Jia-Ethan GitHub avatar

claude-keysmith

Jia-Ethan

claude-keysmith is a local instruction deployment tool for Claude Code that manages import blocks in CLAUDE.md files with dry-run, backup, and uninstall capabilities.

Stars

426

7-day growth

No data

Forks

78

Open issues

1

License

MIT

Last updated

2026-07-28

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It provides reversible, structured management of Claude Code instructions, avoiding manual file edits and optionally integrating a runtime wrapper that aligns system prompts across shell sessions.

Who it is for

  • Developers using Claude Code
  • Teams managing CLAUDE.md across multiple projects
  • Users who want to customize system prompts without manual patching
  • CLI tool maintainers who need reproducible instruction deployment

Use cases

  • Installing project-specific instruction blocks into CLAUDE.md or CLAUDE.local.md
  • Deploying runtime system prompts and append prompts with a zsh wrapper
  • Previewing all changes with dry-run before applying any writes
  • Uninstalling managed blocks and files cleanly without leftover artifacts

Strengths

  • Dry-run mode shows exactly what will change before writing
  • Backup is always created before any file modification
  • Uninstall only removes its own managed blocks and files
  • Supports both project-scope and user-scope deployment with distinct semantics

Considerations

  • Runtime wrapper currently only configures zsh (~/.zshrc)
  • Does not manage Claude Code binary, network, MCP, or credentials
  • Backup files are not automatically cleaned up; manual removal needed after confirming rollback not required

README quick start

快速开始（macOS / Linux）

Description

Claude Code CLAUDE.md import-block installer for local instruction files

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482