APEX: Skill for Claude Code

.agents/skills/apex-replatform/SKILL.md

apex-replatform is a skill for Claude Code from OthmanAdi/APEX. It costs 60 tokens per session (915 once invoked), scanned A, original, MIT.

A skill for rebuilding an existing feature in a different software architecture using a written specification. It maps the specification to the target framework, implements the feature, and checks the result against its requirements.

In plain words
What is it for?
Replatforming features, migrating applications, rebuilding functionality in a new framework, and implementing specifications with validation steps.
Why use it?
It gives developers a structured way to migrate or recreate behavior without relying on the original source code as the main reference.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_SKILL_DIR} variable. Also seen: installed under .agents/ (shared by several agents).

This is OthmanAdi/APEX's own configuration. It tells Claude Code how to work on APEX itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything APEX configures →

Reuse

Borrowing it

Nothing to install: this file belongs to OthmanAdi/APEX. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/OthmanAdi/APEX/main/.agents/skills/apex-replatform/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/OthmanAdi/APEX

Made for: Claude Code.

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 apex-replatform

README.md
[![agentmods](https://agentmods.dev/badge/skills/othmanadi/apex/apex-replatform.svg)](https://agentmods.dev/skills/othmanadi/apex/apex-replatform)
Your own site
<a href="https://agentmods.dev/skills/othmanadi/apex/apex-replatform"><img src="https://agentmods.dev/badge/skills/othmanadi/apex/apex-replatform.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 915 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 $0.00060 $0.00915
Opus 5 $0.00030 $0.00458
Sonnet 5 $0.00012 $0.00183
Haiku 4.5 $0.00006 $0.00092

Measured 7d ago against content hash 56026e6420ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

apex-replatform 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/validate.ps1, scripts/validate.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/apex-replatform/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

APEX Replatform

Take a feature specification (from apex-decompose or manually written) and implement it in a target architecture. This is the "mapping problem" — translating what exists into what should exist.

When to Use

Use this skill after you have a specification document describing the feature's behavior. You should NOT need access to the original source code. The spec is your single source of truth.

Workflow

Replatforming a feature involves these steps:

  1. Load and understand the specification
  2. Map the spec to the target architecture
  3. Implement the feature
  4. Wire up self-correcting feedback loops
  5. Validate against the spec's acceptance criteria

Step 1: Load the Specification

Read the spec file:

Read specs/{feature-name}.md

Identify all [VERIFY] tags. Ask the user to resolve any ambiguities before proceeding. Do not guess on verified items.

Step 2: Map to Target Architecture

Create a mapping document that translates spec concepts to target patterns:

Spec Concept Target Implementation
Database write to users table Prisma user.create() call
REST endpoint /api/v1/items Next.js API route app/api/items/route.ts
Event emission item.created EventEmitter / message queue publish

Ask the user to confirm the mapping before writing code. This is the architectural decision point.

Step 3: Implement the Feature

Write code following these rules:

  1. One file at a time. Complete each file before moving to the next.
  2. Match the spec exactly. Every input, output, and side effect in the spec must be implemented.
  3. Preserve edge cases. If the spec says "returns 400 when empty," implement that exact behavior.
  4. Add inline comments referencing the spec: // Spec: Edge Case #3 — concurrent request handling

Step 4: Self-Correcting Feedback Loop

After writing code, run the validation chain. Detect OS and use the appropriate script:

Linux/Mac:

bash "${CLAUDE_SKILL_DIR}/scripts/validate.sh" <target-dir>

Read the full file on GitHub · 113 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 113 lines · 60 tokens per session scan A 56026e6420ac

Subscribe to this mod's changes

apex-replatform is a skill published in the GitHub repository OthmanAdi/APEX (2 stars, last pushed 5mo ago), licensed MIT. It adds 60 tokens to every session and 915 once invoked, about $0.0003 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

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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 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