By shihwesley
TLDR-aware code simplifier — uses AST summaries for context, full reads only for target files. 80%+ token savings on large codebases. Merkle-integrated for O(1) change detection when used with mercator-ai.
Claude Code plugin that simplifies code using TLDR-aware AST summaries. Reads structure first via lightweight summaries, then targets only the files that need changes. Saves 80%+ tokens compared to reading every file fully.
When paired with mercator-ai, it uses the merkle manifest for O(1) change detection — only looking at files that actually changed.
# From the shihwesley-plugins marketplace
/plugin marketplace add shihwesley/shihwesley-plugins
/plugin install code-simplifier-tldr@shihwesley-plugins
# Or install directly from GitHub
/plugin install --source github shihwesley/code-simplifier-tldr
# Simplify recently modified files
/simplify-tldr
# Simplify a specific file
/simplify-tldr src/api/auth.ts
# Simplify files matching a pattern
/simplify-tldr src/components/*.tsx
The agent can also be triggered automatically by Claude Code when code simplification tasks are detected.
┌─────────────────────────────────────────────┐
│ 1. Merkle check (if mercator-ai installed) │
│ docs/.mercator.json → what changed? │
├─────────────────────────────────────────────┤
│ 2. TLDR summaries for changed files │
│ AST structure, ~200 tokens per file │
├─────────────────────────────────────────────┤
│ 3. Line-range reads for target sections │
│ Only the functions you'll modify │
├─────────────────────────────────────────────┤
│ 4. Edit → Verify → Log │
│ Changes recorded in SIMPLIFICATION_LOG │
└─────────────────────────────────────────────┘
Token cost comparison (100-file codebase, 3 files changed):
| Approach | Tokens |
|---|---|
| Read all files fully | ~250,000 |
| TLDR all files | ~20,000 |
| Merkle diff + TLDR changed | ~650 |
SIMPLIFICATION_LOG.md| Type | File | Purpose |
|---|---|---|
| Agent | agents/code-simplifier.md | Core simplifier with TLDR + merkle protocol |
| Command | commands/simplify.md | /simplify slash command entry point |
docs/.mercator.json merkle manifest for O(1) change detection. Optional but recommended.MIT
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 pipeline + sandboxed Python execution for Claude Code. Turns any topic into agent expertise: structured question tree → source discovery → zero-context fetch (content never enters LLM context) → .mv2 indexing → REPL-based distillation → compact expertise artifact. Also runs Python in isolated Docker containers for code execution, DSPy sub-agents, and data analysis.
Maps codebases of any size using parallel Sonnet subagents with Merkle-tree change detection. Generates docs/CODEBASE_MAP.md with architecture diagrams, module guides, data flows, and navigation guides. Creates docs/.mercator.json merkle manifest for O(1) staleness checks — compare a single root hash to know if anything changed. Post-commit hook auto-refreshes hashes in ~2 seconds with zero API tokens. Supports incremental updates: only re-explores changed modules. Works without git via pure hash-based diff.
Reverse engineer and extract capabilities from any source — repos, configs, binaries, articles — into your agent workflow. Security scanning, manifest tracking, cross-agent restore.
Ambient dev environment management — auto-switches between dev, test, staging, and prod using Docker containers, sidecars, and task-aware classification. Provides /orbit commands for explicit control.
Ambient .tech.md generation — auto-documents and tracks freshness of your codebase
npx claudepluginhub shihwesley/shihwesley-plugins --plugin code-simplifier-tldr簡化和優化程式碼以提升清晰度、一致性和可維護性,同時保持原有功能不變
Agent and skills for code simplification and refactoring to improve code quality while preserving functionality
Extract functions, simplify complex code, and reduce cognitive complexity
AST-powered code compression for LLMs. Send 89% fewer tokens, get the same understanding. Parses your code with tree-sitter, keeps the signal, drops the noise.
Open-source, local-first Claude Code plugin for token reduction, context compression, and cost optimization using hybrid RAG retrieval (BM25 + vector search), reranking, AST-aware chunking, and compact context packets.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.