tell-proof: Skill for Cursor

.cursor/skills/gates-until-verified/SKILL.md

gates-until-verified is a skill for Cursor from ashishpatill/tell-proof. It costs 47 tokens per session (297 once invoked), scanned A, original, MIT.

A workflow for checking Tell UI work against observable acceptance gates before declaring it complete. Tell UI is a user-interface work environment, and acceptance gates are concrete checks that an output must pass.

In plain words
What is it for?
Use it to define the task contract, inspect screenshots, check contrast and keyboard focus, run tests and type checks, record results, and stop only when the required gates pass.
Why use it?
It prevents an agent from approving its own work without evidence and requires revisions when visual, accessibility, workflow, or test checks fail.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is ashishpatill/tell-proof's own configuration. It tells 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/skills/gates-until-verified/SKILL.md
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 gates-until-verified

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ashishpatill/tell-proof/gates-until-verified"><img src="https://agentmods.dev/badge/skills/ashishpatill/tell-proof/gates-until-verified.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 297 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 $0.00047 $0.00297
Opus 5 $0.00023 $0.00148
Sonnet 5 $0.00009 $0.00059
Haiku 4.5 $0.00005 $0.00030

Measured 9d ago against content hash f6d056a2cb9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

gates-until-verified 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 9d 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/skills/gates-until-verified/SKILL.md · 31 lines

What it actually says

gates-until-verified

Preserve the original task. Strengthen the process.

1. Lock the task contract

Outcome, audience, inputs, constraints, definition of done.

2. Convert ambition into gates

Gate Method Pass Evidence
Craft / detectors Tell diagnose or critique No new generic tells; score ≥ prior report JSON
Contrast / a11y basics checklist + focus-visible Pass checklist / screenshot
Proof / workflow Visual inspection Sample labeled; human gate present screenshot
Types / tests pnpm test + typecheck Green command output

3. Separate making from judging

Implementer does not sole-approve. Verifier sees task + gates + artifact — not self-assessment.

4. Loop

Produce → run gates → record pass/fail → smallest fix → re-check affected gates.

5. Stop honestly

All required gates pass, or name the blocker. Never weaken a gate to declare success.

Related: tell-proof-verify, design-research-loop, tell-dogfood-audit.

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. 9d ago First seen · 31 lines · 47 tokens per session scan A f6d056a2cb9a

Subscribe to this mod's changes

gates-until-verified is a skill published in the GitHub repository ashishpatill/tell-proof (1 stars, last pushed 14d ago), licensed MIT. It adds 47 tokens to every session and 297 once invoked, about $0.0002 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.