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 5.5 | $0.00023 | $0.00228 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 (2 stars, last pushed 22d ago), licensed MIT. It adds 57 tokens to every session and 570 once invoked, about $0.0002 per session on Opus 5.5. 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
run-ux-validation
Validate a user journey before merge or release by running Stunt Double workflows and checklists and reporting pass or fail with failure detail.
visual-testing
Visual testing, UI verification, and design comparison using screenshots and Figma integration. Use when the user wants to verify UI appearance, compare with Figma designs, test responsive layouts, check for visual regressions, or validate design implementation.
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
qa-test-planner
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
test-runner
For a code change, pick the right test tier by change surface, run apc test with baseline diff, and report only NEW reds vs baseline back to the task's acceptance criterion. Separates envblocked from SUT red so a broken machine never fails the code.