codebase-map

Normify · DSH 插件：把项目架构写成归一化的分形模块树，三层校验（写时 / 校验 / 冻结回执）、30 个 normify_* 工具 + normify-gen 技能，一键渲染单文件交互式架构图；支持伴随式开发（change_open → brief → check → 实施 → refresh → change_close）。

Agent-first, zero-dependency, self-maintaining codebase documentation & change tracking system. LLM-operated wiki with health matrix, semantic record-change, heartbeat monitor, and static dashboard.

Extends Unix tree so every file shows its one-line concern and boundary, giving a separation-of-concerns overview of the whole workspace at a glance. A fast, enforceable map for AI agents.

Review systems and architecture, not code, with chorograph

meta-bonsai generates a pruned ASCII tree that highlights only developer-marked files and directories, keeping ancestor paths to preserve structure.

Generates a codebase map from @atlas annotations, validated against a repo-owned concept registry — structural facts that cannot drift.

A map of a codebase you have never seen before. Draws the dependency graph, every import cycle, where the mass is, what changes together and what is dead — across TypeScript, Rust, Python and Go. Ranked, explainable findings. Local, offline, no account, and it never modifies your source or history.

Local-first context saving for AI coding agents: map first, slice next, retrieve exactly.

Coding agents re-discover your repo every session and miss what they must not break. code-map hands each agent, subagent and file edit the right zone from one checked-in, validated map. No index or infra.

See what your coding agents are building: your agent draws a map of the system from the code, a checker keeps it honest, and every pull request says what it did to the shape before you merge.

Structural analysis for codebases. Produces dependency graphs, class hierarchies, and cross-boundary coupling maps via language plugins -- compressed into token-efficient formats for LLM context windows. Multi-format output including TOON.

Interactive visualization tool for AIReady codebase analysis

A Claude Agent Skill validator for Claude Code: spec conformance, script testing, quality and security scoring, a Mermaid skill map, and per-skill token cost.

Turn your app into a typed knowledge graph AI coding agents query instead of reading source. Rust CLI, MIT.

Your agents break less code and burn fewer tokens — deterministic call/import graph + 27 MCP tools for coding agents. Claude Code plugin & MCP server; zero deps, runs 100% locally.