discipline-refactor-phase-3-execution
Sub-skill of discipline-refactor: Phase 3: Execution.
Best use case
discipline-refactor-phase-3-execution is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Sub-skill of discipline-refactor: Phase 3: Execution.
Teams using discipline-refactor-phase-3-execution should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/phase-3-execution/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How discipline-refactor-phase-3-execution Compares
| Feature / Agent | discipline-refactor-phase-3-execution | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Sub-skill of discipline-refactor: Phase 3: Execution.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
# Phase 3: Execution
## Phase 3: Execution
**Spawn**: `Task` with `subagent_type=general-purpose`
**Call**: `@git-sync-manager`, `@parallel-batch-executor`
**Prompt**:
```
Execute module-based refactoring:
Migration Plan: {migration_plan}
Package Name: {package_name}
Disciplines: {disciplines}
Execute in order:
1. BACKUP:
git tag pre-module-refactor-$(date +%Y%m%d)
2. CREATE MODULE STRUCTURE:
# For each discipline in [_core, discipline-1, ...]:
mkdir -p src/<package>/modules/<discipline>
mkdir -p tests/modules/<discipline>
mkdir -p docs/modules/<discipline>
mkdir -p specs/modules/<discipline>
mkdir -p data/modules/<discipline> # if data/ exists
mkdir -p .Codex/skills/<discipline>
3. MOVE CODE:
# Move source files to appropriate modules
# Update __init__.py in each module
# Preserve git history with git mv
4. MOVE TESTS:
# Move test files to mirror source structure
# Update test imports
5. MOVE DOCS:
# Move documentation to module folders
# Update internal links
6. MOVE SPECS:
# Move specifications to module folders
# Keep templates/ at top level
7. UPDATE IMPORTS:
# Search and replace import paths
# from <pkg>.old_path → from <pkg>.modules.<discipline>
# Update conftest.py
# Update pyproject.toml entry points
8. UPDATE CONFIGS:
# pyproject.toml: packages, entry points
# Update CI/CD paths
# Update Makefile/scripts
9. CREATE MODULE README:
# Add README.md to each module explaining purpose
Report progress. Stop on failure.
```
---Related Skills
digitalmodel-worktree-test-execution-with-shared-venv
Run digitalmodel tests from isolated worktrees without uv editable-dependency failures by using the main repo's existing virtualenv and PYTHONPATH.
plan-gated-issue-execution-wave
Execute a multi-issue architecture/planning wave in a plan-gated repo, then safely transition approved issues into implementation with file-based Codex prompts, local approval markers, subprocess monitoring, and cleanup handling for sandbox/hook edge cases.
work-around-merge-conflicts-in-test-execution
Run tests when repo has unresolved merge conflicts in config files by bypassing broken configs and executing tests directly
wave-based-parallel-plan-execution
Orchestrate phase execution by discovering dependencies, grouping into waves, spawning subagents, and collecting results with optional wave filtering
plan-governance-vs-execution-boundary-for-adversarial-review
Keep stale-approval/governance remediation out of execution-path pseudocode, TDD, files-to-change, and deliverable acceptance when hardening a GitHub issue plan under adversarial review.
interactive-issue-execution-worktree-guardrails
Execute approved GitHub issues in isolated worktrees with interactive Codex/Codex runs, while containing agent drift and salvaging progress when provider/runtime problems occur.
gtm-prospect-pipeline-phased-execution
Phased execution pattern for
workspace-hub-batch-issue-execution
Deprecated alias for gh-work-execution.
gh-work-execution
Canonical GitHub issue execution route after plan approval — strengthened resource intelligence, TDD-first implementation, targeted validation, adversarial review, delegation controls for Codex agent teams, GitHub progress posting, future-issue capture, and commit/push with closeout discipline.
gh-work-execution-checklist
Compact live-execution checklist companion for approved GitHub issue work. Use during active implementation as a fast operational route; gh-work-execution remains the canonical source of truth.
aqwa-batch-execution
Run ANSYS AQWA analyses in batch/headless mode on Linux. Covers CLI execution, DAT input file structure, multi-stage analysis chaining, output file parsing, failure diagnosis, and HPC job scheduling.
gemini-batch-execution
Execute Gemini research tasks in efficient batches using hermes router to maximize $20/month quota utilization. Covers toolset config, batch patterns, sandbox pitfalls, and cleanup.