tell-proof-verify

tell-proof-verify is a cursor rule for Cursor from ashishpatill/tell-proof. It costs 0 tokens per session (538 once invoked), scanned A, original, MIT.

A project rule for checking that a user interface still looks and behaves correctly after visual code changes. It uses before-and-after reports and requires a person to approve the result.

In plain words
What is it for?
Use it after redesigning or editing a captured interface, to diagnose the preview, apply the patch, and verify the result locally or on a hosted preview.
Why use it?
It catches visual regressions before a frontend change is merged, including changes to components, styles, design tokens, or fixture pages.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions Cursor.

Good fit Use it after redesigning or editing a captured interface, to diagnose the…

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/ashishpatill/tell-proof/tell-proof-verify
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/ashishpatill/tell-proof

Made for: 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 tell-proof-verify

README.md
[![agentmods](https://agentmods.dev/badge/rules/ashishpatill/tell-proof/tell-proof-verify.svg)](https://agentmods.dev/rules/ashishpatill/tell-proof/tell-proof-verify)
Your own site
<a href="https://agentmods.dev/rules/ashishpatill/tell-proof/tell-proof-verify"><img src="https://agentmods.dev/badge/rules/ashishpatill/tell-proof/tell-proof-verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 538 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 $0.00000 $0.00538
Opus 5 $0.00000 $0.00269
Sonnet 5 $0.00000 $0.00108
Haiku 4.5 $0.00000 $0.00054

Measured 6d ago against content hash 808babf26b1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tell-proof-verify 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 6d 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/rules/tell-proof-verify.mdc · 54 lines

What it actually says

Tell Proof verify (agent workflow)

When you change rendered UI (components, styles, tokens, fixture pages), run proof verification before claiming done or opening a PR.

When to invoke

  • After drafting a redesign patch with tell_redesign / tell_apply
  • After editing apps/web or fixtures/generic-app styles that affect the captured surface
  • Before merge on any frontend PR that changes computed styles

MCP path (preferred in Cursor Agent)

1. tell_diagnose on the running preview URL (or localhost:3001 for fixture)
2. tell_redesign with direction
3. tell_apply with projectRoot set to the workspace
4. tell_proof_verify { url, patch, projectRoot }
5. If status is "failed" and reverted is true → revise patch and retry
6. If status is "passed" or "review" → human approves merge (never auto-merge)

Web / hosted path

  • Local disposable checkout: POST /api/proof/apply with jobId, patch, beforeReport
  • Hosted compare (Vercel preview): POST /api/proof/verify with { mode: "compare", url, beforeReport, afterReport }
  • Hosted patch (capture backend): POST /api/proof/verify with { url, patch, projectRoot } — proxied when TELL_CAPTURE_API_URL is set

Verdict meanings

Status Meaning
passed Score improved ≥3, screenshot changed, no focus/structure regression
review Neutral or small change — human should judge
failed Regression or patch did not apply — auto-reverted when configured

Rules

  • Never auto-merge on passed alone — human reviews the diff
  • Always capture the same URL as the baseline report
  • Prefer disposable checkout proof over editing the main branch directly
  • After UI fixes, also run pnpm dogfood:web (Tell must stay at zero tells)
  • Skill: .cursor/skills/tell-proof-verify/SKILL.md
  • Skill: .cursor/skills/tell-dogfood-audit/SKILL.md
  • Core: packages/core/src/proof-verify.ts
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. 6d ago First seen · 54 lines · 0 tokens per session scan A 808babf26b1c

Subscribe to this mod's changes

tell-proof-verify is a cursor rule published in the GitHub repository ashishpatill/tell-proof (1 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 538 tokens. 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.