implement

A command for implementing a software plan that has already been written. It includes reviews of the approach, risks, code quality, and tests before completing the work.

In plain words
What is it for?
Use it to turn a detailed plan into code, tests, and a safe pull-request workflow, with automatic stopping when the change becomes too risky or complex.
Why use it?
It adds checks around implementation so the change is less likely to introduce regressions, unnecessary complexity, or unsafe branch operations.

Command for Claude Code

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/parslee-ai/neo/implement
Clone the repo
git clone --depth 1 https://github.com/Parslee-ai/neo

Made for: Claude Code.

Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,260 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00040 $0.03260
Opus 5 $0.00020 $0.01630
Sonnet 5 $0.00008 $0.00652
Haiku 4.5 $0.00004 $0.00326

Measured 2d ago against content hash 83dee5884c69, 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.

.claude/commands/implement.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Usage

# Paste plan, run command
/quick-implement

# Or inline (for single-line summaries)
/implement "Add user profile dropdown to sidebar: create ProfileMenu component, integrate with auth context, add tests, commit to feature/profile-menu"

Purpose

Implements a pre-written plan with all neo protocol gates intact:

  • Neo strategic review (catch over-engineering)
  • Liotta economic analysis (validate leverage)
  • Sentinel risk assessment (branch safety)
  • Linus code review (kernel standards)
  • Test validation (no regressions)
  • Sentinel git ops (safe PR)

No human gating. Proceeds automatically unless stop rules trigger.

Constraints

  • No broken behavior
  • Only @code-implementer writes code. Only @sentinel does git
  • If branch risk > low → temp branch + PR + rollback
  • Stop if complexity explodes or no safe path
  • Each quick test ≤ 30s

Turn Protocol

Phase 1: Validate & ParallelPlan

Step 1.0: Parse Input

  • Extract plan from parameter or last code block in conversation
  • Restate: approach summary, files/symbols, constraints, acceptance criteria
  • Classify risk: LOW/MEDIUM/HIGH (files changed, criticality, scope)

Step 1.1: Neo Strategic Review (parallel)

  • INVOKE Task tool:
    • subagent_type: "neo:neo"
    • description: "Neo review of implementation plan"
    • prompt: "Review this implementation plan. Plan: {full_plan}. Provide: (1) Approach critique—is it the simplest viable path?, (2) Over-engineering red flags, (3) Simpler alternatives if any, (4) Key risks overlooked, (5) Missing edge cases or tests, (6) Concrete refinements. Be brutally honest."

Step 1.2: Economic Analysis (parallel)

  • INVOKE Task tool:
    • subagent_type: "liotta"
    • description: "Economic analysis of plan"
    • prompt: "Analyze this plan for measurable impact. Plan: {full_plan}. Provide: (1) Scope & complexity assessment, (2) Impact on system (perf, maintainability, risk), (3) Measurable success metrics, (4) Risks and failure modes, (5) Recommend proceed/refine/stop."

Read the full file on GitHub · 263 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. 2d ago First seen · 263 lines · 40 tokens per session scan A 83dee5884c69

Subscribe to this mod's changes

implement is a command published in the GitHub repository Parslee-ai/neo (15 stars, last pushed 2d ago), licensed Apache-2.0. It adds 40 tokens to every session and 3,260 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 2026-08-30.