A setup workflow for adding shared AI-development instructions to a repository and projecting them to Claude Code and GitHub Copilot. It can work with a new repository or migrate an existing setup.

Use it to fully enable a repository for Claude Code and Copilot, migrate existing AI configuration, or create shared skills, agents, rules, and editor settings.

It gives both coding assistants a common project structure and shared guidance, reducing duplicated or conflicting configuration.

setup — Skill by asteasolutions

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/asteasolutions/ai-toolkit/setup

Any agent

npx skills add asteasolutions/ai-toolkit --skill setup

Clone the repo

git clone --depth 1 https://github.com/asteasolutions/ai-toolkit

Made for: Claude Code, Codex.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,083 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.

Model	Per session	Once invoked
Fable 5	$0.00049	$0.02083
Opus 5	$0.00024	$0.01042
Sonnet 5	$0.00010	$0.00417
Haiku 4.5	$0.00005	$0.00208

Measured 2d ago against content hash 685b0c32b0d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup 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 2d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/harness-projection.mjs, scripts/sync-setup-bundle.sh, scripts/verify-install.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.

.claude/skills/setup/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Setup — project or fully AI-enable a repo

Project an existing Claude Code setup to GitHub Copilot, or lay the full minimal set of artifacts that make a repo behave effectively under both harnesses. Full setup ships with the developer-led method as its baseline; the /helm loop is its centre of gravity, not its boundary.

The installed layout is the harness-agnostic blueprint: AGENTS.md is the single source of shared instructions, .claude/ directories are the sources of truth for skills/agents/rules, and committed VS Code settings bridge Copilot to both. This flow targets Claude Code and GitHub Copilot only. Full design lives in references/blueprint.md — inside this skill, no external docs required.

This is prompt-driven, not a script. Present the path choice first. Then explore, preview, confirm, and write only what that path permits.

Scope. Handles both greenfield (clean repo) and brownfield (existing AI config). Brownfield is a migration: a gated conversion of what's there into the canonical layout, one declinable move at a time — see references/migration.md.

Agent / rule projection. Both paths follow PROJECTION.md first — the bundled CLI generates owned .github/ mirrors. Do not hand-sync.

The canonical layout

repo/
├── AGENTS.md                     # single source of shared instructions, all harnesses
├── CLAUDE.md                     # real file: "@AGENTS.md" import + Claude-only extras (not a symlink)
├── .vscode/settings.json         # committed chat.* settings that wire Copilot (pinned by harness-projection sync)
├── .claude/
│   ├── skills/                   # skills home — Claude reads it natively, Copilot via chat.agentSkillsLocations
│   ├── agents/                   # source of truth for agent definitions (created by migration only)
│   └── rules/                    # source of truth for path-scoped rules (created by migration only)
├── .github/
│   ├── agents/                   # derived from .claude/agents/ via harness-projection (do not edit)
│   └── instructions/             # derived from .claude/rules/ via harness-projection (do not edit)
└── .gitignore                    # .scratch/ ignored

Read the full file on GitHub · 136 lines

Files

What ships with it

41 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.

2d ago First seen · 136 lines · 49 tokens per session scan A 685b0c32b0d6

Subscribe to this mod's changes

setup is a skill published in the GitHub repository asteasolutions/ai-toolkit (5 stars, last pushed 5d ago), licensed MIT. It adds 49 tokens to every session and 2,083 once invoked, about $0.0002 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.

Productivity

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