hongmaple0820/scale-engine

SCALE Engine 是一个 AI 工程化脚手架引擎,为 AI Agent(Claude Code、Codex CLI、OpenCode、Cursor、Gemini CLI 等)提供物理约束层,确保 AI 在编码过程中遵循工程规范,而不是依赖提示词的"自律"。

51Stars on the repository
29Mods indexed here, across every type
9d agoLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied

kc-autopilot

01

hongmaple0820/scale-engine

Skill Claude CodeCodexCursor

KC-Chat group autopilot autonomous mode full protocol. Read ONLY when user says "start autopilot/autonomous mode", or about to call autopilotstart / autopilotpause / autopilotstop / autopilotstatus, or on receiving [AUTOPILOTTICK] / [AUTOPILOTPAUSED] / [AUTOPILOTBUDGETEXHAUSTED] system messages. Covers: startup flow…

51 9d ago A 0 tokens

.harness

02

hongmaple0820/scale-engine

Skill Claude CodeCodex

A skill file for scale-engine that describes harness engineering practices, including automated quality checks, detecting unfinished work, and a standard session-start sequence.

51 9d ago A 0 tokens

api-design

03

hongmaple0820/scale-engine

Skill Claude CodeCodex

Skill "api-design" from hongmaple0820/scale-engine, covering api design standards, endpoint naming, http methods, response format and status codes.

51 9d ago A 7 tokens

git-workflow

09

hongmaple0820/scale-engine

Skill Claude CodeCodex

Skill "git-workflow" from hongmaple0820/scale-engine, covering git workflow, commit format, commit rules, pr workflow and pr description.

51 9d ago A 8 tokens

performance

10

hongmaple0820/scale-engine

Skill Claude CodeCodex

Skill "performance" from hongmaple0820/scale-engine, covering performance optimization, measurement first, common issues, n+1 queries and memory leaks.

51 9d ago A 4 tokens

storage-analyzer

16

hongmaple0820/scale-engine

Skill Claude CodeCodex

When this vendored skill is used by SCALE Engine, scanning and report generation are the default workflow. Do not run scripts/server.py, move files to Trash, or hard-delete paths unless the user explicitly asks for cleanup after seeing the report and confirms the exact action. Record evidence for read-only-scan…

51 9d ago A 319 tokens

karpathy-guidelines

19

hongmaple0820/scale-engine

Skill Claude CodeCodex

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

51 9d ago A 46 tokens