An internal generator that creates Claude Code configuration files from a codebase analysis and developer preferences. It is used by an onboarding workflow rather than directly by a developer.

Use it during the onboarding commands that generate Claude tooling artifacts. It writes the generated files to the project's chosen directory.

It turns project analysis and setup choices into a complete set of Claude tooling files. This avoids manually creating configuration for each codebase.

generation — Skill for Claude Code and Codex by ApurvBazari: An internal generator that creates Claude Code configuration files…

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/apurvbazari/claude-plugins/generation

Any agent

npx skills add ApurvBazari/claude-plugins --skill generation

Clone the repo

git clone --depth 1 https://github.com/ApurvBazari/claude-plugins

Made for: Claude Code, Codex.

Or install onboard, the plugin that ships this one along with the rest of its 8 skills, 5 agents.

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/apurvbazari/claude-plugins/generation.svg)](https://agentmods.dev/skills/apurvbazari/claude-plugins/generation)

Your own site

<a href="https://agentmods.dev/skills/apurvbazari/claude-plugins/generation"><img src="https://agentmods.dev/badge/skills/apurvbazari/claude-plugins/generation.svg" alt="Measured on agentmods" height="20"></a>

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 8,079 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	$0.00037	$0.08079
Opus 5	$0.00018	$0.04040
Sonnet 5	$0.00007	$0.01616
Haiku 4.5	$0.00004	$0.00808

Measured 3d ago against content hash 386959de0355, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

generation 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 3d 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.

onboard/skills/generation/SKILL.md · 404 lines

How it starts

The opening of the file, as written. The whole thing — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generation Skill — Claude Tooling Artifact Generator

You are an expert at generating Claude Code configuration artifacts. You take a codebase analysis report and wizard answers as input, and produce a complete, tailored set of Claude tooling files.

Purpose

Generate all Claude Code artifacts for a project based on analysis data and developer preferences. Every artifact must be useful, accurate, and maintainable.

Inputs

You receive:

Codebase Analysis Report — From the codebase-analyzer agent, or from pre-seeded context in programmatic mode
Wizard Answers — Structured JSON from the wizard phase, or from pre-seeded context in programmatic mode
Project Root Path — Where to write artifacts

Programmatic Mode Guard

When programmatic is true in the input context, this skill is being invoked via /onboard:generate from an external caller. In programmatic mode:

Skip all interactive steps — Do not ask the developer any questions, present confirmation prompts, or wait for user input. All decisions have already been made by the caller.
Accept pre-seeded inputs as authoritative — The analysis report and wizard answers provided by the caller are treated identically to data gathered by onboard's own analyzer and wizard. Do not second-guess or re-validate the content beyond basic structural checks.
Merge hooks carefully — The caller may have already written hooks to .claude/settings.json. Read the file first and merge onboard's hooks alongside existing entries. This is the most common source of conflicts in programmatic mode.
Record provenance — Include programmatic: true and the caller's source identifier in onboard-meta.json.
All generation rules still apply — Artifact order, quality checks, maintenance headers, autonomy cascade, reference guides — everything in this skill applies equally in programmatic mode. The only difference is the source of inputs and the absence of interactive prompts.

Maintenance Header

Read the full file on GitHub · 404 lines

Files

What ships with it

35 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.

3d ago First seen · 404 lines · 37 tokens per session scan A 386959de0355

Subscribe to this mod's changes

generation is a skill published in the GitHub repository ApurvBazari/claude-plugins (0 stars, last pushed 27d ago), licensed MIT. It adds 37 tokens to every session and 8,079 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.

Building agents agentic-workflows ai-driven-development claude-code developer-tools macos notifications

cross-platform

Cross-platform development patterns for macOS, Windows, and Linux.

mylee04/code-notify · 15 tokens

shell-scripting

Shell scripting best practices for cross-platform CLI tools.

mylee04/code-notify · 13 tokens

c-notify

Send native macOS notification center alerts from the command line using terminal-notifier.

daxaur/openpaw · 20 tokens

frame-macos-notification

拟真 macOS 通知 banner + app icon + 标题正文, 适合 video overlay / 产品发布预告.

nexu-io/html-anything · 31 tokens

create-modal

Create declarative modals using the modal library API. Covers modal types (confirm, input, select, form), sections (Text, Buttons, Input, Textarea, Checkbox, List, Combo, When, Custom), rendering with OverlayModal, and keyboard/mouse handling. Use when adding modals or dialogs to the application.

marcus/sidecar · 69 tokens

merge-strategy

Git merge strategies, conflict resolution approaches, merge vs rebase recommendations, and branch integration patterns in sidecar. Covers pull strategy menu, direct merge workflow, squash merge, commit message templates, configurable defaults, and protected branches. Use when working on git merge features or making…

marcus/sidecar · 63 tokens