LiChang1125

Agent Effective Config — Development skill for Claude Code

Development community

Probe-first CLI for verifying effective Claude Code, Codex, and Cursor configuration.

How to install Agent Effective Config

This entry records only its repository, not the path inside it, so there is no exact command to give. Open LiChang1125/agent-effective-config and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Agent Effective Config does

Probe-first CLI for verifying effective Claude Code, Codex, and Cursor configuration.

Alternatives in Development

  • Understand Anything — Graphs that teach graphs that impress 80.7k ★
  • Haft — Engineering decisions engine that know when they're stale 1.4k ★
  • Coding Agent Session Search — Unified TUI and CLI to index and search your local coding agent session history across 11+ providers (Codex, C 708 ★

README

Agent Effective Config mascot holding a configuration scanner

Agent Effective Config aec

Know what your AI coding agent actually loaded.
Probe-first diagnostics for rules, skills, permissions, hooks, and MCP servers across Claude Code, Codex, and Cursor.

MIT license Node.js 18 or newer 10 tests passing Zero runtime dependencies

Demo · Quick start · Features · Evidence model · Agent support


🎬 Demo

Real aec Codex diagnostic session

Run `aec` against the Codex fixture and it separates declarations from observations: `AGENTS.override.md` replaces `AGENTS.md`, an MCP executable is missing, and operation-specific permissions and hooks remain explicitly unverified. Every conclusion includes its evidence and the limit of what was observed.

[!TIP] `fixtures/scenario-b` is intentionally misconfigured so a fresh clone produces useful findings immediately—without changing your machine or repository.

💡 Why this exists

Static scanners can prove that a configuration file exists. They canno