Spawn: Instructions file for Claude Code

CLAUDE.md

Spawn CLAUDE.md is an instructions file for Claude Code from Abhiix0/Spawn. It costs 1,313 tokens per session, scanned A, original, MIT.

Repository instructions for Spawn, a Python command-line program that creates project templates, checks project health, and can publish projects to GitHub. The file records its commands, architecture, development setup, and contribution rules for Claude Code.

In plain words
What is it for?
It helps an agent install dependencies, run tests and lint checks, format code, understand the project structure, keep version information consistent, and add templates according to the repository’s guidance.
Why use it?
It gives a coding agent the project-specific conventions and commands needed to work safely in the repository instead of relying on generic assumptions.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is Abhiix0/Spawn's own configuration. It tells Claude Code how to work on Spawn itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Spawn configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Abhiix0/Spawn. 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/Abhiix0/Spawn/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Abhiix0/Spawn

Made for: Claude Code.

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 Spawn CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/abhiix0/spawn/claude-md/github.svg)](https://agentmods.dev/instructions/abhiix0/spawn/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/abhiix0/spawn/claude-md"><img src="https://agentmods.dev/badge/instructions/abhiix0/spawn/claude-md/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 Spawn CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/abhiix0/spawn/claude-md"><img src="https://agentmods.dev/badge/instructions/abhiix0/spawn/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,313 This file is loaded in full into every session.
When invoked 1,313 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01313 $0.01313
Opus 5.5 $0.00525 $0.00525
Sonnet 5.5 $0.00263 $0.00263
Haiku 4.5 $0.00131 $0.00131

Measured 3d ago against content hash 84b046a3c1fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Spawn CLAUDE.md 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.

CLAUDE.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Overview

Spawn (PyPI: spawnio, entry point spawn = spawn.cli.app:main) is a Typer/Rich CLI that scaffolds Python projects from intent-based templates (spawn create), scores project health (spawn doctor, spawn doctor --fix), inspects existing repositories read-only (spawn inspect), and optionally publishes to GitHub. Python 3.12+, managed with uv, built with hatchling. Version lives in pyproject.toml (spawn.__version__ reads it via importlib.metadata, with a hardcoded fallback in src/spawn/__init__.py that must be kept in sync).

Commands

uv sync --all-groups                 # install incl. dev group
uv run pytest                        # all tests
uv run pytest tests/test_app.py      # one file
uv run pytest tests/test_app.py::test_name   # one test
uv run pytest --cov=src/spawn --cov-report=term-missing
uv run ruff check .                  # lint (CI runs pytest + ruff check)
uv run ruff format .                 # format (required before PRs)
uv run spawn inspect . --json        # run the read-only inspector on this repo

Architecture

Detailed reference: docs/architecture.md, docs/commands.md, CONTRIBUTING.md. Big picture:

  • Create flow: cli/app.py → a core/models.ProjectConfig from either interactive cli/prompts.py (questionary, menus derived from the registry) or cli/noninteractive.py (flags / --config JSON, validated by core/planning.py::plan_project) → generators/pipeline.py::generate_project, which dispatches to ProjectGenerator (templates) or CustomStructureGenerator (template == "custom"). Both guard the destination via generators/destination.py (assert_available, safe_join), write folders/files/README/.gitignore, run git init and (unless --no-uv) uv init/uv venv/uv add/template.post_install(), then generators/metadata.py::write_project_meta writes .spawn/meta.json. On failure only a directory created by this run is removed (cleanup_created); OSError becomes FilesystemError.
  • Template registry (core/registry.py): TEMPLATES dict of TemplateMetadata is the single source of truth for slugs, frameworks, extras, and prompt menus. instantiate_template(config) passes framework/extras/cli_type etc. to a template's constructor only if its signature accepts them (signature introspection), so constructor parameter names matter.
  • Templates (templates/<slug>/__init__.py + content.py): subclass BaseTemplate (templates/base.py); __init__.py holds the class (dispatching on framework), content.py holds all file contents as string constants plus make_readme() / make_agents_md(). templates/mcp_server/ is the minimal example to copy. Shared README/gitignore/CI/tool-config strings are in templates/shared_content.py; standalone file writers in generators/project_files.py.
  • Custom structure (generators/custom_structure.py): parses pasted Tree/Markdown/Indented layouts and builds them without a template.
  • Doctor: utils/doctor.py computes the 0–100 health score; utils/doctor_fix.py plans/applies fixes (plan_fixes, apply_fixes) — it never overwrites existing files or installs packages.
  • GitHub publishing: github/publisher.py (GitHubPublisher), errors derive from PublishError. All errors derive from SpawnError (core/exceptions.py), each class with its own exit_code; cli/errors.py::fail prints ❌ message and exits with it, report_unexpected exits 10 (traceback with SPAWN_DEBUG=1).
  • Inspection (spawn inspect [PATH] [--json] [-v], docs/inspection/): cli/app.py::inspect_command → inspection/orchestrator.py::run_inspection → discovery.validate_inspection_root / discover_repository (one scan) → analyzers LanguageDetector, FrameworkDetector, DependencyAnalyzer, ToolingAnalyzer (consume the inventory only) → aggregate by (category, subject) → InspectionReport → cli/inspect_render.py or to_json. Static and read-only: no code execution, installs, network or writes. InspectionError exits 7; inspection/ must not import spawn.cli (tests/test_boundaries.py). The report schema is SCHEMA_VERSION in inspection/models.py; behavior changes need docs/inspection/ updated.
  • Metadata: .spawn/meta.json is historical, not authoritative; read it with core/project.py::read_project_metadata. ProjectConfig is generation intent only.
  • Every generated project ships an AGENTS.md (plus CLAUDE.md with --claude-md).

Read the full file on GitHub · 43 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. 3d ago Changed · +6 lines · +308 tokens per session 84b046a3c1fa
  2. 20d ago First seen · 37 lines · 1,005 tokens per session scan A 7dbd924d4e6b

Subscribe to this mod's changes

Spawn CLAUDE.md is an instructions file published in the GitHub repository Abhiix0/Spawn (25 stars, last pushed 3d ago), licensed MIT. It adds 1,313 tokens to every session, about $0.0053 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 2026-10-10.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens