tell-proof: Agent for Claude Code

.cursor/agents/dogfood-auditor.md

dogfood-auditor is an agent for Claude Code, Cursor from ashishpatill/tell-proof. It costs 53 tokens per session (307 once invoked), scanned A, original, MIT.

A self-audit specialist for checking a web app against its own design system. It inspects the app, lists visual inconsistencies with file locations, and fixes them using the system's design tokens.

In plain words
What is it for?
Use it before a demo to inspect apps/web for typography, colors, shadows, corner shapes, layout, state coverage, and raw color values. It reports blockers when a fix would require schema changes.
Why use it?
It catches generic-looking interface choices and accidental visual drift before a demo. Repeating the audit verifies that the listed issues are gone.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

This is ashishpatill/tell-proof's own configuration. It tells Claude Code and Cursor 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/.cursor/agents/dogfood-auditor.md
Clone the repo
git clone --depth 1 https://github.com/ashishpatill/tell-proof

Made for: Claude Code, Cursor.

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 dogfood-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/ashishpatill/tell-proof/dogfood-auditor/github.svg)](https://agentmods.dev/agents/ashishpatill/tell-proof/dogfood-auditor)
Your own site
<a href="https://agentmods.dev/agents/ashishpatill/tell-proof/dogfood-auditor"><img src="https://agentmods.dev/badge/agents/ashishpatill/tell-proof/dogfood-auditor/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 dogfood-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/ashishpatill/tell-proof/dogfood-auditor"><img src="https://agentmods.dev/badge/agents/ashishpatill/tell-proof/dogfood-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 307 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00053 $0.00307
Opus 5 $0.00026 $0.00153
Sonnet 5 $0.00011 $0.00061
Haiku 4.5 $0.00005 $0.00031

Measured 10d ago against content hash 91f871330f94, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

dogfood-auditor 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 10d 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.

.cursor/agents/dogfood-auditor.md · 30 lines

What it actually says

You are Tell's dogfood auditor. Tell must practice what it preaches.

Target

Zero generic tells, zero unintentional drift on apps/web.

Checklist (docs/01_DESIGN_SYSTEM.md §12)

  • Display + sans + mono typefaces present; no Inter-only
  • No violet gradient hero; no acid accent on near-black
  • e2 shadow max; not shadow on every element
  • ≥2 distinct radii in main view
  • Asymmetric layout; not centered-everything
  • ≤4 gray values in token ramp
  • Full state matrix on Button, CaptureBar, VoiceDirector, seam
  • No raw hex in committed component classNames

Process

  1. Run diagnose on localhost:3000 (or static analysis of apps/web)
  2. List findings with file:line
  3. Fix in apps/web using design tokens only
  4. Re-run until clean
  5. Document result for demo close: "Tell runs on itself: zero tells"

Report blockers to orchestrator if fixes require schema changes.

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. 10d ago First seen · 30 lines · 53 tokens per session scan A 91f871330f94

Subscribe to this mod's changes

dogfood-auditor is an agent published in the GitHub repository ashishpatill/tell-proof (1 stars, last pushed 15d ago), licensed MIT. It adds 53 tokens to every session and 307 once invoked, about $0.0003 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.