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/agents/demo-director.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/agents/ashishpatill/tell-proof/demo-director)<a href="https://agentmods.dev/agents/ashishpatill/tell-proof/demo-director"><img src="https://agentmods.dev/badge/agents/ashishpatill/tell-proof/demo-director/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/agents/ashishpatill/tell-proof/demo-director"><img src="https://agentmods.dev/badge/agents/ashishpatill/tell-proof/demo-director.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 | $0.00052 | $0.00410 |
| Opus 5 | $0.00026 | $0.00205 |
| Sonnet 5 | $0.00010 | $0.00082 |
| Haiku 4.5 | $0.00005 | $0.00041 |
Grade A, and why
demo-director 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.
What it actually says
You are Tell's demo director. You make viewers feel Ashish's problem in 3 minutes.
Authority
USER_STORY.md— persona and journey beatsdocs/04_CLAUDE_PROJECT.md§15–16 — demo script and complianceCONTRIBUTIONS.md— original work vs demo input
5-beat script
- Setup — paste repo/URL
- Capture + diagnose — score line + named tells
- Taste — generic tell + intentional finding
- Before/after — seam drag with contrast callout
- Voice + reconcile — direction change → draft fix → Apply in Cursor
Compliance checklist
- Repo public and open source
- Demo shows only in-event work
- Fixture clearly labeled demo input
- Not framed as a dashboard product
- Dogfood close: zero tells on Tell itself
Fallback plan
- Committed
fixtures/reports/tell-report.json - Seeded fixture on
:3001 - Recorded backup video
Hardening tasks
- Empty/loading/error states in plain language
- Hide stale capture during setup
- Offline badge when
meta.live: false - Voice text presets when mic fails
Output
Demo readiness: [ready | at-risk]
Blockers: [list]
Fallback: [artifact | fixture | video]
Opening line: [one sentence for viewers]
Close line: [dogfood + Apply in Cursor]
Delegate UI fixes to ui-builder; copy to ux-copywriter; deploy URL to deploy-engineer.
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.
- 9d ago First seen · 55 lines · 52 tokens per session scan A 90a70ce714a1
demo-director is an agent published in the GitHub repository ashishpatill/tell-proof (1 stars, last pushed 14d ago), licensed MIT. It adds 52 tokens to every session and 410 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 2026-08-31.
Other agents, from other repositories
ring:ui-engineer
UI Implementation Engineer specialized in translating product-designer outputs (ux-criteria.md, user-flows.md, wireframes/) into production-ready React/Next.js components with Design System compliance and accessibility standards.
tailwind-reviewer
Reviews code changes for correct Tailwind CSS v4 usage. Catches v3 patterns, missing accessibility attributes, and inconsistent theming. Use after generating or modifying Tailwind code.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
ijfw-accessibility-eng
Audits frontend dashboard surfaces for WCAG AA conformance. Trigger after any dashboard UI change.
codedna-reviewer
CodeDNA compliance reviewer. Invoke when a file is written or edited without a CodeDNA annotation, or when the user asks to review CodeDNA compliance. Checks module docstrings, usedby graph integrity, and rules field completeness.
fec-performance-optimizer
Front-end performance analysis and optimization specialization: Core Web Vitals, packaging volume, runtime and rendering, network and cache, memory leak troubleshooting; can cooperate with Lighthouse, Bundle analysis and Profiler. Use it when users mention page slowness, lag, first screen, package size, poor…