andrewlau624

13 mods across 1 repository, 2 stars between them.

graymatter

01

andrewlau624/agentmaxx

MCP server Claude CodeCodexCursor

MCP server "graymatter" as configured in andrewlau624/agentmaxx. Launched with graymatter mcp serve.

2 7d ago A tokens not measured

agentmaxx AGENTS.md

02

andrewlau624/agentmaxx

Instructions file CodexOpenCode

AGENTS.md instructions for andrewlau624/agentmaxx, covering memory (graymatter), your identity, every session, without exception, what triggers a call and the tools.

2 7d ago C 681 tokens

agentmaxx CLAUDE.md

03

andrewlau624/agentmaxx

Instructions file

Claude Code instructions for andrewlau624/agentmaxx, covering memory (graymatter), your identity, every session, without exception, what triggers a call and the tools.

2 7d ago C 681 tokens

andrewlau624/agentmaxx

Skill Claude CodeCodex

Use this skill ALWAYS whenever the user asks you to write code, modify files, fix bugs, plan features, or do any software development task. Trigger this whenever the user wants efficient execution, low token usage, or mentions "antigravity", "planning mode", "fast path", or complains about you using too many tokens or…

2 7d ago A 76 tokens

assumption-check

05

andrewlau624/agentmaxx

Skill Claude CodeCodex

Extract and verify implicit assumptions before implementing. Use before any non-trivial implementation, bug fix, integration, or refactor - especially when the task relies on undocumented behavior, says "should" or "probably", or touches code you haven't read yet.

2 7d ago A 54 tokens

code-review

06

andrewlau624/agentmaxx

Skill Claude CodeCodex

Structured diff review with persistent reviewer preferences. Use when asked to review code, review a PR or diff, check changes before commit — or whenever the user states a review nit, style rule, or correction worth remembering.

2 7d ago A 46 tokens

context-handoff

07

andrewlau624/agentmaxx

Skill Claude CodeCodex

Preserve the minimum sufficient working state required for another coding agent to continue a task without repeating repository discovery, reconstructing prior decisions, or losing task-specific constraints.

2 7d ago A 0 tokens

design-system-ui

08

andrewlau624/agentmaxx

Skill Claude CodeCodex

Frontend and UI work discipline. Detects and reuses an existing design system before writing any interface code, and applies sound UI craft when no system exists. Use whenever creating or modifying components, pages, layouts, themes, styling, or any visual interface.

2 7d ago A 55 tokens

explore

09

andrewlau624/agentmaxx

Skill Claude CodeCodex

Efficiently discover the minimum necessary code context for a task by using ranked search instead of undifferentiated exploration.

2 7d ago A 0 tokens

fast-commit

10

andrewlau624/agentmaxx

Skill Claude CodeCodex

Batched git commit workflow. Use whenever asked to commit, write a commit message, or save work. One shell call gathers repository state, one silent reasoning step composes the message, one shell call commits — Claude only where needed.

2 7d ago A 51 tokens

human-voice

11

andrewlau624/agentmaxx

Skill Claude CodeCodex

Write like a person. Use when drafting or editing anything meant to read as human writing such as READMEs, documentation, blog posts, commit messages, emails, announcements, or changelogs. Also use when asked to make text sound less AI-generated, more natural, or more human.

2 7d ago A 63 tokens

test-first

12

andrewlau624/agentmaxx

Skill Claude CodeCodex

Test-driven development loop with enforced verification. Use when implementing new behavior, fixing bugs with reproducible symptoms, or whenever the user asks for tests, TDD, or test coverage.

2 7d ago A 39 tokens

andrewlau624/agentmaxx

Skill Claude CodeCodex

Use this skill ALWAYS when the user explicitly requests "ultimate mode", "max efficiency", "binary mode", or asks you to write code with literally zero English output. This forces the agent into a non-human syntax protocol.

2 7d ago A 50 tokens