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.
curl -O https://raw.githubusercontent.com/ashishpatill/tell-proof/master/.cursor/skills/tell-proof-verify/SKILL.mdgit clone --depth 1 https://github.com/ashishpatill/tell-proofWrote 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.
[](https://agentmods.dev/skills/ashishpatill/tell-proof/tell-proof-verify)<a href="https://agentmods.dev/skills/ashishpatill/tell-proof/tell-proof-verify"><img src="https://agentmods.dev/badge/skills/ashishpatill/tell-proof/tell-proof-verify/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.
<a href="https://agentmods.dev/skills/ashishpatill/tell-proof/tell-proof-verify"><img src="https://agentmods.dev/badge/skills/ashishpatill/tell-proof/tell-proof-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.00573 |
| Opus 5 | $0.00023 | $0.00287 |
| Sonnet 5 | $0.00009 | $0.00115 |
| Haiku 4.5 | $0.00005 | $0.00057 |
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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tell Proof verify workflow
When to use
- After drafting a redesign patch with
tell_redesign/tell_apply - Before merging a frontend PR that changes rendered UI
- When Ashish asks whether a visual fix actually improved the surface
MCP path (Cursor Agent)
1. tell_diagnose on the running preview URL
2. tell_redesign with direction (e.g. "editorial")
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
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 |
Web path
- Set up repo locally (
/api/setup/start) - Draft fix in Tell Report UI
- Click Prove patch — uses
/api/proof/apply - Compare before/after screenshots and score delta
Rules
- Never auto-merge on
passedalone — human reviews the diff - Always capture the same URL as the baseline report
- Prefer disposable checkout proof over editing the main branch directly
Related
- Skill:
tell-mcp-tools - Skill:
tell-dogfood-audit - Skill:
gates-until-verified— acceptance-gate loop around this verify path - Skill:
agency-quality-site— for new marketing sites, run typography → spacing → motion → 375px polish before proof-verify; keep axes isolated packages/core/src/proof-verify.ts
Agency polish (when verifying a built marketing page)
If the change set is a greenfield / redesign marketing surface (not a one-line patch):
- Confirm
agency-quality-sitephases 0–3 completed (or runpnpm agency:pipeline) - Proof-verify the final HTML/URL after axis-isolated polish — not the raw first build
- Fail proof if ban-list /
assertAgencyDeliveryregressions appear after the patch - Prefer separate commits or ledger rows per polish axis when iterating
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.
- 7d ago First seen · 62 lines · 47 tokens per session scan A 853e4100de9c
tell-proof-verify is a skill published in the GitHub repository ashishpatill/tell-proof (1 stars, last pushed 15d ago), licensed MIT. It adds 47 tokens to every session and 573 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 2026-09-03.
Other skills, from other repositories
visual-validation
Autonomous screenshot verification — captures, compares, and AI-evaluates UI changes for visual regressions.
ui-aqa-flow
Workflow for automated QA: integration and end-to-end UI test automation, page objects, etc.
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.
e2e-runner
End-to-end testing specialist using Vercel Agent Browser or Playwright.
dev-testing
A testing guide that defines when to use unit, integration, API, and end-to-end tests. Unit tests check small pieces of code, while end-to-end tests check a full user flow.
dev-scenario-test
A specification for scenario testing, covering end-to-end tests, integration tests, and Artillery load tests. The input does not provide further details about its exact setup or outputs.