api-toolkit

api-toolkit is a skill for Claude Code from aAAaqwq/AGI-Super-Team. It costs 31 tokens per session (692 once invoked), scanned A, original, MIT.

A general toolkit for calling REST APIs, which are web services accessed through standard HTTP requests. It covers authentication, response handling, endpoint testing, and data retrieval.

In plain words
What is it for?
Send GET and POST requests, use common authentication methods, parse JSON responses, check errors, and build simple automation flows.
Why use it?
It provides repeatable commands for connecting to third-party services and checking whether API requests and responses work.

Skill for Claude Code

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

Part of the agi-super-team plugin — 192 skills, 1 agent 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 skills/aaaaqwq/agi-super-team/api-toolkit
Any agent
npx skills add aAAaqwq/AGI-Super-Team --skill api-toolkit
Clone the repo
git clone --depth 1 https://github.com/aAAaqwq/AGI-Super-Team

Made for: Claude Code.

Or install agi-super-team, the plugin that ships this one along with the rest of its 192 skills, 1 agent.

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-toolkit

README.md
[![agentmods](https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/api-toolkit.svg)](https://agentmods.dev/skills/aaaaqwq/agi-super-team/api-toolkit)
Your own site
<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/api-toolkit"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/api-toolkit.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 692 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00031 $0.00692
Opus 5 $0.00015 $0.00346
Sonnet 5 $0.00006 $0.00138
Haiku 4.5 $0.00003 $0.00069

Measured yesterday against content hash 3a0b5dc13277, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

api-toolkit 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 yesterday.

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.

curl -s "https://api.example.com/endpoint" \
skills/api-toolkit/SKILL.md · 99 lines

What it actually says

API Toolkit Skill

通用 API 调用工具包,用于快速接入任何 RESTful API。

使用场景

  • 调用第三方 API 服务
  • 测试和调试 API 端点
  • 构建自动化工作流
  • 数据获取和同步

核心能力

1. HTTP 请求

# GET 请求
curl -s "https://api.example.com/endpoint" \
  -H "Authorization: Bearer $(pass show tokens/example-api)"

# POST 请求
curl -s -X POST "https://api.example.com/endpoint" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  -d '{"key": "value"}'

# 带查询参数
curl -s "https://api.example.com/search?q=query&limit=10"

2. 认证方式

方式 示例
Bearer Token -H "Authorization: Bearer $TOKEN"
API Key Header -H "X-API-Key: $KEY"
Basic Auth -u "user:pass"
Query Param ?api_key=$KEY

3. 响应处理

# JSON 解析
curl -s ... | jq '.data'

# 提取特定字段
curl -s ... | jq -r '.items[].name'

# 错误检查
response=$(curl -s -w "\n%{http_code}" ...)
body=$(echo "$response" | head -n -1)
code=$(echo "$response" | tail -n 1)

常用 API 模板

天气 API (wttr.in)

curl -s "wttr.in/Shanghai?format=j1" | jq '.current_condition[0]'

GitHub API

curl -s "https://api.github.com/users/USERNAME/repos" \
  -H "Authorization: token $(pass show tokens/github)"

Telegram Bot API

curl -s "https://api.telegram.org/bot$TOKEN/sendMessage" \
  -d "chat_id=$CHAT_ID" \
  -d "text=$MESSAGE"

安全注意事项

  1. 密钥管理 - 使用 pass 存储,不硬编码
  2. 日志脱敏 - 不在输出中显示完整密钥
  3. 速率限制 - 遵守 API 的调用频率限制
  4. 错误处理 - 检查响应状态码

添加新 API

  1. 获取 API 文档和密钥
  2. 存储密钥:pass insert tokens/new-api
  3. 测试基本调用
  4. 记录到 TOOLS.md

相关文件

  • TOOLS.md - 记录已配置的 API
  • SECURITY.md - 安全策略
  • memory/audit-*.log - 操作审计
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. yesterday First seen · 99 lines · 31 tokens per session scan A 3a0b5dc13277

Subscribe to this mod's changes

api-toolkit is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (91 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 692 once invoked, about $0.0002 per session on Opus 5. 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 2026-09-05.

Related

Other skills, from other repositories