alphanana: Instructions file for Claude Code

CLAUDE.md

alphanana CLAUDE.md is an instructions file for Claude Code from tobiasstrebitzer/alphanana. It costs 875 tokens per session, scanned B, original, MIT.

Project instructions for Alphanana, a tool that creates transparent image assets by comparing rendered images with black and white versions. It is published as a JavaScript library, command-line tool, and Claude Code plugin.

In plain words
What is it for?
Use them when building, testing, linting, type-checking, or publishing Alphanana and when changing its rendering, image variants, batch processing, or configuration.
Why use it?
They explain the repository layout, available checks, and how the image-processing pipeline decides whether an output is trustworthy.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is tobiasstrebitzer/alphanana's own configuration. It tells Claude Code how to work on alphanana 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 alphanana configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tobiasstrebitzer/alphanana. 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/tobiasstrebitzer/alphanana/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/tobiasstrebitzer/alphanana

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 alphanana CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tobiasstrebitzer/alphanana/claude-md"><img src="https://agentmods.dev/badge/instructions/tobiasstrebitzer/alphanana/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 875 This file is loaded in full into every session.
When invoked 875 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.00875 $0.00875
Opus 5 $0.00438 $0.00438
Sonnet 5 $0.00175 $0.00175
Haiku 4.5 $0.00088 $0.00088

Measured 9d ago against content hash 8f762cce78a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

alphanana CLAUDE.md scanned grade B with 1 finding 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 9d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- co_authored_by: no (already disabled globally in ~/.claude/settings.json)
CLAUDE.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

alphanana

Single-package repo (pnpm, ESM-only, built with tsdown). Ships three ways from one source tree: an npm library, an alphanana CLI, and a Claude Code plugin.

See README.md for what the difference-matte pipeline does and why it exists.

Commands

pnpm build       # tsdown -> build/ (esm + .d.mts, no sourcemaps)
pnpm typecheck   # tsgo -p tsconfig.json
pnpm lint        # oxlint src test
pnpm test        # vitest run

There is no aggregate check script — run pnpm lint && pnpm typecheck together.

Layout

  • src/matte.ts — the alpha solve (a = 1 - (white - black), F = black / a) and the guard stats that decide whether a matte is trustworthy. The only unit-tested module.
  • src/gemini.ts — Gemini image model calls (render, then edit-to-black).
  • src/generate.ts — one asset: render pair, matte, guard, re-roll on drift.
  • src/variants.ts — N seeds of one subject, optional contact sheet.
  • src/batch.ts — manifest-driven runs; writes assets.report.json.
  • src/config.ts / src/env.tsalphanana.json schema (zod) and .env discovery.
  • src/cli.ts — arg parsing; progress to stderr, output paths to stdout.
  • skills/alphanana/SKILL.md + .claude-plugin/ — the Claude Code plugin. The skill drives the published CLI via npx -y alphanana, so it is distributed through the plugin marketplace (git), never through the npm tarball.
  • docs/ — README assets only, outside the files whitelist so none of it ships. make-casts.mjs regenerates both terminal demos; see README > Development for the svg-term-cli invocations and the two manual post-edits it needs. The casts are hand-authored on purpose — a real recording would cost a paid generate run per tweak.

.claude-plugin/plugin.json carries its own version and is kept in lockstep with package.json. npm version does not touch it — bump both, or the marketplace and the npm package disagree.

Publishing

Automated. .github/workflows/publish.yml publishes to npm on every push to master whose package.json version is not on the registry yet — so bumping the version is what ships, and an ordinary commit is a no-op.

Read the full file on GitHub · 66 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. 9d ago First seen · 66 lines · 875 tokens per session scan B 8f762cce78a8

Subscribe to this mod's changes

alphanana CLAUDE.md is an instructions file published in the GitHub repository tobiasstrebitzer/alphanana (4 stars, last pushed 1mo ago), licensed MIT. It adds 875 tokens to every session, about $0.0044 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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 · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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 · 6,785 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens