What is aiws-configure-workspace?

A guided workspace setup helper that examines an existing code repository, or asks about a new one, and proposes a workspace.config.yaml file and set of skills. The configuration describes the project's technology, targets, and working rules.

Use it when starting or reconfiguring an AI coding workspace, detecting its languages and frameworks, validating available modules, and preparing a reviewed configuration.

It helps avoid guessing which tools and settings a coding workspace needs, while keeping the user in control before files are changed.

How grojof/ai-workspace-generator configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to grojof/ai-workspace-generator. 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/grojof/ai-workspace-generator/main/.claude/skills/aiws-configure-workspace/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/grojof/ai-workspace-generator

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/grojof/ai-workspace-generator/aiws-configure-workspace/github.svg)](https://agentmods.dev/skills/grojof/ai-workspace-generator/aiws-configure-workspace)

Your own site

<a href="https://agentmods.dev/skills/grojof/ai-workspace-generator/aiws-configure-workspace"><img src="https://agentmods.dev/badge/skills/grojof/ai-workspace-generator/aiws-configure-workspace/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/grojof/ai-workspace-generator/aiws-configure-workspace"><img src="https://agentmods.dev/badge/skills/grojof/ai-workspace-generator/aiws-configure-workspace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,065 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.

Model	Per session	Once invoked
Fable 5.1	$0.00057	$0.01065
Opus 5	$0.00028	$0.00532
Sonnet 5	$0.00011	$0.00213
Haiku 4.5	$0.00006	$0.00106

Measured 11d ago against content hash 47ebbd605848, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

aiws-configure-workspace 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 11d 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.

.claude/skills/aiws-configure-workspace/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Configure this AI workspace (guided)

Help the user produce a correct, explained workspace.config.yaml and skill set — for an existing repo (analyze → propose) or a new one (describe → ask). Propose-and-review: never write or move files without explicit approval.

1. Analyze

Run ai-workspace detect --json for a deterministic stack seed (languages/frameworks/environments).
Read the repo to enrich it: manifests, folder layout, existing docs/configs. Note anything the detector missed. If nothing is detected and it's a new project, ask targeted questions instead of guessing.

2. Propose

Draft a candidate workspace.config.yaml (project, profile, stack, sdd, language, targets…). Validate every module id against the registry (ai-workspace list); for a gap, propose either adding a module or discovering a pack with the find-skills skill — and say why.
Profile is the user's choice — never infer it. profile.userType (technical | business) and profile.experience (beginner | standard | advanced) set the governance posture. Detection seeds the stack only; it does NOT tell you the user type. Ask both explicitly; do not assume "technical" because code was detected.

Option guide (what each means, and the why — explain before you ask)

targets — which AI tools to wire: claude (CLAUDE.md + skills + .mcp.json), copilot (.github/*, also Visual Studio), codex (AGENTS.md as instructions + .codex/config.toml). Why: only generate for tools the user actually uses.
profile.userType — technical (code/devops/data/infra) vs business (process/docs/analysis). Why: tunes how much architecture/testing/security depth the AI applies.
profile.experience — beginner (clear guidance, safe paths) · standard (balance) · advanced (trade-offs, more autonomy). Why: tunes verbosity and how many decisions are surfaced.
project.mode — new (use current stable versions) vs existing (conserve versions; upgrade only on assessment). Why: governs the versioning posture and the Safety gate.
project.purpose — build (normal) vs learn (tutor mode). Why: adds learner skills/explanations.
stack — languages / frameworks / environments (+ versions). Why: drives per-layer rules and VS Code recs.
sdd.enabled / backend / methodology — SDD on/off; artifacts in files (recommended), hybrid (+ memory), or none; sdd vs spdd. Why: where specs live and how much process for non-trivial changes.
workflow.hooks.safetyGuard — warn | block | off for risky-command hook (Claude). Why: hardens the Safety gate without changing the AGENTS.md rule.
vscode — generate .vscode/ recs; set false for Visual Studio / non-VS-Code. mcp (context7) — up-to-date library docs. company — org overlay (none for personal). language — human-facing docs language (AI files stay English).
Produce a conflict report: existing paths/docs that would collide with generated structure, plus an optional folder-alignment plan. Multi-repo: if the workspace spans several repos, propose a top-level repos: list (each with its path and optional stack); a single repo needs no repos.

Read the full file on GitHub · 61 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.

11d ago First seen · 61 lines · 57 tokens per session scan A 47ebbd605848

Subscribe to this mod's changes

aiws-configure-workspace is a skill published in the GitHub repository grojof/ai-workspace-generator (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,065 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.

Building agents

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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 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

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

ai-workspace-generator: Skill for Claude Code