phased-implementation

phased-implementation is a skill for Claude Code, Codex from lstudlo/curated-skills. It costs 37 tokens per session (602 once invoked), scanned A, original, MIT.

A workflow for delivering large software changes in separate, complete phases, with each phase tested and committed before the next begins.

In plain words
What is it for?
Use it for multi-feature work, large refactors, or projects that can be divided into independent database, API, frontend, or testing stages.
Why use it?
It makes complex projects easier to isolate, review, test, and recover when a later phase has problems.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for multi-feature work, large refactors, or projects that can be divided into independent database, API, frontend, or testing stages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lstudlo/curated-skills/phased-implementation
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add lstudlo/curated-skills --skill phased-implementation
Clone the repo
git clone --depth 1 https://github.com/lstudlo/curated-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for phased-implementation

README.md
[![agentmods](https://agentmods.dev/badge/skills/lstudlo/curated-skills/phased-implementation.svg)](https://agentmods.dev/skills/lstudlo/curated-skills/phased-implementation)
Your own site
<a href="https://agentmods.dev/skills/lstudlo/curated-skills/phased-implementation"><img src="https://agentmods.dev/badge/skills/lstudlo/curated-skills/phased-implementation.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 602 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.00602
Opus 5 $0.00018 $0.00301
Sonnet 5 $0.00007 $0.00120
Haiku 4.5 $0.00004 $0.00060

Measured 7d ago against content hash 5c3c03ad1142, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

phased-implementation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

src/skills/phased-implementation/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phased Implementation

Four Core Principles

1. Divide Meaningful Phases

Break work into independent, testable chunks where each phase is a complete, logical unit.

Phase types:

  • Feature-based: One complete feature per phase
  • Layer-based: Database → API → Frontend → Tests
  • Dependency-based: Base types → Data → Service → Presentation

Phase must be:

  • Logically independent (testable in isolation)
  • Clearly bounded (obvious when done)
  • Committable (produces working code)

2. Git Worktree-based Workflow

Use git worktrees to isolate each phase in its own working directory.

Workflow:

# Create worktree
git worktree add ../<phase-name> main

# Implement phase, commit changes

# Merge to main, then remove
git worktree remove ../<phase-name>

3. Commit After Each Phase

Every completed phase is committed before starting the next. Use the git-commit skill for proper commit message formatting.

Commit format: Describe the specific unit completed

feat: add user registration form component
- Implement form fields (username, email, password)
- Add validation logic
- Connect to registration API

❌ Avoid: WIP: started working on user features, feat(phase-1): xxx, feat(auth-phase): xxx — phase labels make commits meaningless

4. Ground with MCP Documentation

MANDATORY: Before any implementation, research using MCP docs/web search for current, version-specific documentation. Never rely on training data or assumptions.

Implementation Workflow

0. Research documentation (MCP tools) → 1. Plan phases →
2. Execute phase → 3. Verify → 4. Commit → 5. Repeat

When NOT to Use

  • Single-phase work: Small changes, one-off adjustments
  • Tightly coupled changes: Must be atomic to work
  • Hotfixes: Urgent fixes where speed > phased approach

Examples

E-commerce Checkout Flow (3 phases):

Phase 1: Shopping cart implementation
Phase 2: Payment integration
Phase 3: Order confirmation and email notifications

Read the full file on GitHub · 92 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 92 lines · 37 tokens per session scan A 5c3c03ad1142

Subscribe to this mod's changes

phased-implementation is a skill published in the GitHub repository lstudlo/curated-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 602 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.