An implementation command for carrying out a planned feature in phases. It uses planning documents, specialized agents, and checks between phases.

Use it to run implementation phases, execute or validate a specific phase, or deliberately skip a validation gate when appropriate.

It provides a structured path from an approved plan to working code and can stop or validate work at defined points. It requires the feature's plan to exist first.

implement — Command by Rito-w

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.

agentmods

npx agentmods add commands/rito-w/claude-code-best-practice-zh/implement

Clone the repo

git clone --depth 1 https://github.com/Rito-w/claude-code-best-practice-zh

Made for: Claude Code.

Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,665 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin 100% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5	$0.00006	$0.03665
Opus 5	$0.00003	$0.01833
Sonnet 5	$0.00001	$0.00733
Haiku 4.5	$0.00001	$0.00366

Measured 2d ago against content hash 2ba1c8ae518b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement 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 2d 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.

Origin

This is a copy

100% identical to implement — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

development-workflows/rpi/.claude/commands/rpi/implement.md · 635 lines

How it starts

The opening of the file, as written. The whole thing — 635 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Input

$ARGUMENTS

You MUST parse the user input to extract the feature slug (the folder name in rpi/).

Purpose

This command executes phased implementation of features based on planning documentation. It orchestrates specialized agents, enforces validation gates, and ensures constitutional compliance throughout implementation.

Prerequisites:

Feature folder exists at rpi/{feature-slug}/
Planning completed (rpi/{feature-slug}/plan/PLAN.md exists)

Output Location: rpi/{feature-slug}/implement/

This is Step 4 of the RPI Workflow (final step - actual implementation).

Flags

--phase N: Execute specific phase number (1-8), if omitted starts from phase 1
--validate-only: Only validate current phase, don't implement
--skip-validation: Skip validation gate and proceed (use with caution)

Available Agents

All agents use Opus model for maximum quality.

Implementation Agent

Agent	Type	When to Use
`senior-software-engineer`	Custom	All implementation tasks

Support Agents

Agent	Type	Purpose
`Explore`	Built-in	Pre-implementation code exploration
`code-reviewer`	Custom	Code review and quality validation
`constitutional-validator`	Custom	Validate against project constitution
`documentation-analyst-writer`	Built-in	Documentation generation

Agent Routing

All implementation tasks are handled by the senior-software-engineer agent.

Phase 0: Load Context and Rules

Prerequisites: Feature slug parsed from user input

Process:

0.1 Load Project Constitution

Check for a constitution or principles document in the repository
If exists, extract:
- Technical constraints (type safety, testing, component isolation)
- Business principles (quality standards, workflow)
- Architectural boundaries
Store constraints for enforcement during implementation

Read the full file on GitHub · 635 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.

2d ago First seen · 635 lines · 6 tokens per session scan A 2ba1c8ae518b

Subscribe to this mod's changes

implement is a command published in the GitHub repository Rito-w/claude-code-best-practice-zh (10 stars, last pushed 2mo ago), licensed MIT. It adds 6 tokens to every session and 3,665 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to implement, differing in 0 lines, and is treated as a copy.

Planning

implement