Skip to main content
Agent skill

Patch Edit

Apply one rewrite-plan step at a time as small reviewable file edits, never rewriting whole files when a localised change suffices.

Get started

Get the complete skill folder, including its scripts and reference files.

When to use this skill

Use Patch Edit when an AI agent needs a reusable SKILL.md workflow for this job: Apply one rewrite-plan step at a time as small reviewable file edits, never rewriting whole files when a localised change suffices.

When not to use it

Skip Patch Edit when the task is outside the coding category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.

How to install

Where will you use it?

Install scope
Claude Code folder setup
mkdir -p ~/.claude/skills/patch-edit
# Save SKILL.md to ~/.claude/skills/patch-edit/SKILL.md
  1. Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/patch-edit/SKILL.md. For a shared project, commit the folder at .claude/skills/patch-edit/ instead.
  2. Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
  3. For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.

Full install guide for Claude, Cursor, and Codex →

Try a starter prompt

After installing the skill, paste this starter prompt into your agent to verify it triggers on a small task.

Starter prompt
Use the Patch Edit skill for this task: Use Patch Edit when this documented workflow matches the task. Confirm any required inputs or files before making changes.

What supports this recommendation?

69/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.

Documentation
73/100
Practical detail
68/100
Source evidence
63/100
Source signals
72/100
Model compatibility evidence
  • claudeuntested

    No model-specific signal or recorded compatibility test was found.

  • chatgptuntested

    No model-specific signal or recorded compatibility test was found.

  • geminiuntested

    No model-specific signal or recorded compatibility test was found.

  • copilotuntested

    No model-specific signal or recorded compatibility test was found.

  • llamauntested

    No model-specific signal or recorded compatibility test was found.

  • perplexityuntested

    No model-specific signal or recorded compatibility test was found.

  • mistraluntested

    No model-specific signal or recorded compatibility test was found.

  • grokuntested

    No model-specific signal or recorded compatibility test was found.

Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.

What this skill does

# Patch edit

Spec §20.3 / §21.3.2: code-migration / tune-collab cannot ship a trustworthy diff when the agent rewrites whole files in one pass — the reviewer can't audit the change. This atom enforces "one step per turn, smallest possible localised edit".

## Inputs

- `plan/steps.json` from `rewrite-plan`. - The current value of `iterations` (the daemon's per-stage counter). - `code/index.json` for the file's known imports + neighbours.

## Output

The atom mutates files inside the project cwd via the `file-edit` tool. After every iteration, it writes a per-step receipt:

```text project-cwd/ └── plan/ ├── steps.json (status updated: 'pending' → 'completed' | 'skipped') └── receipts/ └── step-<id>.json # { files: ['...'], diffSummary, rationale, completedAt } ```

## Convergence

The atom completes when every step in `plan/steps.json` is in a terminal state (`completed` / `skipped`) OR `iterations >= OD_MAX_DEVLOOP_ITERATIONS`. Use:

```jsonc { "id": "patch-edit-loop", "atoms": ["patch-edit"], "repeat": true, "until": "plan.steps.terminal === plan.steps.total || iterations >= 8" } ```

## Anti-patterns the prompt fragment forbids

- Rewriting an entire file when the rewrite-plan step is localised. - Touching a file outside the step's `files[]`. - Touching a `shell`-tier file when the step's `risk` is not `'high'` or the user hasn't confirmed. - Skipping a step without a receipt + a rationale string.

## Status

Implemented by the daemon runner in `apps/daemon/src/plugins/atoms/patch-edit.ts`. It validates step ownership and risk, applies unified diffs with atomic writes, and records receipts and progress.

Intended uses

  • Use Patch Edit when this documented workflow matches the task.

Implementation notes

  • Review the source instructions and adapt inputs before running the workflow.

Try it, then tell us how it went

A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.