davidYichengWei

48 mods across 2 repositories, 164 stars between them.

codebase-researcher

01

davidYichengWei/agentic-engineering-framework

Agent Claude Code

A read-only investigation of a software codebase, including its modules, dependencies, call paths, configuration, and tests. The report distinguishes direct evidence from conclusions drawn from it.

not rated 159 7mo ago A 63 tokens original MIT

davidYichengWei/agentic-engineering-framework

Agent Claude Code

A systems-code review agent that tracks every changed decision branch from its contract through the evidence needed to trust it. A branch is a path such as an early return, fallback, allow-list check, or null check.

not rated 159 7mo ago A 65 tokens original MIT

review-critic

04

davidYichengWei/agentic-engineering-framework

Agent Claude Code

An adversarial review agent that tries to disprove specific software-review findings submitted by another agent. It returns whether each finding was rejected, not proven, or could not be rebutted.

not rated 159 7mo ago A 77 tokens original MIT

robustness-reviewer

05

davidYichengWei/agentic-engineering-framework

Agent Claude Code

A code-review agent focused only on reliability in unusual situations, including boundary cases, error handling, resource cleanup, concurrency, and exception paths. Its instructions are written in Chinese.

not rated 159 7mo ago A 46 tokens original MIT

davidYichengWei/agentic-engineering-framework

Agent Claude Code

A software-review agent that checks whether code matches the requested features, design documents, tasks, and interface agreements. It focuses on expected behavior and missing requirements.

not rated 159 7mo ago A 49 tokens original MIT

standards-reviewer

07

davidYichengWei/agentic-engineering-framework

Agent Claude Code

A project-rules reviewer that checks code against explicitly stated engineering standards, such as naming, file structure, dependencies, logging, and synchronization rules.

not rated 159 7mo ago A 46 tokens original MIT

reflect

11

davidYichengWei/agentic-engineering-framework

Command Claude Code

A command that invokes a manual self-review mode for the coding agent. It reviews errors corrected in the current conversation and produces structured suggestions.

not rated 159 7mo ago A 0 tokens original MIT

bp-component-design

19

davidYichengWei/agentic-engineering-framework

Skill Claude CodeCodex

A guide to designing individual software components, such as classes, modules, interfaces, and data models. It includes rules for responsibilities, dependencies, error handling, concurrency, and common design patterns.

not rated 159 7mo ago A 50 tokens original MIT

davidYichengWei/agentic-engineering-framework

Skill Claude CodeCodex

A guide to designing systems made of multiple computers or services that communicate over a network. It covers delays, lost connections, security, coordination, data consistency, failures, and recovery.

not rated 159 7mo ago A 48 tokens original MIT

self-refinement

23

davidYichengWei/agentic-engineering-framework

Skill Claude CodeCodex

A feedback process that turns repeated corrections into lasting rules or skill updates. It reviews what went wrong, finds the root cause, and suggests how to prevent the same mistake later.

not rated 159 7mo ago A 55 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: