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 api-agent-readygit 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/api-agent-ready)<a href="https://agentmods.dev/skills/geckovision/gecko-surf/api-agent-ready"><img src="https://agentmods.dev/badge/skills/geckovision/gecko-surf/api-agent-ready.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Data Exfiltration · line 75 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00186 | $0.01796 |
| Opus 5 | $0.00093 | $0.00898 |
| Sonnet 5 | $0.00037 | $0.00359 |
| Haiku 4.5 | $0.00019 | $0.00180 |
Grade A, and why
api-agent-ready 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Agent-Ready Skill
For the provider. Every other agent skill teaches how to call one API. This skill takes an API you own (or one you want agents to use) and makes its whole surface agent-usable — first-call-correct, over MCP — without writing integration code, and without touching the MCP the provider already ships.
What this skill is for
A provider's API is built for humans: prose docs, an auth handshake assumed, units implied, a spec with dozens–hundreds of operations. The provider can only hand-wrap a few endpoints into an MCP, so agents see a fraction of the API. The long tail stays invisible unless someone writes glue.
This skill closes that gap with gecko, the open-source comprehension engine. You
run a spine that turns an OpenAPI (or a doc page) into a first-call-correct MCP
for the full surface, emits the breadcrumbs agents use to find it, and serves it
with a one-click add — alongside whatever MCP the provider built.
If the provider is still building or hardening the API, start one step earlier: Step 0 — Design for agents (best-practices.md) is a checklist for shaping endpoints agents consume well (one canonical read, field-complete, clear enums/required fields, a machine-authable auth path) before Gecko comprehends them. A surface designed to that checklist lands first-call-correct because it's unambiguous — not because a layer papered over the ambiguity.
"Make every API easily pluggable."
The spine
Pick the step you're on; load only the file you need (progressive, token-efficient). Step 0 is provider-side design work; steps 1–3 are where Gecko acts; 4–5 are the discipline that keeps it in lane.
| # | Step | Read | Status |
|---|---|---|---|
| 0 | Design for agents — the API best-practices checklist (do this while building) | best-practices.md | provider-side guidance |
| 1 | Comprehend the OpenAPI/docs → first-call-correct tools | comprehend.md | Live |
| 2 | Emit artifacts — llms.txt, x-gecko, gecko.json breadcrumbs |
artifacts.md | Building (hand-authored pattern) |
| 3 | Serve MCP — Streamable-HTTP + one-click claude mcp add |
serve-mcp.md | Live |
| 4 | Make discoverable — breadcrumb, not a public catalog | discoverable.md | Building |
| 5 | Aggregate, not replace — never touch the provider's own MCP | aggregate-not-replace.md | invariant |
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 122 lines · 186 tokens per session scan A f8768bb2d26a
api-agent-ready is a skill published in the GitHub repository GeckoVision/gecko-surf (6 stars, last pushed today), licensed Apache-2.0. It adds 186 tokens to every session and 1,796 once invoked, about $0.0009 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.
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.
muapi-platform
Setup and utility scripts for muapi.ai — configure API keys, test connectivity, and poll for async generation results.
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.