.
potpie-repo-baseline
Use when establishing, refreshing, or deeply understanding a repository's baseline memory in Potpie: purpose, application type, features, services/modules, environments, deploy shape, dependencies, API contracts, datastores, integrations, ownership, and explicit preferences. The harness reads authored and…
potpie-infra-architecture
Use for project infra and architecture context: environments, adapters, runtime configuration, deployments, service dependencies, datastores, API contracts, ownership, incidents, and dependency blast radius.
potpie-project-preferences
Use before writing, modifying, reviewing, refactoring, or testing code so repo/project preferences surface: error handling, file structure, frameworks, logging, dependency choices, testing, security, API style, and naming. Also use after code work when a reusable project preference should be recorded.
api-caller
Call any REST API dynamically. Make GET, POST, PUT, DELETE requests to any endpoint with custom headers and JSON body.
protect
Add Arcjet request protection to JavaScript and TypeScript HTTP handlers. Use when protecting Next.js, Express, Fastify, SvelteKit, Remix, Astro, Nuxt, Bun, Deno, NestJS, or Node.js routes with rate limiting, bot detection, Shield, email validation, or sensitive info detection.