MCP server Claude CodeCodexCursor +2
MCP server "NEUTRON-EVO-OS" as configured in adamwang99/NEUTRON-EVO-OS. Runs mcp_server with python3.
20 4mo ago A
tokens not measured
original MIT
Instructions file
Instructions for adamwang99/NEUTRON-EVO-OS, covering ai context master — neutron evo os, stack, commands, local docs and key conventions.
20 4mo ago A 512 tokens
original MIT
Skill Claude CodeCodex
This rule is ABSOLUTE. Violating it = system failure. There are no exceptions.
20 4mo ago A 3 tokens
original MIT
checkpoint
04Skill Claude CodeCodex
Dump current session state to disk so that.
20 4mo ago A 0 tokens
original MIT
context
05Skill Claude CodeCodex
Manage context loading, injection, and priority for NEUTRON EVO OS across Claude CLI, Cursor, and IDE Context Windows.
20 4mo ago A 1 tokens
original MIT
discovery
06Skill Claude CodeCodex
This rule is ABSOLUTE. Violating it = system failure. There are no exceptions.
20 4mo ago A 2 tokens
original MIT
engine
07Skill Claude CodeCodex
The Expert Skill Router — NEUTRON EVO OS's central dispatch engine. Audits PERFORMANCELEDGER.md before executing any skill. Routes tasks to appropriate skills based on CI scores and availability.
20 4mo ago A 1 tokens
original MIT
Skill Claude CodeCodex
Suggests the best architectural patterns and code implementations for a project based on: tech stack, requirements, and detected use cases.
20 4mo ago A 2 tokens
original MIT
go-reviewer
09Skill Claude CodeCodex
Expert Go code reviewer: goroutines, channels, error handling, interface design.
20 4mo ago A 3 tokens
original MIT
memory
10Skill Claude CodeCodex
Manage long-term memory, daily logs, and Memory 2.0 (Dream Cycle: pruning + distillation) for NEUTRON EVO OS.
20 4mo ago A 1 tokens
original MIT
Skill Claude CodeCodex
This skill decomposes large tasks into independent units and coordinates parallel execution. It is a PLANNING + COORDINATION tool — it does NOT spawn agents directly. Agents are spawned via Claude Code's built-in /batch command (git worktree-based parallel).
20 4mo ago A 3 tokens
original MIT
spec
12Skill Claude CodeCodex
Before writing SPEC.md, the AI conducts an adversarial debate session with the user to challenge assumptions, surface hidden edge cases, and ensure the spec is airtight. SPEC is not just written — it is debated, questioned, and hardened until both AI and user agree it's ready.
20 4mo ago A 1 tokens
original MIT
ui_library
13Skill Claude CodeCodex
Suggests the best UI library for a frontend project based on: framework, app type, and requirements.
20 4mo ago A 2 tokens
original MIT
workflow
14Skill Claude CodeCodex
BEFORE doing anything else, check if auto-confirm is enabled.
20 4mo ago A 1 tokens
original MIT
Skill Claude CodeCodex
When implementing an auto-confirm/config system, the configuration exists but the AI doesn't read it because it's only checked at the Python execution layer (skillexecution.run()), not at the SKILL.md layer that Claude Code reads directly. Claude Code reads SKILL.md files to understand what to do — it never calls…
20 4mo ago A 5 tokens
original MIT
Skill Claude CodeCodex
Skill "test-audit-skill" from adamwang99/NEUTRON-EVO-OS, covering learned skill: test-audit-skill, pattern, when to apply, example and notes.
20 4mo ago A 5 tokens
original MIT