tell-proof: Instructions file for Claude Code

CLAUDE.md

tell-proof CLAUDE.md is an instructions file for Claude Code from ashishpatill/tell-proof. It costs 791 tokens per session, scanned A, original, MIT.

A CLAUDE.md instruction file for Tell, an AI tool that captures interfaces, detects visual problems, proposes a design direction, and prepares changes for human approval. It describes the project's role, user, technology, and architecture.

In plain words
What is it for?
Use it when Claude Code is helping build Tell's web app, interface analysis pipeline, voice direction, or agent connection.
Why use it?
It gives Claude Code the background and constraints needed to work on the project without treating it as a generic software codebase.

Instructions file for Claude Code

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

This is ashishpatill/tell-proof's own configuration. It tells Claude Code how to work on tell-proof 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 tell-proof configures →

Reuse

Borrowing it

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

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 tell-proof CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ashishpatill/tell-proof/claude-md.svg)](https://agentmods.dev/instructions/ashishpatill/tell-proof/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ashishpatill/tell-proof/claude-md"><img src="https://agentmods.dev/badge/instructions/ashishpatill/tell-proof/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 791 This file is loaded in full into every session.
When invoked 791 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 $0.00791 $0.00791
Opus 5 $0.00396 $0.00396
Sonnet 5 $0.00158 $0.00158
Haiku 4.5 $0.00079 $0.00079

Measured 4d ago against content hash d5ed45f14a4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

tell-proof 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 4d 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 · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Claude Code / Claude Project

Mirror of AGENTS.md tuned for Claude. Upload docs/* + this file to a Claude Project.

Role

Build partner for Tell (Cursor build sprint). Help ship a winning 2-day build that viewers experience as Ashish's problem solved — not a tech demo.

User you serve

Ashish — shipped with Cursor, UI looks like every AI product, investor demo tomorrow, no designer. He needs: name the tells → see a direction → art-direct in plain English → patch in Cursor.

Read USER_STORY.md before planning.

Stack

TypeScript · pnpm workspaces · Playwright capture · Next.js 14 · Tailwind · Gemini (taste + voice refinement) · Cursor SDK (agentic draft enhancement) · deterministic reconciliation · MCP stdio · zod · vitest

Architecture

capture → fingerprint → detect (tells + drift) → taste → art-direct → contrast-grounded reconcile → diff

Shared by web app and MCP. Deterministic through detection; LLM only for judgment and diffs.

Web-only conveniences (local dev):

  • /api/setup/* — clone a GitHub repo, install, verify a reachable dev server, capture localhost (trusted repos only)
  • /api/voice — parse compound text/voice direction into action items with deterministic fallback
  • /api/redesign — use Cursor SDK for richer JSON-only patch drafts when CURSOR_API_KEY is present; deterministic fallback otherwise
  • packages/redesign/reconcile.ts — token-grounded before/after from captured CSS variables with contrast-floor reporting (no LLM)
  • Live seam — replays captured snapshotHtml with reconciled CSS custom properties

Rules

  • Do NOT build static token-diffing or codebase mind-maps
  • Do NOT auto-apply fixes
  • Do NOT use Inter / violet gradients / shadow-everywhere in Tell's own UI
  • DO enforce full state matrix on interactive components (empty, loading, error, focus-visible)
  • DO keep reconciliation measurable: contrast, focus, radius, depth, and token consistency must be visible in the report
  • DO prefer committed fixtures/reports/tell-report.json for demo reliability

Read the full file on GitHub · 74 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. 4d ago First seen · 74 lines · 791 tokens per session scan A d5ed45f14a4e

Subscribe to this mod's changes

tell-proof CLAUDE.md is an instructions file published in the GitHub repository ashishpatill/tell-proof (1 stars, last pushed 12d ago), licensed MIT. It adds 791 tokens to every session, about $0.0040 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 2026-09-03.

Related

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.

openai/codex · 5,182 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

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

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

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

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