cocos-wechat-local-build

cocos-wechat-local-build is a skill for Codex from lightblink/cocos-creator-local-mcp. It costs 86 tokens per session (1,673 once invoked), scanned A, original, MIT.

A local build and debugging workflow for Cocos Creator 3.8 projects targeting WeChat Mini Games. Cocos Creator is a game-development tool, and a WeChat Mini Game runs inside WeChat without a traditional app installation.

In plain words
What is it for?
It is for checking a Cocos project, preparing build settings, running a local WeChat Mini Game build, inspecting its output, and preparing local simulator or debugging work. It does not cover publishing or release operations.
Why use it?
It helps prepare and inspect a local game build before publishing, including project settings, generated files, and package limits.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

Good fit It is for checking a Cocos project, preparing build settings, running a local WeChat Mini Game build, inspecting its output, and preparing local simulator or debugging work. It does not cover publishing or release operations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lightblink/cocos-creator-local-mcp/cocos-wechat-local-build
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 lightblink/cocos-creator-local-mcp --skill cocos-wechat-local-build
Clone the repo
git clone --depth 1 https://github.com/lightblink/cocos-creator-local-mcp

Made for: 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 cocos-wechat-local-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/lightblink/cocos-creator-local-mcp/cocos-wechat-local-build/github.svg)](https://agentmods.dev/skills/lightblink/cocos-creator-local-mcp/cocos-wechat-local-build)
Your own site
<a href="https://agentmods.dev/skills/lightblink/cocos-creator-local-mcp/cocos-wechat-local-build"><img src="https://agentmods.dev/badge/skills/lightblink/cocos-creator-local-mcp/cocos-wechat-local-build/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 cocos-wechat-local-build

Your own site · 80×15
<a href="https://agentmods.dev/skills/lightblink/cocos-creator-local-mcp/cocos-wechat-local-build"><img src="https://agentmods.dev/badge/skills/lightblink/cocos-creator-local-mcp/cocos-wechat-local-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,673 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 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 $0.00086 $0.01673
Opus 5 $0.00043 $0.00837
Sonnet 5 $0.00017 $0.00335
Haiku 4.5 $0.00009 $0.00167

Measured 11d ago against content hash 6286a7a7f3c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

cocos-wechat-local-build 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 11d 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.

skills/cocos-wechat-local-build/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cocos WeChat Local Build

Overview

Use this skill for the local-only Cocos Creator to WeChat Mini Game loop: project readiness, build config, wechatgame command-line build, output inspection, and local simulator/debug preparation. Do not handle upload, review, release, payment, or production operations with this skill.

Target Cocos Creator 3.8.8 when the local machine has it installed; otherwise detect the configured Creator path.

Core Workflow

  1. Detect environment.
    • Prefer cocos_local_get_environment when the Cocos local MCP tools are available.
    • Confirm Cocos Creator path, WeChat DevTools CLI path if needed, and target project root.
  2. Inspect the project.
    • If starting from zero and no project exists, use cocos_local_create_project to create a Cocos Creator 3.8 project from the built-in empty-2d template and create assets/scenes/Main.scene before build preparation.
    • Use cocos_local_inspect_project when available.
    • Check for assets/, settings/, scenes, scripts, existing build output, and project metadata.
  3. Prepare build config.
    • For generated starter projects, use cocos_local_open_project, cocos_local_wait_for_editor_bridge, and cocos_local_apply_scene_blueprint to prepare an active saved scene before creating the final build config.
    • Reuse an already-open Cocos Creator process for the same project when possible. If old projects are still open from earlier tests, close them or use distinct editor bridge ports before trusting scene or build preparation evidence.
    • Before creating the build config, declare the target device class, orientation, design resolution, and fit policy. For phone-first WeChat Mini Games, prefer an explicit portrait design resolution such as 720x1280 or a project-proven equivalent unless the game design requires landscape.
    • Use cocos_local_create_wechat_build_config for a reproducible config JSON.
    • Pass designResolution when the MCP tool supports it. If the tool does not support it, patch the generated config or report the missing adaptation setting instead of silently building with a desktop/template default.
    • When a scene asset is known, pass startScenePath such as assets/scenes/Main.scene so the MCP reads the UUID from the .meta file.
    • Use placeholder appid only for local non-platform gameplay checks; ask for a real appid before testing WeChat APIs.
  4. Build locally.
    • Use cocos_local_build_wechatgame with configPath when available.
    • Prefer dry run first when the project, appid, or Creator path is uncertain.
  5. Inspect output.
    • Use cocos_local_check_wechat_build_output for required files and package budget warnings.
    • Confirm game.json and project.config.json exist under the built wechatgame folder.
  6. Audit local runtime package risk.
    • Use cocos_local_audit_runtime_package before opening the simulator when the tool is available.
    • Review package budgets, largest files, oversized textures/audio, and first-package pressure.
    • Treat this as static risk analysis; it is not FPS, memory, or gameplay verification.
  7. Open or prepare WeChat DevTools locally.
    • Use cocos_local_open_wechat_devtools to open the local build/wechatgame output.
    • Use cocos_local_preview_wechat_devtools only when preview artifacts are useful for local/debug review.
    • Use cocos_local_manage_wechat_devtools for cache cleanup, closing the project, or quitting DevTools.
  8. Collect runtime evidence.
    • Use cocos_local_collect_runtime_evidence after observing launch, first input, core loop, result/failure, restart, and logs.
    • Keep build success, DevTools opening, and runtime verification as separate states in the final answer.

Read the full file on GitHub · 137 lines

Files

What ships with it

1 file 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. 11d ago First seen · 137 lines · 86 tokens per session scan A 6286a7a7f3c4

Subscribe to this mod's changes

cocos-wechat-local-build is a skill published in the GitHub repository lightblink/cocos-creator-local-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 1,673 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

cocos-asset-pipeline-director

Plan, generate, adapt, validate, and import Cocos Creator 3.x game assets through a configured Cocos Asset Forge-compatible MCP. Use whenever the user asks for Cocos assets, sprites, sprite sheets, tilesets, UI packs, effects, placeholders, audio, art bibles, Cocos-ready metadata, asset folders, bundle placement…

lightblink/cocos-asset-forge-mcp · 91 tokens

cocos-asset-review-director

Review generated or imported Cocos Creator game assets against game design, art direction, gameplay semantics, animation needs, technical quality, mobile readability, interaction feedback, audio fit, performance risk, and runtime import constraints. Use after asset generation or adaptation, before importing assets…

lightblink/cocos-asset-forge-mcp · 88 tokens

cocos-art-direction-director

Direct visual style, art bibles, asset consistency, prompt language, sprite readability, UI visual systems, animation style, and Cocos-ready asset QA for game art pipelines. Use before asset generation when Codex needs to define a coherent look, guide or critique generated assets, coordinate with cocosassetforge…

lightblink/cocos-asset-forge-mcp · 90 tokens

cocos-helper

A helper guide for building games with Cocos Creator, a game engine and editor. It covers project folders, common components, and managers written in TypeScript.

guyulong/cn-agent-skills · 10 tokens

particle-modifier

A framework for creating and debugging custom particle modifiers in Cocos Creator 2.4.x, a tool for making games and interactive scenes. Particle modifiers can change properties such as position, color, size, rotation, and speed.

958877748/skills · 73 tokens

gameobject-component-destroy

Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.

IvanMurzak/Unity-MCP · 49 tokens