implement

implement is a skill for Claude Code from GoogilyBoogily/googilyboogily-claude-power-tools. It costs 51 tokens per session (3,104 once invoked), scanned A, original, MIT.

A tool that turns a High Level Design or Low Level Design into working code through planned phases and checks. It first examines what is missing and then verifies whether the intended result was achieved.

In plain words
What is it for?
Use it to implement finalized designs, organize work into phases, pause and resume multi-session work, and verify the finished changes.
Why use it?
It connects architecture documents to implementation while exposing gaps and checking the actual outcome, rather than only marking tasks as done.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool.

Part of the architecture-docs plugin — 19 skills shipped together

Good fit Use it to implement finalized designs, organize work into phases, pause and resume multi-session work, and verify the finished changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/googilyboogily/googilyboogily-claude-power-tools/implement
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 GoogilyBoogily/googilyboogily-claude-power-tools --skill implement
Clone the repo
git clone --depth 1 https://github.com/GoogilyBoogily/googilyboogily-claude-power-tools

Made for: Claude Code.

Or install architecture-docs, the plugin that ships this one along with the rest of its 19 skills.

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 implement

README.md
[![agentmods](https://agentmods.dev/badge/skills/googilyboogily/googilyboogily-claude-power-tools/implement/github.svg)](https://agentmods.dev/skills/googilyboogily/googilyboogily-claude-power-tools/implement)
Your own site
<a href="https://agentmods.dev/skills/googilyboogily/googilyboogily-claude-power-tools/implement"><img src="https://agentmods.dev/badge/skills/googilyboogily/googilyboogily-claude-power-tools/implement/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for implement

Your own site · 80×15
<a href="https://agentmods.dev/skills/googilyboogily/googilyboogily-claude-power-tools/implement"><img src="https://agentmods.dev/badge/skills/googilyboogily/googilyboogily-claude-power-tools/implement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,104 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00051 $0.03104
Opus 5 $0.00026 $0.01552
Sonnet 5 $0.00010 $0.00621
Haiku 4.5 $0.00005 $0.00310

Measured 12d ago against content hash 253af511f8e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

implement scanned grade A with 1 finding 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| T-01 | Truth | GraphQL responds with schema | `curl /graphql` + check introspection |
plugins/architecture-docs/skills/implement/SKILL.md · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Document Implementation

Translate an HLD or LLD into working code through phased, verified implementation with goal-backward verification. Performs gap analysis, establishes must-haves before execution, and verifies the actual goals were achieved — not just that tasks completed.

When to Use

Use after an HLD or LLD is finalized and ready for implementation. Works best with LLDs (which contain file-level implementation plans), but can also work from HLDs at a higher level.

Use --resume to continue from a paused implementation session.

Source Integrity Rules

Every factual claim about the codebase must be verified through tool calls in this session.

  1. Cite your work. When referencing code, patterns, or architecture, cite the specific tool call that discovered it (file path + line number from Read, Grep result, Explore agent finding).
  2. Never reference prior Claude sessions or Claude memory. Do not source implementation decisions from auto-memory, MCP memory tools, or cross-session context.
  3. Assumptions are labeled, not hidden. If you lack evidence for a claim and cannot research it, explicitly label it as an assumption.

Process

Human-in-the-loop: Never proceed past a decision point without user approval. Each implementation phase requires explicit sign-off before moving to the next.

Resume Check

If --resume is set or .continue-here.md exists in the project root:

  1. Read .continue-here.md
  2. Present what was completed, what remains, and any anti-patterns encountered
  3. Ask: "Resume from where we left off?"
  4. If yes: skip to the recorded next action
  5. If no: start fresh (rename .continue-here.md to .continue-here-<timestamp>.md)

Phase 1: Absorb the Design Document

  1. Read the document at the path provided via $ARGUMENTS. If no path is provided, ask which HLD or LLD to implement.
  2. Detect document type (HLD vs LLD) from content and structure:
    • LLD indicators: method signatures, sequence diagrams, file-level implementation plan, error catalogs
    • HLD indicators: component diagrams, trade-off analysis, high-level architecture
  3. If HLD: check if a corresponding LLD exists (look for lld- variant of the filename, or references in the HLD). If found, suggest reading both. If not, note that implementation will proceed at a higher level of abstraction.
  4. Extract key elements:
    • Goals — what the implementation achieves
    • Components — modules, services, files involved
    • Implementation phases — if the doc defines them
    • File-level plan — specific files to create/modify (LLD)
    • Dependencies — libraries, services, infrastructure
    • Assumptions — stated assumptions that need validation
    • Open questions — unresolved items from the design process
    • D-XX decisions — if the context file has numbered decisions, extract them for coverage tracking

Read the full file on GitHub · 281 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. 12d ago First seen · 281 lines · 51 tokens per session scan A 253af511f8e6

Subscribe to this mod's changes

implement is a skill published in the GitHub repository GoogilyBoogily/googilyboogily-claude-power-tools (2 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 3,104 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens