By AnjanJ
Research-informed interactive coding tutor. Learn anything in tech with a wise, patient guide.
Reviews learner code in educational context. Analyzes what code reveals about understanding, not just code quality. Uses Socratic questioning.
Searches web for verified, community-recommended free learning resources. Validates links. Analyzes user's existing materials.
Evaluates learner skill level through adaptive Bloom's taxonomy questioning and code analysis. Returns per-concept level classification.
Analyzes a learner's full project history to produce a structured trajectory report (per-topic Bloom movement, retention, precision-gap movements with source quotes, completion). Used by /evaluate so the parent skill stays light.
Assess your current skill level on any programming topic
Resume a learning project from where you left off
Scientific debugging: reproduce, hypothesize, probe, isolate, fix. Never fixes bugs directly.
Comprehensive evaluation of your entire learning journey
Demote one or more concepts back to Box 1 for review tomorrow. Use when you feel a concept has slipped.
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.
Research-informed interactive coding tutor for Claude Code.
Bodhi (Pali: "awakening") is a patient, wise guide that teaches you anything in the world of coding, software engineering, and tech. It does not write code for you. It teaches you to write code yourself.
BodhiKit turns Claude Code into a research-informed coding tutor. Not a chatbot, not "ChatGPT that explains code" — a stateful learning architecture that orchestrates a learner's journey across sessions, projects, and months.
The animating constraint: "The learner writes code. BodhiKit asks questions. The goal is to become unnecessary."
The voice is grounded in four named teachers (Gautama Buddha, Dr. B.R. Ambedkar, Master Oogway, Yoda) — not as aesthetic flavor, but tied to specific pedagogical principles (Upaya / skillful means; Educate–Agitate–Organize; faith in learner potential; challenge with care).
Pedagogical theories wired into behavior, not vibes. Bloom's taxonomy (per-concept level tracking), Vygotsky's ZPD (calibrated difficulty), Leitner spaced repetition (5-box system with date-computed reviews), Feynman (explain-back gates), Sweller's cognitive load (faded worked examples), Bjork's pretesting, Rawson & Dunlosky's successive relearning, Koriat's confidence calibration, deliberate practice, Whitmore's GROW, Kram's mentoring functions, Flavell's metacognition. Each lives in its own KB, loaded only when its phase fires (progressive disclosure).
Socratic enforcement as architecture, not suggestion. /teach uses graduated hints (Direction → Approach → Near-solution) and forbids "Hint 4." /debug-together says "Do NOT look at the code yet." dev/check.sh fails the build if a skill restates voice rules inline instead of referencing the teaching-personality KB.
Cross-session memory. .bodhi/state.json, spaced-review.json, progress.md, and .bodhi-profile.json form a learner profile that persists. Streaks, Box-3 review dates, Bloom level per sub-topic, persistent challenges — all carried forward.
A deterministic state layer (1.11.0). Every JSON mutation goes through scripts/bodhi-state — Leitner math, the Bloom ratchet, mastery formula, migration, and schema validation run in code, not in model prose. A Stop hook verifies tracking files before a session ends, and a two-layer test harness (free deterministic tests + pre-tag LLM evals asserting on file state) guards the contracts that manual dogfooding used to.
Single sources of truth + lint as contract. state-schema KB owns every tracking-file shape. spaced-repetition KB owns every Leitner interval. teaching-personality owns the voice. dev/check.sh enforces the contracts — version sync, KB references, agent fallbacks, --invoked-from= chaining, the bodhi-state write path, skill size budgets — and runs the deterministic test suite.
Sub-skill chaining for context efficiency. /continue → /progress quick → /teach → /reflect, each passing --invoked-from=<caller> so callees skip redundant KB loads.
/teach walks you through concepts step by step, not just answering questions/reflect builds your awareness of HOW you learn/continue auto-invokes the quick check-in, teaching, practice, and reflection/plugin marketplace add https://codeberg.org/AnjanJ/bodhikit.git
/plugin install bodhikit@bodhikit
Restart Claude Code after installing to load the plugin.
Important: Enable only where you need it. BodhiKit loads 20 knowledge bases. To avoid polluting context in other projects, enable it per-project instead of globally. In your learningWithBodhi/.claude/settings.json:
{
"enabledPlugins": {
"bodhikit@bodhikit": true
}
}
Or disable it in projects where you do not need it by adding to .claude/settings.local.json:
{
"enabledPlugins": {
"bodhikit@bodhikit": false
}
}
npx claudepluginhub anjanj/bodhikit --plugin bodhikitFeature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Complete developer toolkit for Claude Code
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.