By fingerskier
Build a mindmap and guided tour of a repo or document set. Scans code or prose, then produces a Mermaid mindmap of concepts/modules and a guided reading tour.
Build a mindmap and guided tour of a repo.
introspector scans a codebase (or a set of documents) and produces two things:
It ships as a Claude Code plugin (skill, slash command, agent, and a SessionStart hook) backed by a small, dependency-free TypeScript scanner you can also run on its own.
The artifacts are written to ./.introspector/ in the current repo (overwritten on re-run):
| File | What it is |
|---|---|
mindmap.md | Markdown report: embedded Mermaid mindmap + guided tour + tables |
mindmap.mmd | The raw Mermaid mindmap diagram |
inventory.json | Structured inventory (with --json) — modules, tests, doc outlines |
Scan deterministically, then enrich semantically.
.gitignore), classifies
every file (code / test / docs / config / asset), groups files into modules,
links test files to the sources they likely exercise, and extracts document
heading outlines. It emits a deterministic baseline mindmap and inventory.json.The scanner alone is useful and runs without an LLM; the Claude layer makes the map meaningful.
This repo is itself a plugin marketplace. Add it and install:
/plugin marketplace add fingerskier/introspector
/plugin install introspector@introspector
Then, in any project:
/introspect [--mode code|docs|mixed]introspector subagent for a hands-off pass.When a project already has a .introspector/mindmap.md, the bundled SessionStart
hook surfaces it automatically so Claude starts oriented.
Requires Node.js ≥ 22.18 (the scanner runs TypeScript directly via type stripping — no build step needed).
The CLI always scans the current working directory and writes into ./.introspector/.
# scan the current repo
node src/cli.ts
# also emit inventory.json
node src/cli.ts --json
# force a mode, or just print the report to stdout
node src/cli.ts --mode docs
node src/cli.ts --stdout
Options: -m, --mode code|docs|mixed|auto, --json, --stdout, -h, --help.
import { scan, toMermaid, toMarkdown } from 'introspector';
const inventory = scan('path/to/project');
console.log(toMermaid(inventory)); // Mermaid mindmap string
console.log(toMarkdown(inventory)); // full Markdown report
.claude-plugin/ Plugin + marketplace manifests
skills/introspect/ The introspect skill (scan → enrich → write workflow)
commands/ /introspect slash command
agents/ introspector subagent
hooks/ SessionStart hook that surfaces an existing mindmap
src/ TypeScript scanner (walk, classify, scan, mindmap, report, cli)
tests/ node:test suite for the scanner
npm install # dev deps: typescript + @types/node
npm test # run the scanner test suite (node:test)
npm run check # type-check (tsc --noEmit)
npm run build # optional: compile src/ -> dist/
Apache-2.0 — see LICENSE.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub fingerskier/introspector --plugin introspectorExegetical theology research — rigorous, multi-perspective Biblical exegesis with historian, linguist, author, theologian, disciple, shepherd, numerology, and full research skills.
CAD modeling with build123d — create, inspect, and export parametric 3D models using Python.
Design electronic schematics and PCB layouts using SKiDL — create circuits with Python code, validate designs, and export to KiCad.
Subagents for literature research — search PubMed, format citations, and synthesize a verified corpus into prose. Zero-install: uses public APIs, no bundled servers.
OpenSCAD parametric modeling — generate, edit, and visually inspect 3D models
Make your AI agent code with your project's architecture, rules, and decisions.
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).
Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
Comprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation