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.
curl -O https://raw.githubusercontent.com/leporel/huetension/master/CLAUDE.mdgit clone --depth 1 https://github.com/leporel/huetensionWrote 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/leporel/huetension/claude-md)<a href="https://agentmods.dev/instructions/leporel/huetension/claude-md"><img src="https://agentmods.dev/badge/instructions/leporel/huetension/claude-md.svg" alt="Measured on agentmods" 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 | $0.00552 | $0.00552 |
| Opus 5 | $0.00276 | $0.00276 |
| Sonnet 5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
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 7d 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.
What it actually says
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.gois the public facade — re-exports the canonical types (import "github.com/leporel/huetension"); internal packages stay private.- The CLI must not import MCP or web types —
go list -deps ./cmd/huetensionshows neither.
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/randdirectly in an extract path.
CLI conventions
- Default
--format:text(ANSI swatches) for palette commands,jsonfor machine-oriented ones. -o FILE— when--formatis unset, the file extension picks the format.convert/sort/css/tailwind/blindnessread colors from stdin (one per line) when given no positional args.- Exit codes:
0ok,1total failure,2partial failure. - Globals:
--no-color(honoursNO_COLOR),--quiet/-q,--data-dir DIR(config + palette library; honoursHUETENSION_DATA_DIR).
Tests & dependencies
go test ./... -short— skips the slowTestExtractWritesPaletteSidecar(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 ininternal/imageio/imageio.go.
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.
- 7d ago First seen · 49 lines · 552 tokens per session scan A 8a9e0eedc669
huetension CLAUDE.md is an instructions file published in the GitHub repository leporel/huetension (0 stars, last pushed 3mo ago), licensed MIT. It adds 552 tokens to every session, about $0.0028 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
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).
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.
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).
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.