Borrowing it
Nothing to install: this file belongs to ArturSkowronski/minipainter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ArturSkowronski/minipainter/master/CLAUDE.mdgit clone --depth 1 https://github.com/ArturSkowronski/minipainterWrote 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.
[](https://agentmods.dev/instructions/arturskowronski/minipainter/claude-md)<a href="https://agentmods.dev/instructions/arturskowronski/minipainter/claude-md"><img src="https://agentmods.dev/badge/instructions/arturskowronski/minipainter/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.
<a href="https://agentmods.dev/instructions/arturskowronski/minipainter/claude-md"><img src="https://agentmods.dev/badge/instructions/arturskowronski/minipainter/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.02301 | $0.02301 |
| Opus 5 | $0.01151 | $0.01151 |
| Sonnet 5 | $0.00460 | $0.00460 |
| Haiku 4.5 | $0.00230 | $0.00230 |
Grade A, and why
minipainter 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
minipainter — project guide for Claude
A CLI + MCP server for managing a miniature-paint inventory and doing cross-brand
paint matching. Node.js ESM, tested with the built-in runner (npm test → node --test).
Paint catalog architecture
Paint data lives in two layers — never conflate them:
data/catalog/*.json— one file per brand (citadel,army_painter,vallejo,ak_interactive). These are an upstream mirror and must not be hand-edited; they are refreshable/regenerable. Each paint:{ id, provider, name, normalized_name, aliases, usage_roles, color_families, rgb, owned }.data/overrides/product_formats.json— an overlay that maps(provider, usage_role)→ normalizedproduct_format(opaque_base | opaque_layer | wash | contrast | technical | drybrush | metallic | ink). Brand rules are matched in order (first wins); per-idoverrideswin over rules.src/overrides.mjs::enrichPaintattachesproduct_formatat load time.
Rules
- To correct a mistagged paint, add a per-id entry in
data/overrides/, never edit the catalog. - For cross-brand reasoning read
paint.product_format— do not infer product type fromusage_rolesor RGB. Predicates live insrc/paint-format.mjs. color_familiesis an approximate RGB/HSL classification for search/browse only; it never influencesproduct_format.- After any catalog refresh, run
catalog lint(the CLI command) — it fails if any paint has a nullproduct_format, i.e. an unresolved overlay rule.
Upstream source ("Workbench")
The upstream is the GitHub repo alexparlett/hobby-desk-data
— scraper-driven, organized per-brand/per-range (e.g. ak-interactive/ak_3gen.json,
games-workshop/citadel.json). Its records look like
{ brand, name, sku, type, hex, range, category, discontinued }; our catalog schema is produced
by a transform on top of that.
Adding / refreshing a brand catalog
- Import from the matching
hobby-desk-datafolder via a transform script (seescripts/ak-transform.mjsfor the pure transform andscripts/import-ak.mjsfor the I/O wrapper —node scripts/import-ak.mjs <source-dir> [out-file]). Pin the source commit. - Write deterministic ids (
<provider>/<slug>, disambiguating name collisions with-<sku>). - Add overlay rules in
data/overrides/product_formats.jsonso every new paint resolves aproduct_format; verify withcatalog lint.
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.
- 12d ago First seen · 127 lines · 2,301 tokens per session scan A d67f8945614e
minipainter CLAUDE.md is an instructions file published in the GitHub repository ArturSkowronski/minipainter (0 stars, last pushed 21d ago), licensed MIT. It adds 2,301 tokens to every session, about $0.0115 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.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.
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).
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.
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).