Morph Apply

This is a speed optimization for editing large files you haven't read yet. Instead of burning tokens to read a 1000 line file just to add three lines of error handling, you pass a code snippet with markers like "// ... existing code ..." and let Morph's API figure out where it goes. Processes at 10,500 tokens per second with 98% accuracy. The tradeoff is obvious: you need the MCP server configured and you're trusting the API to place your edit correctly, but when you're working with big files or doing batch edits where you know the context, it beats reading the whole thing into Claude first.

skills.sh installs: 489
GitHub stars: 3.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add parcadei/continuous-claude-v3 --skill morph-apply --agent claude-code

Installs into .claude/skills of the current project.

Files

Morph Fast Apply

Fast, AI-powered file editing using the Morph Apply API. Edit files without reading them first. Processes at 10,500 tokens/sec with 98% accuracy.

When to Use

Fast file edits without reading entire file first
Batch edits to a file (multiple changes in one operation)
When you know what to change but file is large
Large files where reading would consume too many tokens

Key Pattern: Code Markers

Use // ... existing code ... (or language-appropriate comments) to mark where edits go:

# ... existing code ...
try:
    result = process()
except Exception as e:
    log.error(e)
# ... existing code ...

The API intelligently places your edit in the right location.

Usage

Add error handling

uv run python -m runtime.harness scripts/mcp/morph_apply.py \
    --file "src/auth.py" \
    --instruction "Add error handling to login function" \
    --code_edit "# ... existing code ...
try:
    user = authenticate(credentials)
except AuthError as e:
    log.error(f'Auth failed: {e}')
    raise
# ... existing code ..."

SKILL.md on GitHub