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.
git clone --depth 1 https://github.com/fabis94/universal-ai-confignpx agentmods add skills/fabis94/universal-ai-config/create-targetWrote 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.
[](https://agentmods.dev/skills/fabis94/universal-ai-config/create-target)<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="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00023 | $0.02116 |
| Opus 5 | $0.00012 | $0.01058 |
| Sonnet 5 | $0.00005 | $0.00423 |
| Haiku 4.5 | $0.00002 | $0.00212 |
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 8d 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.
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.
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
-
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"
Look through docs for all supported configuration types:
- Instructions/rules/"system prompt"
- Skills/Commands
- Agents
- Hooks
- File locations and naming conventions (e.g.,
-
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
- 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.
Phase 2 — Plan
After the user approves the research findings, enter plan mode to design the full implementation before writing any code. The plan should cover:
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.
- 8d ago First seen · 113 lines · 23 tokens per session scan A 0d0ed3b30917
create-target is a skill published in the GitHub repository fabis94/universal-ai-config (11 stars, last pushed 12d ago), licensed MIT. It adds 23 tokens to every session and 2,116 once invoked, about $0.0001 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…