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 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?
mkdir -p ~/.claude/skills/patch-edit # Save SKILL.md to ~/.claude/skills/patch-edit/SKILL.md
- 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.
- 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.
- 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.
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.