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-dogfood-audit/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-dogfood-audit)<a href="https://agentmods.dev/skills/ashishpatill/tell-proof/tell-dogfood-audit"><img src="https://agentmods.dev/badge/skills/ashishpatill/tell-proof/tell-dogfood-audit/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-dogfood-audit"><img src="https://agentmods.dev/badge/skills/ashishpatill/tell-proof/tell-dogfood-audit.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 | $0.00057 | $0.00570 |
| Opus 5 | $0.00028 | $0.00285 |
| Sonnet 5 | $0.00011 | $0.00114 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
tell-dogfood-audit 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 8d 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.
What it actually says
Tell dogfood audit
Goal
Tell must pass its own audit: 0 generic tells, 0 unintentional drift on apps/web.
Checklist (from docs/01_DESIGN_SYSTEM.md §12)
| Check | Pass criteria |
|---|---|
| Type system | Display + sans + mono present; no Inter-only |
| Color | No violet gradient hero; no acid accent on near-black |
| Chrome contrast | pnpm eye:shell green - sidebar/rail text ≥ 4.5:1 on its painted surface (do not trust vision alone) |
| Shadow | e2 max on cards; not shadow on every element |
| Radius | ≥2 distinct radii in main view |
| Centering | Asymmetric report layout |
| Grays | ≤4 distinct gray values in token ramp |
| States | Full matrix on Button, CaptureBar, VoiceDirector, seam handle |
| Tokens | No raw hex in committed TSX classNames |
Workflow
- Run Tell diagnose on local web app (
http://localhost:3000) or inspect committed self-report - Run
pnpm eye:shell- measured WCAG contrast on.tell-rail(closeschrome:rail-ghost-contrast) - Fix real findings in
apps/webusing semantic tokens fromglobals.css/tailwind.config.ts - Re-run until generic tells are zero and eye:shell passes
- Verify a11y: focus-visible, reduced motion, non-color verdict encoding
Vision is not enough
Agent image descriptions miss low-contrast chrome. Before shipping Tell UI or showcase shell
changes, run the measured probe (pnpm eye:shell). Paper rails must use --ink-on-paper
hex tokens - never dark-theme --text (paper-on-dark) on a light surface.
Hook support
.cursor/hooks/after-edit-check.mjs flags Inter-only stacks and raw hex in web edits when hooks are wired.
DoD
- Demo line holds: "Tell runs on itself: zero tells."
- UI matches editorial print-atelier aesthetic
- No TokenBypass violations in Tell's own source
Related
- Rules:
.cursor/rules/tell-ui-design.mdc,.cursor/rules/tell-mission.mdc - Agent:
.cursor/agents/dogfood-auditor.md
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.
- 8d ago First seen · 54 lines · 57 tokens per session scan A ce8a8cde4e06
tell-dogfood-audit is a skill published in the GitHub repository ashishpatill/tell-proof (1 stars, last pushed 17d ago), licensed MIT. It adds 57 tokens to every session and 570 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 2026-09-03.
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.
agent-gan-evaluator
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.
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.