decantr: Instructions file for Claude Code

CLAUDE.md

decantr CLAUDE.md is an instructions file for Claude Code from decantr-ai/decantr. It costs 8,678 tokens per session, scanned A, original, MIT.

Repository instructions for Decantr, a local-first tool that prepares and verifies bounded UI changes. UI means the screens and controls people use, and local-first means project information stays under the project's control.

In plain words
What is it for?
Use them to understand Decantr's packages, applications, terminology, and verification behavior. The excerpt also describes its current release line and compatibility modes.
Why use it?
They explain how Decantr scopes changed interface code and reports evidence without generating code or modifying files during verification.

Instructions file for Claude Code

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

This is decantr-ai/decantr's own configuration. It tells Claude Code how to work on decantr 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 decantr configures →

Reuse

Borrowing it

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

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 decantr CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/decantr-ai/decantr/claude-md.svg)](https://agentmods.dev/instructions/decantr-ai/decantr/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/decantr-ai/decantr/claude-md"><img src="https://agentmods.dev/badge/instructions/decantr-ai/decantr/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 8,678 This file is loaded in full into every session.
When invoked 8,678 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 $0.08678 $0.08678
Opus 5 $0.04339 $0.04339
Sonnet 5 $0.01736 $0.01736
Haiku 4.5 $0.00868 $0.00868

Measured 8d ago against content hash 32b325a43af9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

decantr 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 8d 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 · 374 lines

How it starts

The opening of the file, as written. The whole thing — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md -- Decantr

Do not add Co-Authored-By lines to commits.

Project

Decantr is local-first AI Frontend Governance and UI change control. It observes project-owned authority, prepares bounded context for a specific UI change, verifies the resulting diff, and reports typed evidence. Decantr does not generate code -- the AI or developer does.

Current stable product: Decantr 3.11.3 is the Changed-UI Assurance line. Bare decantr verify is zero-write and adoption-free: it scopes the current Git change, selects exactly one changed UI app when provable, and returns at most three source-anchored findings. The patch keeps SvelteKit +page.svelte files as taskable implementations and colocated page-data modules as supporting authority. The 3.10 independent authority axes, framework-specific production topology, route and non-route task preparation, bounded route capsules, and Project Health contracts remain the foundation. Explicit CI v3 includes the same change-assurance report while v2 stays the compatibility default. Product release readiness is separate from model-lift research qualification. No precision, recall, adoption-proof, or general model-improvement claim is allowed without its corresponding evidence.

Current research program: docs/programs/2026-07-22-decantr-3-10-ui-change-control-proof.md tests whether the shipped Observe -> Prepare -> Verify -> Report product materially improves model outcomes. Product 3.10 treats routes, layouts, components, stories, overlays, flows, packages, and runtime states as independent UI surfaces; route inventory is evidence, not the product ontology. A predeclared treatment lift must pass separately for each locked frontier model before any material-improvement claim. The frozen 3.9.4 Day-0 result and 3.10 regression replays are diagnostics, not control/treatment results. Paid model runs require explicit budget authorization. The current no-cost runtime matrix is independently reverified at digest ce55618610740db332d19c6314f78d0141f440bc5ca04ec79698b3359d6c93bc; evaluator qualification, runnable task materialization, paid trajectories, and independent human review remain incomplete. None of those research gaps block an honestly bounded product release.

Read the full file on GitHub · 374 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. 8d ago First seen · 374 lines · 8,678 tokens per session scan A 32b325a43af9

Subscribe to this mod's changes

decantr CLAUDE.md is an instructions file published in the GitHub repository decantr-ai/decantr (6 stars, last pushed 11d ago), licensed MIT. It adds 8,678 tokens to every session, about $0.0434 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.

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

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.

github/spec-kit · 7,104 tokens