Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Phase Gated Commits

ASecurity

Phase-gated commit workflow for clean git history -- implement, review, test, commit per phase

530 stars
0 votes
0 copies
1 views
Added 5/29/2026
ai-agentsrefactoringgitapifrontendsecuritydocumentation

Works with

api

Security Analysis

A100/100

Scanned 5/29/2026

$npx -y skills add vibeeval/vibecosystem --skill phase-gated-commits --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Phase Gated Commits?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Phase Gated Commits
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/vibeeval-phase-gated-commits/badge)](https://www.skillsdirectory.com/skills/vibeeval-phase-gated-commits)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: phase-gated-commits
description: Phase-gated commit workflow for clean git history -- implement, review, test, commit per phase
---

# Phase-Gated Commits

Break large features and refactoring into discrete phases. Each phase follows a strict implement -> review -> test -> commit cycle. The result is a clean, bisectable git history where every commit represents a working state.

## When to Use

- Multi-file features where changes span 3+ files
- Refactoring that touches shared code used by many modules
- Any work where you want the ability to revert one phase without losing others
- Migrations or upgrades that should be applied incrementally

## When NOT to Use

- Single-file changes or small fixes
- Exploratory work where the final shape is unknown
- Prototyping where speed matters more than history

## Phase Structure

Break the work into 2-5 phases. Each phase should:
- Be independently functional (the codebase works after each commit)
- Have a clear scope (you can describe it in one sentence)
- Be reviewable in isolation (a reviewer can understand the diff without needing other phases)

### Phase Sizing

| Phase Size | Guideline |
|-----------|-----------|
| Too small | Renaming a single variable is not a phase |
| Right size | Add the data model + migration + basic tests |
| Too large | Implement entire feature end-to-end in one phase |

Aim for phases that touch 2-8 files each. If a phase touches more than 10 files, consider splitting it further.

## Workflow Per Phase

```
Phase N:
  1. IMPLEMENT -- Write the code for this phase only
  2. REVIEW    -- Self-review the diff, check for issues
  3. TEST      -- Run tests, verify nothing is broken
  4. COMMIT    -- Create a single commit for this phase
  5. PAUSE     -- Wait for user confirmation before Phase N+1
```

### Step 1: Implement

Write only the code that belongs to this phase. Do not reach ahead into the next phase. If you realize the current phase needs to be larger, stop and re-scope before continuing.

### Step 2: Review

Review your own diff before committing:
- Are there debug statements or commented-out code?
- Does the code follow existing patterns in the codebase?
- Are there any security concerns (hardcoded values, missing validation)?
- Is the change minimal -- nothing extra included?

If review finds issues, fix them within the same phase. Do not defer fixes to a later phase.

### Step 3: Test

Run the project test suite. At minimum:
- Existing tests must still pass (no regressions)
- New code should have tests if the codebase has test coverage
- If tests fail, fix within the current phase

### Step 4: Commit

Create one commit per phase with a descriptive message.

**Commit message format:**

```
feat(phase N/M): <description of what this phase accomplishes>

<Optional body explaining WHY this phase exists as a separate unit>
```

Examples:
```
feat(phase 1/3): add user preference data model and migration

Separate from the API layer so the schema can be reviewed independently.

feat(phase 2/3): implement preference API endpoints with validation

Builds on the data model from phase 1. Includes input validation
with zod schemas and error handling for all edge cases.

feat(phase 3/3): add preference UI components and integration tests

Connects the API to the frontend. Integration tests cover the
full create/read/update flow.
```

### Step 5: Pause

After committing, pause and confirm with the user before starting the next phase. This gives the user a chance to:
- Review what was committed
- Adjust the plan for remaining phases
- Stop early if the work so far is sufficient

## Rules

1. **One commit per phase.** Do not batch multiple phases into one commit or split one phase into multiple commits.
2. **No forward references.** Phase N should not depend on code that will be written in Phase N+1. Each commit must leave the codebase in a working state.
3. **Fix before advancing.** If review or tests reveal a problem, resolve it in the current phase. Never push a known issue to the next phase.
4. **Phases are sequential.** Do not start Phase N+1 until Phase N is committed. This ensures each phase builds on a verified foundation.
5. **Re-scope when needed.** If mid-implementation you realize the phase breakdown is wrong, stop, revise the plan, and communicate the change. Do not silently merge phases.
6. **Keep phases balanced.** Avoid one giant phase followed by tiny cleanup phases. Redistribute work so each phase carries meaningful weight.

## Integration with Plan Documentation

When using this skill alongside `plan-documentation`:
- Each phase in the plan maps to one phase-gated commit
- Phase completion docs (`<task>-phase-N-complete.md`) are written after the commit
- The plan file phase status is updated after each commit

Attribution

vibeevalvibeeval
View sourceSee grades on GitHubMore from vibeeval →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →