create-target

create-target is a skill for Claude Code, Codex from fabis94/universal-ai-config. It costs 23 tokens per session (3,307 once invoked), scanned A, original, MIT.

A guide for adding support for another AI coding assistant to universal-ai-config. It maps shared templates—such as rules, skills, agents, and hooks—to that assistant's own configuration files and syntax.

In plain words
What is it for?
Use it when adding a target such as Zed or Windsurf, researching its configuration rules, and preparing an implementation for approval.
Why use it?
Different coding assistants store settings in different places and formats, so support requires checking their current documentation first. The process also verifies how each assistant represents tools and permissions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions Claude Code; mentions AGENTS.md.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { defineTarget } from "../define-target.js";.

Good fit Use it when adding a target such as Zed or Windsurf, researching its configuration rules, and preparing an implementation for approval.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/fabis94/universal-ai-config
agentmods
npx agentmods add skills/fabis94/universal-ai-config/create-target

Made for: Claude Code, Codex.

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 create-target

README.md
[![agentmods](https://agentmods.dev/badge/skills/fabis94/universal-ai-config/create-target/github.svg)](https://agentmods.dev/skills/fabis94/universal-ai-config/create-target)
Your own site
<a href="https://agentmods.dev/skills/fabis94/universal-ai-config/create-target"><img src="https://agentmods.dev/badge/skills/fabis94/universal-ai-config/create-target/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 create-target

Your own site · 80×15
<a href="https://agentmods.dev/skills/fabis94/universal-ai-config/create-target"><img src="https://agentmods.dev/badge/skills/fabis94/universal-ai-config/create-target.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,307 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00023 $0.03307
Opus 5.5 $0.00009 $0.01323
Sonnet 5.5 $0.00005 $0.00661
Haiku 4.5 $0.00002 $0.00331

Measured yesterday against content hash b20597d7f762, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

create-target 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.

.universal-ai-config/skills/create-target/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a new target implementation for universal-ai-config. A target maps universal template frontmatter and hooks to a specific AI coding assistant's configuration format.

Phase 1 — Research & Approval

  1. Research the target's config format — find up-to-date documentation online for how the target AI assistant expects its configuration files. Look for:

    • File locations and naming conventions (e.g., .cursor/rules/*.mdc, .github/instructions/*.md)

    • Frontmatter format for each file type

    • Hook configuration format (JSON structure, event names)

    • MCP tool reference syntax — how the target references MCP tools in hook matchers, agent tools: frontmatter, and any allow/deny lists. Find the exact string format (e.g. mcp__server__tool, server/tool, MCP:tool) and the wildcard convention for "all tools on a server"

    • What it reads from other tools — whether it also loads AGENTS.md (root, nested, when) and project skills from .agents/skills/ (the Agent Skills standard's folder), other tools' folders (.claude/skills, .claude/agents, .claude/settings.json hooks, root .mcp.json), and what it does when it finds its own copy too: loads both, dedupes identical entries, or prefers its own. Docs are often vague here — follow Part 6 of the upstream validation reference to check by running the tool.

    Look through docs for all supported configuration types:

    • Instructions/rules/"system prompt"
    • Skills/Commands
    • Agents
    • Hooks
    • MCP servers
  2. Present findings for approval — before writing any code, present a structured summary of your research to the user. For each supported configuration type, include:

    • What it maps to: the universal template type it corresponds to (instructions, skills, agents, hooks)
    • File location & naming: where the target expects these files and what extensions/naming conventions it uses
    • Frontmatter/metadata format: the exact fields, keys, and structure the target uses (with examples from docs)
    • Hook format (if applicable): event names, JSON structure, how handlers are defined, which handler types it runs
    • Cross-tool reads: the other outputs it loads and how it reconciles duplicates (see above)
    • Source links: direct URLs to the official documentation pages you referenced

    Format as a clear table or grouped list so the user can review each mapping. Ask the user to approve or flag any corrections before proceeding. Do not continue until the user explicitly approves.

Read the full file on GitHub · 141 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 Changed · +28 lines b20597d7f762
  2. 2d ago Changed d201c07b388b
  3. 2mo ago First seen · 113 lines · 23 tokens per session scan A 0d0ed3b30917

Subscribe to this mod's changes

create-target is a skill published in the GitHub repository fabis94/universal-ai-config (14 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 3,307 once invoked, about $0.0001 per session on Opus 5.5. 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.

Related

create-target compared with skills from other repositories

create-target next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
create-targetfabis94/universal-ai-configSkill142d agoMITA23Claude Code, Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex