# Workflow Checkpoint Refactor

> Multi-phase refactoring with checkpoint files that survive context limits. Use when refactoring spans 10+ files, needs phased rollout, or risks running out of context mid-session.

- Skill: `laurigates/workflow-checkpoint-refactor` (Agent Skill)
- Install (CLI): `npx skillmds@latest add laurigates/workflow-checkpoint-refactor`
- Raw SKILL.md: https://api.skillmd.com/api/skills/laurigates/workflow-checkpoint-refactor/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: laurigates (https://skillmd.com/u/laurigates)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/laurigates/workflow-checkpoint-refactor

---


# /workflow:checkpoint-refactor

Multi-phase refactoring with persistent state that survives context limits and session boundaries.

## When to Use This Skill

| Use this skill when... | Use direct refactoring instead when... |
|------------------------|---------------------------------------|
| Refactoring spans 10+ files | Changing 1-5 files |
| Work will exceed context limits | Small, focused change |
| Need to resume across sessions | Single-session task |
| Multiple dependent phases | Independent file changes |
| Team coordination on large refactor | Solo quick fix |

## Context

- Repo root: !`git rev-parse --show-toplevel`
- Plan file exists: !`find . -maxdepth 1 -name REFACTOR_PLAN.md`
- Git status: !`git status --porcelain`
- Recent commits: !`git log --oneline --max-count=5`

## Parameters

- **`--init`**: Create a new refactoring plan interactively
- **`--continue`**: Resume from the last completed phase
- **`--status`**: Show current plan progress
- **`--phase=N`**: Execute a specific phase

## Plan File Format

The plan file (`REFACTOR_PLAN.md`) serves as persistent state. It is the loop's
**compact state packet** (`.claude/rules/loop-integrity.md`): a fresh session,
or a sub-agent with no memory of prior phases, must be able to re-enter from this
file alone. Every phase therefore carries not just *what to do* but *what was
verified* and *what changed* — without those, resuming across a context limit
silently redoes or undoes work.

```markdown
# Refactor Plan: {description}

Created: {date}
Last updated: {date}
Base commit: {hash}
Exit condition: {the literal criterion that ends the whole refactor — e.g. "all phases done, full suite + tsc green on base"}

## Overview
{What is being refactored and why}

## Phase 1: {phase name}
- **Status**: done | in-progress | pending | needs-review
- **Files**: file1.ts, file2.ts, file3.ts
- **Description**: {what this phase does}
- **Acceptance criteria**: {how to verify success — the phase's exit condition}
- **Verifier result**: {what the independent check returned — PASS/FAIL + the criterion it judged; filled in at the phase boundary}
- **Changed since last run**: {what this phase actually touched, so a successor doesn't redo or undo it}
- **Result**: {summary of changes made, filled in after completion}

## Phase 2: {phase name}
- **Status**: pending
- **Files**: file4.ts, file5.ts
- **Description**: {what this phase does}
- **Acceptance criteria**: {how to verify success}
- **Verifier result**: {empty until verified}
- **Changed since last run**: {empty until completed}
- **Result**: {empty until completed}

...
```

## Execution

Execute this multi-phase refactoring workflow:

### Step 1: Initialize refactoring plan (--init mode)

If `--init` flag provided:

1. Analyze scope: Read files to be refactored, understand dependencies
2. Define phases where each:
   - Touches 3-7 files (bounded scope)
   - Has clear acceptance criteria (tests, type check)
   - Can be committed independently
   - Builds on previous phases
3. Write plan file: Create `REFACTOR_PLAN.md` at repo root
4. Record base commit: `git log --format='%H' -1`

**Phase ordering**: Shared utilities/types first, leaf components last, tests alongside implementation.

### Step 2: Resume existing refactor (--continue mode)

If `--continue` flag provided:

1. Read `REFACTOR_PLAN.md`
2. Find next pending phase (status `pending` or `needs-review`)
3. Verify all prior phases are `done`
4. Execute phase (go to Step 4)

### Step 3: Check progress (--status mode)

If `--status` flag provided:

1. Read `REFACTOR_PLAN.md`
2. Parse plan and display status table with phases, descriptions, statuses, file counts
3. Exit

### Step 4: Execute target phase (--phase=N or selected via Step 2)

For each phase:

1. Read context from plan file (current phase's details)
2. Read only the files listed for this phase
3. Implement changes according to phase description
4. Validate with appropriate tool (tsc, ty check, cargo check, or npm/pytest test)
5. If validation fails:
   - Fix errors if straightforward
   - If complex, mark phase as `needs-review` with error details
   - Commit partial work with `WIP:` prefix
6. If validation passes, **gate `done` on an independent verifier** when the
   acceptance criteria are a judgement (e.g. "the class is now single-purpose"),
   not a purely mechanical check (a green suite / clean `tsc` is already
   independent — a failing test does not care how hard you worked):
   - Dispatch a fresh `Task` sub-agent that reads **only** this phase's
     acceptance criteria and the resulting diff — not the worker's reasoning —
     and judges whether the criteria are met. The worker is biased toward
     declaring completion; the loop's stop condition must come from outside it
     (`.claude/rules/loop-integrity.md`, Pillar 1). When the criteria are about
     **behaviour** ("endpoint returns X", "the bug no longer reproduces"),
     delegate this to `agent-patterns-plugin:execution-grounded-review`, which
     runs the suite first and grounds each criterion in execution evidence
     rather than appearance.
   - Record the verdict in the phase's **Verifier result** field (PASS/FAIL +
     the criterion judged).
   - If the verifier returns FAIL, leave status `in-progress`/`needs-review`
     and address the gap before marking `done`.
7. Once verified, update the plan file: set status to `done`, fill **Verifier
   result**, **Changed since last run**, and **Result**, then commit:
   `git add -u && git commit -m "refactor phase N: {description}"`
8. If more phases remain, proceed to next phase or suggest `--continue`

### Step 5: Sub-agent delegation (for large phases)

For phases with 7+ files, delegate to Task sub-agent with:
- File list to modify
- Phase description and acceptance criteria
- Instructions: run validation, update plan file, stage/commit changes
- If validation fails: mark phase as `needs-review` with error details

## Recovery Patterns

| Situation | Action |
|-----------|--------|
| Context limit hit mid-phase | Start new session, run `--continue` |
| Phase marked needs-review | Read plan for details, fix issues, run `--phase=N` |
| Tests broken after a phase | Revert phase commit, investigate, re-execute |
| Plan needs adjustment | Edit REFACTOR_PLAN.md directly, update phases |
| Base branch moved | Rebase onto new base, re-validate completed phases |

## Agentic Optimizations

| Context | Command |
|---------|---------|
| Check plan exists | `test -f REFACTOR_PLAN.md && echo "exists"` |
| Quick typecheck | `npx tsc --noEmit --pretty 2>&1 \| head -20` |
| Quick test | `npm test -- --bail=1 2>&1 \| tail -20` |
| Phase commit | `git commit -m "refactor phase N: description"` |
| Verify working state | `npx tsc --noEmit && npm test -- --bail=1` |
| Show plan phases | `grep "^## Phase" REFACTOR_PLAN.md` |
| Show phase status | `grep -A1 "^## Phase" REFACTOR_PLAN.md \| grep Status` |

## Quick Reference

| Operation | Command |
|-----------|---------|
| Init new refactor | `/workflow:checkpoint-refactor --init` |
| Check progress | `/workflow:checkpoint-refactor --status` |
| Resume work | `/workflow:checkpoint-refactor --continue` |
| Run specific phase | `/workflow:checkpoint-refactor --phase=3` |
| Manual plan edit | Edit `REFACTOR_PLAN.md` directly |

## Related Skills

- [code-review-checklist](../../../code-quality-plugin/skills/code-review-checklist/SKILL.md) - Review refactored code
- [refactoring-patterns](../../../code-quality-plugin/skills/refactoring-patterns/SKILL.md) - Refactoring techniques
- [adversarial-review](../../../agent-patterns-plugin/skills/adversarial-review/SKILL.md) - The isolated verifier a judgement-based phase gate delegates to
- [execution-grounded-review](../../../agent-patterns-plugin/skills/execution-grounded-review/SKILL.md) - The execution-grounded verifier for behaviour-based phase acceptance criteria
- `.claude/rules/loop-integrity.md` - Why the plan file is a state packet and why `done` is judged independently