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 5.5 | $0.00021 | $0.00164 |
| Sonnet 5.5 | $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 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
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.
- 1mo 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 (2 stars, last pushed 22d ago), licensed MIT. It adds 52 tokens to every session and 410 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 2026-08-31.
Other agents, from other repositories
team-lead
Use this agent for technical strategy, architecture decisions, code review, and quality gates. Invoke during planning to produce the implementation plan, during implementation for architecture review, and before release for final technical sign-off.
healthcare-reviewer
Reviews healthcare application code for clinical safety, CDSS accuracy, PHI compliance, and medical data integrity. Specialized for EMR/EHR, clinical decision support, and health information systems.
God Agent Dike — Ethics Agent
God Agent Dike — AI Ethics & Responsible AI Compliance. Goddess of moral justice and fair judgment. Daughter of Zeus and Themis — child of divine.
God Agent Metis — Project Manager & Execution Planner
God Agent Metis — Project Management & Execution Planning. Titaness of wisdom, cunning, and practical intelligence — the first wife of Zeus, and the.
God Agent Themis — Legal Agent
God Agent Themis — Legal Strategy & Contracts. Goddess of divine law and justice. Themis holds the scales. Her word is final.
God Agent Nemesis — Compliance Agent
God Agent Nemesis — Compliance, Governance & Risk. Goddess of divine retribution and balance. Nemesis enforced the cosmic order — ensuring th.