huetension: Instructions file for Claude Code

CLAUDE.md

huetension CLAUDE.md is an instructions file for Claude Code from leporel/huetension. It costs 579 tokens per session, scanned A, original, MIT.

A project instruction guide for huetension, a color-palette toolkit written in Go with command-line, MCP, and web interfaces.

In plain words
What is it for?
It guides work on internal packages, public APIs, fixed JSON responses, repeatable color extraction, and dependency checks for the CLI.
Why use it?
It keeps the different interfaces consistent by defining the code layout, JSON format, reproducibility rules, and command-line conventions.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

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

Reuse

Borrowing it

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

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 huetension CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/leporel/huetension/claude-md"><img src="https://agentmods.dev/badge/instructions/leporel/huetension/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 579 This file is loaded in full into every session.
When invoked 579 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 $0.00579 $0.00579
Opus 5.5 $0.00232 $0.00232
Sonnet 5.5 $0.00116 $0.00116
Haiku 4.5 $0.00058 $0.00058

Measured 1mo ago against content hash 3b98e5a9ec12, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

huetension 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 1mo 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 · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

huetension

Color palette toolkit — a pure-Go core with three thin frontends: CLI, MCP, Web.

Layout

  • All logic lives in internal/* packages (color, palette, extract, harmony, gradient, contrast, blindness, exporter, imageio, cliutil); the CLI / MCP / web frontends stay thin.
  • ./huetension.go is the public facade — re-exports the canonical types (import "github.com/leporel/huetension"); internal packages stay private.
  • The CLI touches MCP / web / serve only through their Config + Run / Handler seams in cmd/huetension/cli/{mcp,web,serve}.go; it never builds on their internal types.

Wire contract

All JSON output uses the fixed huetension/v1 envelope: {schema, tool?, params?, result: {palette, metadata}}. Emit it through the library helpers (exporter.Export(p, FormatJSON, opts)) — never invent per-command shapes. Bumping schema is a coordination event across all three frontends.

Determinism

Extract methods must be reproducible across runs and processes:

  • Sort any map-derived output by a stable key — Go map order is random.
  • Seed the PRNG from the input pixels; never use math/rand directly in an extract path.

CLI conventions

  • Default --format: text (ANSI swatches) for palette commands, json for machine-oriented ones.
  • -o FILE — when --format is unset, the file extension picks the format.
  • convert / sort / css / tailwind / blindness read colors from stdin (one per line) when given no positional args.
  • Exit codes: 0 ok, 1 total failure, 2 partial failure.
  • Globals: --no-color (honours NO_COLOR), --quiet/-q, --data-dir DIR (config + palette library; honours HUETENSION_DATA_DIR).

Tests & dependencies

  • go test ./... -short — skips the slow TestExtractWritesPaletteSidecar (regenerates extract testdata previews). Fixtures: img1.png (PNG, not JPG), img2.jpg, img3.jpg.
  • Terminal styling: charm.land/lipgloss/v2. Image decoders: stdlib + golang.org/x/image, blank-imported in internal/imageio/imageio.go.

Read the full file on GitHub · 50 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. 1mo ago Changed · +1 lines · +27 tokens per session 3b98e5a9ec12
  2. 2mo ago First seen · 49 lines · 552 tokens per session scan A 8a9e0eedc669

Subscribe to this mod's changes

huetension CLAUDE.md is an instructions file published in the GitHub repository leporel/huetension (0 stars, last pushed 1mo ago), licensed MIT. It adds 579 tokens to every session, about $0.0023 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 2026-08-31.

Related

huetension CLAUDE.md compared with instructions from other repositories

huetension CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
huetension CLAUDE.mdleporel/huetensionInstructions file01mo agoMITA579Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode