api-exploration

api-exploration is a skill for Claude Code from ryan-haver/fusebase-mcp. It costs 79 tokens per session (761 once invoked), scanned A, a copy of api-exploration, MIT.

A workflow for interactively testing Fusebase API calls with temporary access tokens before writing application code.

In plain words
What is it for?
It helps verify endpoints, explore responses and schemas, and investigate API integration problems.
Why use it?
It helps reveal an API's responses and data structure early, reducing guesswork when an integration behaves unexpectedly.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Part of the fusebase plugin — 16 skills, 2 agents, 1 hook, 1 MCP server shipped together

Good fit It helps verify endpoints, explore responses and schemas, and investigate API integration problems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ryan-haver/fusebase-mcp/api-exploration
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 ryan-haver/fusebase-mcp --skill api-exploration
Clone the repo
git clone --depth 1 https://github.com/ryan-haver/fusebase-mcp

Made for: Claude Code.

Or install fusebase, the plugin that ships this one along with the rest of its 16 skills, 2 agents, 1 hook, 1 MCP server.

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-exploration

README.md
[![agentmods](https://agentmods.dev/badge/skills/ryan-haver/fusebase-mcp/api-exploration/github.svg)](https://agentmods.dev/skills/ryan-haver/fusebase-mcp/api-exploration)
Your own site
<a href="https://agentmods.dev/skills/ryan-haver/fusebase-mcp/api-exploration"><img src="https://agentmods.dev/badge/skills/ryan-haver/fusebase-mcp/api-exploration/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.

agentmods 80×15 button for api-exploration

Your own site · 80×15
<a href="https://agentmods.dev/skills/ryan-haver/fusebase-mcp/api-exploration"><img src="https://agentmods.dev/badge/skills/ryan-haver/fusebase-mcp/api-exploration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 761 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.
Origin 100% copy Near-identical to another mod 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 $0.00079 $0.00761
Opus 5.5 $0.00032 $0.00304
Sonnet 5.5 $0.00016 $0.00152
Haiku 4.5 $0.00008 $0.00076

Measured 1mo ago against content hash f93ed335be2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

api-exploration 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.

Origin

This is a copy

100% identical to api-exploration — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

apps/client-portal-dashboard/.claude/skills/api-exploration/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

API Exploration with Temporary Tokens

When you're unsure about an API endpoint's behavior, response shape, or want to test a flow before committing to implementation — create a temporary token and run test calls directly.

Workflow

1. Create a temporary token

fusebase token create --app <appId>

This outputs a short-lived token (15 min) to stdout. Capture it:

TOKEN=$(fusebase token create --app <appId>)

The appId comes from fusebase.json → apps[].id.

2. Write and run test code

Create a temporary script (e.g. _test-api.ts) to make the API calls you want to verify:

const token = process.env.TOKEN || "<paste-token-here>";

const res = await fetch("https://api-endpoint/...", {
  headers: { "x-app-feature-token": token },
});
console.log(res.status);
console.log(await res.json());

Run it:

TOKEN=$(fusebase token create --app <appId>) bun _test-api.ts

3. Inspect results and iterate

Read the output, adjust your calls, and re-run. Once you understand the API behavior, implement it properly in your app code.

4. Clean up

Delete the temporary test script when done — don't commit it.

Example: Testing @fusebase/dashboard-service-sdk

Use this to verify SDK calls before wiring them into app UI code.

_test-sdk.ts:

import {
  createClient,
  DatabasesApi,
  CustomDashboardRowsApi,
} from "@fusebase/dashboard-service-sdk";

const token = process.env.TOKEN!;
const BASE_URL =
  "https://app-api.thefusebase.com/v4/api/proxy/dashboard-service/v1";

const client = createClient({
  baseUrl: BASE_URL,
  defaultHeaders: { "x-app-feature-token": token },
});

const dbApi = new DatabasesApi(client);
const rowsApi = new CustomDashboardRowsApi(client);

// List databases visible to this app
const dbs = await dbApi.listDatabases({});
console.log("databases:", JSON.stringify(dbs, null, 2));

// Read rows from a specific dashboard view
const rows = await rowsApi.getRows({
  dashboardId: "<dashboardId>",
  viewId: "<viewId>",
});
console.log("rows:", JSON.stringify(rows, null, 2));

Read the full file on GitHub · 105 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. 1mo ago First seen · 105 lines · 79 tokens per session scan A f93ed335be2c

Subscribe to this mod's changes

api-exploration is a skill published in the GitHub repository ryan-haver/fusebase-mcp (8 stars, last pushed 3d ago), licensed MIT. It adds 79 tokens to every session and 761 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to api-exploration, differing in 2 lines, and is treated as a copy.

Related

api-exploration compared with skills from other repositories

api-exploration next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
api-explorationryan-haver/fusebase-mcpSkill83d agoMITA79Claude Code
mem0-oss-to-platformmem0ai/mem0Skill69kyesterdayApache-2.0A217Claude Code, Codex
azure-mgmt-botservice-dotnetmicrosoft/skillsSkill3.2kyesterdayMITA78Claude Code
fastapi-router-pymicrosoft/skillsSkill3.2kyesterdayMITA46Claude Code
dev-runtimelangwatch/langwatchSkill5.0ktodayApache-2.0A172Claude Code
api-designericrisco/rsc-harnessSkill5293d agoMITA105Claude Code, Codex
migrate-segw-to-raparc-mcp/arc-1Skill253todayMITA106Claude Code