Safely swap ~/.claude/CLAUDE.md for test/joke configs via symlink, with terminal-only restore that does not depend on the harness
Swap ~/.claude/CLAUDE.md for test configs via symlink, with terminal-only restore that does not depend on the Claude harness.
You want to try weird, joke, or character-heavy CLAUDE.md configs without risking your real one. Naive approaches (rename the file, write a new one in place) are fragile: a partial failure can leave you with no real CLAUDE.md, and a hostile test config can instruct Claude to refuse to restore it.
This plugin uses a symlink swap plus terminal-only recovery scripts so the harness is never in the recovery path. If the test config tells Claude to do nothing but recite a UUID, you still recover by running one shell command.
configs/ — the library of test CLAUDE.md filesbin/activate.sh <name> — swap CLAUDE.md for configs/<name>.md (terminal only)bin/restore.sh — restore the real CLAUDE.md, idempotent (terminal only)bin/status.sh — report current stateskills/safety-check/ — plugin skill that walks the user through the swap without executing it# see what's currently active
~/repos/github/my-repos/Claude-MD-Tester/bin/status.sh
# swap in a test config
~/repos/github/my-repos/Claude-MD-Tester/bin/activate.sh symlink-test
# (start a fresh Claude Code session to test)
# restore — always safe, always idempotent
~/repos/github/my-repos/Claude-MD-Tester/bin/restore.sh
The first activate moves the real ~/.claude/CLAUDE.md to ~/.claude/CLAUDE.md.real and symlinks CLAUDE.md to the chosen config. Restore reverses that. Subsequent activates just relink — the backup is touched only on the first swap.
CLAUDE.md.real already exists when activate is asked to back up a regular file, it aborts. You will never silently lose your real config to a stale backup collision.status.sh shows whether you're in test mode at a glance.Drop a markdown file in configs/. The filename (without .md) becomes the config name. That's it.
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 danielrosehill/claude-code-plugins --plugin claude-md-testerComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Modern R development skills for Claude Code - tidyverse patterns, rlang metaprogramming, Bayesian inference, performance optimization, and more
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Claude Code plugin: ideation and planning workflow — capture, evaluate, rank, simulate, and plan ideas, with ideation/single-idea-eval/multi-idea-ranking/feature-ideas/simulation/idea-capture variants.
First-pass data analysis toolkit: correlations, PII flagging, anomalies, hypothesis tests, data dictionaries, and trend analysis on a dataset in a folder.
Claude Code plugin for generating personal user manuals and private documentation for codebases. Creates personalized, private reference guides with PDF output support.
Research, filter, compare, and evaluate AI models on OpenRouter — discover models by capability (tool use, vision, audio), get cost/context-aware recommendations, run head-to-head comparisons, and conduct deep research that goes beyond the OpenRouter catalog.
Claude Code plugin for writing assistance, proofreading, style editing, and text transformation workflows.