agentmods.dev

QianYuan.AIAgenticFramework: Skill for Claude Code

.agents/skills/api-gateway/SKILL.md

api-gateway is a skill for Claude Code, Codex from zhouguoqing/QianYuan.AIAgenticFramework. It costs 49 tokens per session (13,463 once invoked), scanned A, original, Apache-2.0.

A method for connecting to third-party services through managed API routes. It requires naming the specific app, account, and task, and starts with read-only checks of the target.

In plain words
What is it for?
Use it to read information from a named connected app and, when explicitly approved, send requests that change data through its documented API route.
Why use it?
It provides a defined way to inspect an external service while reducing the risk of acting on the wrong account or resource.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is zhouguoqing/QianYuan.AIAgenticFramework's own configuration. It tells Claude Code and Codex how to work on QianYuan.AIAgenticFramework itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything QianYuan.AIAgenticFramework configures →

not rated 36repo +1 24d ago A scan SkillSpector: warn 49 tokens original Apache-2.0
View source ↗ zhouguoqing/QianYuan.AIAgenticFramework
Reuse

Borrowing it

Nothing to install: this file belongs to zhouguoqing/QianYuan.AIAgenticFramework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zhouguoqing/QianYuan.AIAgenticFramework/main/.agents/skills/api-gateway/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/zhouguoqing/QianYuan.AIAgenticFramework

Made for: Claude Code, Codex.

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-gateway

README.md
[![agentmods](https://agentmods.dev/badge/skills/zhouguoqing/qianyuan.aiagenticframework/api-gateway/github.svg)](https://agentmods.dev/skills/zhouguoqing/qianyuan.aiagenticframework/api-gateway)
Your own site
<a href="https://agentmods.dev/skills/zhouguoqing/qianyuan.aiagenticframework/api-gateway"><img src="https://agentmods.dev/badge/skills/zhouguoqing/qianyuan.aiagenticframework/api-gateway/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-gateway

Your own site · 80×15
<a href="https://agentmods.dev/skills/zhouguoqing/qianyuan.aiagenticframework/api-gateway"><img src="https://agentmods.dev/badge/skills/zhouguoqing/qianyuan.aiagenticframework/api-gateway.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 13,463 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 28 findings, up to high

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 →

  • high Tool Misuse · line 230
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium Data Exfiltration · line 37
    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.
  • medium Data Exfiltration · line 45
    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.
  • medium Data Exfiltration · line 56
    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.
  • medium Data Exfiltration · line 57
    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.
  • medium Data Exfiltration · line 124
    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.
  • medium Data Exfiltration · line 170
    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.
  • medium Data Exfiltration · line 198
    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.
  • medium Data Exfiltration · line 238
    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.
  • medium Data Exfiltration · line 263
    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.
  • medium Data Exfiltration · line 625
    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.
  • medium Data Exfiltration · line 645
    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.
  • medium Data Exfiltration · line 665
    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.
  • medium Data Exfiltration · line 685
    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.
  • medium Data Exfiltration · line 705
    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.
  • medium Data Exfiltration · line 726
    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.
  • medium Data Exfiltration · line 748
    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.
  • medium Data Exfiltration · line 773
    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.
  • medium Data Exfiltration · line 788
    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.
  • medium Data Exfiltration · line 835
    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.
How audits are shown
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 $0.00049 $0.13463
Opus 5 $0.00024 $0.06731
Sonnet 5 $0.00010 $0.02693
Haiku 4.5 $0.00005 $0.01346

Measured 10d ago against content hash 6755c661b621, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

api-gateway 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.

import urllib.request, os, json
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.agents/skills/api-gateway/SKILL.md · 901 lines

How it starts

The opening of the file, as written. The whole thing — 901 lines — stays where its author put it; the contents beside it link to each section on GitHub.

API Gateway

Managed API routing for third-party services, provided by Maton. Use this only for a user-requested app, account, and task.

Quick Start

CLI:

maton slack channel list --types public_channel --limit 10

maton api '/slack/api/conversations.list?types=public_channel&limit=10'

Python:

python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://api.maton.ai/slack/api/conversations.list?types=public_channel&limit=10')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Routing

Use https://api.maton.ai/ with the app-prefixed routes documented in the examples below or in the matching reference file.

Usage protocol:

  1. Only invoke after the user specifies the exact app, account, and task.
  2. Always start with read-only (GET) calls to verify the target account, resource identifiers, and current state.
  3. All non-GET requests are denied unless the user explicitly approves each one. Before any POST, PUT, PATCH, or DELETE call, present the user with: the exact connection ID, the full endpoint path, the request body, and the expected outcome — then wait for approval.
  4. If the user's request implies a non-GET operation, first show them what you intend to call and ask for confirmation. Do not infer approval from the original request.

Read-only route examples:

https://api.maton.ai/slack/api/conversations.list?types=public_channel&limit=10
https://api.maton.ai/google-mail/gmail/v1/users/me/messages

The first path segment is the app identifier listed in Supported Services. For Gmail, use /google-mail/gmail/v1/users/me/messages.

Installation

NPM:

npm install -g @maton-ai/cli

Homebrew:

brew install maton-ai/cli/maton

Authentication

IMPORTANT — Credential Safety:

  • Treat MATON_API_KEY as a secret. Never log it, echo it, paste it into prompts, or expose it in shared files, command output, or tool results.
  • Connection creation requires explicit user approval. Before creating any connection, ask the user to confirm the specific service and confirm they intend to authorize access. Never create connections on the agent's own initiative.
  • Least-privilege scopes: When a service offers scope selection during OAuth, select only the scopes the current task requires. Do not accept broader scopes for convenience.
  • Remove connections immediately after the task is complete if they are no longer needed (maton connection delete {id}).
  • If the key may have been exposed (logs, screenshots, shared terminals), rotate it immediately at maton.ai/settings.
  • Never share the key across users, workflows, or environments that do not require it.

Read the full file on GitHub · 901 lines

Files

What ships with it

60 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.

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. 10d ago First seen · 901 lines · 49 tokens per session scan A 6755c661b621

Subscribe to this mod's changes

api-gateway is a skill published in the GitHub repository zhouguoqing/QianYuan.AIAgenticFramework (36 stars, last pushed 24d ago), licensed Apache-2.0. It adds 49 tokens to every session and 13,463 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 2026-08-30.

Backend and APIsagenticagentic-aiaiai-agents
Related

Other skills, from other repositories

Telephony

Give Elephant Agent phone capabilities without core tool changes. Provision and persist a Twilio number, send and receive SMS/MMS, make direct calls, and place AI-driven outbound calls through Bland.ai or Vapi.

agentic-in/elephant-agent · 45 tokens

GIF Search

Search and download reaction GIFs through the Tenor API using curl and jq when the user wants lightweight media retrieval.

agentic-in/elephant-agent · 26 tokens

ASCII Art

Generate ASCII art using pyfiglet (571 fonts), cowsay, boxes, toilet, image-to-ascii, remote APIs (asciified, ascii.co.uk), and LLM fallback. No API keys required.

agentic-in/elephant-agent · 47 tokens

eng-go-developer

Implement Go code with clear errors, tests, and observability.

oodaris/autocodex · 18 tokens

api-testing

Comprehensive API testing, validation, and test suite generation.

laragentic/agents · 14 tokens

event-store-design

Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.

wshobson/agents · 33 tokens