implement

A workflow for turning an approved software architecture document into a project skeleton and initial code files.

In plain words
What is it for?
Use it to propose a folder structure, then create data models, API placeholders, configuration files, and infrastructure files after confirmation.
Why use it?
It provides a structured starting point after design work and checks that the architecture session is complete before implementation begins.

Skill for Claude CodeCodex

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 skills/sembraniteam/claude-plugins/implement
Any agent
npx skills add sembraniteam/claude-plugins --skill implement
Clone the repo
git clone --depth 1 https://github.com/sembraniteam/claude-plugins

Made for: Claude Code, Codex.

Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,499 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 $0.00099 $0.03499
Opus 5 $0.00049 $0.01750
Sonnet 5 $0.00020 $0.00700
Haiku 4.5 $0.00010 $0.00350

Measured yesterday against content hash 62c1f1668af4, 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 yesterday.

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.

architecture-designer/skills/implement/SKILL.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Designer — Implementation Workflow

This skill turns an approved architecture document into a working project skeleton: data models, API stubs, configuration files, and infrastructure files. It always proposes a folder structure first and waits for the user's confirmation before writing any files.

Scripts and shared-reference paths: this file has no references/ of its own and points into the sibling design skill's references/ directory throughout (first used just below, in "Before starting"). See "Path resolution" at the bottom of this file for how both <scripts_dir> and design/references/... paths resolve.


Before starting — session completeness gate

Check for docs/architecture-designer/session.json:

  • If the file exists: read it in full, then run python3 <scripts_dir>/validate-session.py and show its output — this is a hard gate; do not proceed to Step 1 until it reports SESSION CHECK PASSED. See design/references/session-schema.md section "Session completeness gate" for what the script checks, how to resolve a failure, and why this gate applies to implement even though its steps mostly work from the confirmed architecture document rather than the session stages directly. Reading it in full here (rather than only running the validator) is what makes its stage5 object available as a cross-check for Step 3's "Technology stack" input — the architecture document itself is that input's primary source, not stage5 (see Step 3 for why).
  • If the file does not exist: this gate only applies when session.json exists — proceed without it. The architecture document confirmed in Step 1 is the authoritative source of truth for implementation in that case.

Step 1 — Find the architecture document

Check for an architecture document path in this order:

  1. docs/architecture-designer/session.json — if it exists and contains a documents array, use its last entry (the most recently saved document) — the authoritative location when this skill follows a design session in the same working directory. If that path doesn't resolve to an existing file (moved or deleted since), fall back to option 2, not directly to option 3 — a stale recorded path doesn't mean no path is available; the current conversation may still hold the correct one.
  2. Current conversation context — if the user just completed a /architecture-designer:design or /architecture-designer:review session and the document path is visible in the conversation.
  3. Manual selection — if neither above yields a path, proceed to list files as described below.

Read the full file on GitHub · 218 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. yesterday First seen · 218 lines · 99 tokens per session scan A 62c1f1668af4

Subscribe to this mod's changes

implement is a skill published in the GitHub repository sembraniteam/claude-plugins (2 stars, last pushed 28d ago), licensed MIT. It adds 99 tokens to every session and 3,499 once invoked, about $0.0005 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.

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

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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens