What is cloudx-sdk-agents AGENTS.md?

Repository instructions for integrating the CloudX software development kit into publisher apps on Android, iOS, React Native, Flutter, or Unity. They require current product facts and API details to be fetched from CloudX documentation.

Use it when adding or maintaining CloudX SDK integrations and when deciding which CloudX documentation or integration workflow to follow.

It prevents agents from relying on outdated or invented SDK versions, dependencies, APIs, or advertising guidance.

cloudx-sdk-agents AGENTS.md — Instructions file by cloudx-io

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 instructions/cloudx-io/cloudx-sdk-agents/agents-md

Clone the repo

git clone --depth 1 https://github.com/cloudx-io/cloudx-sdk-agents

Made for: Codex, OpenCode.

Per session 513 This file is loaded in full into every session.

When invoked 513 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.00513	$0.00513
Opus 5	$0.00257	$0.00257
Sonnet 5	$0.00103	$0.00103
Haiku 4.5	$0.00051	$0.00051

Measured 2d ago against content hash 0fac5a585276, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cloudx-sdk-agents AGENTS.md 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 2d 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.

AGENTS.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This repository packages AI-agent guidance for integrating the CloudX SDK into publisher apps (Android, iOS, React Native, Flutter, Unity). It works with any agent that can read files and fetch URLs — Claude Code, Codex, Cursor, and others.

The one rule

This repository contains no product facts, and neither does your memory. SDK versions, dependency coordinates, APIs, ad-format guidance, and adapter matrices live on the docs site and are fetched at run time:

Page index: https://docs.cloudx.io/llms.txt
Every listed page is raw markdown at its .md URL (e.g. https://docs.cloudx.io/en/android/integration.md)
Alternative: the CloudX MCP server's SearchDocs tool, if configured (https://docs.cloudx.io/en/mcp/installation.md)

Never write a CloudX version number, coordinate, or API signature from memory. Fetch first, always.

Repository map

.agents/skills/cloudx-integrate/ — the integration workflow skill: Detect → Plan → Integrate → Build-verify → Audit → Report. Start here for any "integrate CloudX" task. Its references/doc-map.md maps questions to docs pages; references/playbook-index.md maps project signals to playbooks.
.agents/skills/cloudx-audit/ — standalone audit of an existing CloudX integration.
playbooks/ — field knowledge the docs site does not cover: coexisting with an existing mediation stack (AppLovin MAX, LevelPlay, Google, or another — first-look or parallel), migrating off a mediation stack, CMP/consent handling, and per-platform build-system quirks. Load only the playbooks whose signals match the project.

For agent tooling maintainers

.agents/skills/ is the canonical skill catalog. .claude/skills is a compatibility symlink; .claude-plugin/ packages the same skills as a Claude Code plugin. Do not create copies.
Playbooks must contain only knowledge absent from docs.cloudx.io, link docs pages instead of restating them, and contain no version numbers. CI enforces the no-hardcoded-version rule and checks every docs link against the live site (scripts/verify.sh).

Read the full file on GitHub · 46 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.

2d ago First seen · 46 lines · 513 tokens per session scan A 0fac5a585276

Subscribe to this mod's changes

cloudx-sdk-agents AGENTS.md is an instructions file published in the GitHub repository cloudx-io/cloudx-sdk-agents (15 stars, last pushed 29d ago), licensed MIT. It adds 513 tokens to every session, about $0.0026 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 2026-08-30.

Mobile ai-agents android claude-code-plugin cloudx flutter ios

cloudx-sdk-agents AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

The one rule

Repository map

For agent tooling maintainers

What this file has done since we first saw it

Other instructions, from other repositories

im_flutter_sdk AGENTS.md

mobile-e2e-mcp AGENTS.md

mobile-e2e-mcp CLAUDE.md

ccpocket CLAUDE.md

react-native-restart CLAUDE.md

tapflow AGENTS.md