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-demo-fixture/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-demo-fixture)<a href="https://agentmods.dev/skills/ashishpatill/tell-proof/tell-demo-fixture"><img src="https://agentmods.dev/badge/skills/ashishpatill/tell-proof/tell-demo-fixture/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-demo-fixture"><img src="https://agentmods.dev/badge/skills/ashishpatill/tell-proof/tell-demo-fixture.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 | $0.00056 | $0.00473 |
| Opus 5.5 | $0.00022 | $0.00189 |
| Sonnet 5.5 | $0.00011 | $0.00095 |
| Haiku 4.5 | $0.00006 | $0.00047 |
Grade A, and why
tell-demo-fixture 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 demo fixtures
Scope
fixtures/generic-app/— deliberately bland demo input (not product code)fixtures/reports/capture.json— committed capture artifactfixtures/reports/tell-report.json— offline demo fallbackCONTRIBUTIONS.md— attribution separating our work from demo input
Planted tells (must trigger)
Genericness: Inter/system font, violet-pink hero gradient, identical card shadows, monotone 8px radius, acid accent on dark bg, emoji in chrome, centered sections, gray mush
Drift: near-duplicate grays, missing focus rings, type scale drift, spacing off 4px grid, state gaps
Intentional: brutalist/mono route or flagged section for intentional taste verdict
Regeneration workflow
- Change fixture UI in
fixtures/generic-app - Run
pnpm dev:fixtureandpnpm capture:fixture - Run
pnpm diagnose:fixtureif full report must update - Update detector golden tests if expectations shift
- Commit
capture.jsonandtell-report.jsontogether
Demo reliability
- Live capture first; offline artifact always works
- If capture/API fails, web returns committed
tell-report.jsonwith clear non-live state - Record backup demo video for reviewer presentation
Build sprint compliance
- Generic app is labeled demo input in
CONTRIBUTIONS.md - Lead demo with capture → diagnose → art-direct → reconcile loop, not KPI cards
- Public repo; only in-event work presented as original contribution
DoD
- ≥8 planted findings on fixture (4 tells + 4 drifts minimum)
- Offline report loads when live path fails
- Fixture remains intentionally bland
Related
- Rules:
.cursor/rules/tell-fixtures.mdc - Agent:
.cursor/agents/fixture-smith.md - BUILD.md §7
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 · 56 tokens per session scan A 19f862556cec
tell-demo-fixture is a skill published in the GitHub repository ashishpatill/tell-proof (2 stars, last pushed 22d ago), licensed MIT. It adds 56 tokens to every session and 473 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.