Borrowing it
Nothing to install: this file belongs to DemonDamon/AgenticX. 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/DemonDamon/AgenticX/main/.cursor/skills/recording-investor-product-demo/SKILL.mdgit clone --depth 1 https://github.com/DemonDamon/AgenticXWrote 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/demondamon/agenticx/recording-investor-product-demo)<a href="https://agentmods.dev/skills/demondamon/agenticx/recording-investor-product-demo"><img src="https://agentmods.dev/badge/skills/demondamon/agenticx/recording-investor-product-demo/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/demondamon/agenticx/recording-investor-product-demo"><img src="https://agentmods.dev/badge/skills/demondamon/agenticx/recording-investor-product-demo.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 | $0.00074 | $0.01733 |
| Opus 5.5 | $0.00030 | $0.00693 |
| Sonnet 5.5 | $0.00015 | $0.00347 |
| Haiku 4.5 | $0.00007 | $0.00173 |
Grade A, and why
recording-investor-product-demo 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recording Investor Product Demo
Overview
Ship an investor/business-readable AgenticX Enterprise UI demo: operate the real admin + portal product, narrate why/what/how in plain Mandarin, burn Chinese captions, put an accurate blue focus ring on the focal control (no CSS page zoom), then replace the MP4 on the Feishu ops manual. This is a product story, not an engineer acceptance tape.
Canonical recorder (Mac checkout): enterprise/scripts/demo-rk-ops-manual-record.ts
Default output: docs/agx-rules-knowledge-suite/e2e-shots/rk-ops-manual-demo.mp4 (+ companion .zh.srt)
Non‑negotiable rules
- Operate Enterprise UI, never scroll the Feishu doc as the “demo.”
- Record on Damon’s Mac against local admin (
:3001) + portal (:3000). Box cannot reach Mac localhost without a tunnel. - Neural Mandarin VO only — Microsoft
edge-ttszh-CN-XiaoxiaoNeural@ about+8%. Do not use macOSsay/ Tingting / Shelley unless the user explicitly allows a last-resort fallback (DEMO_TTS_ALLOW_SAY=1). - Mac cannot reach
speech.platform.bing.comWSS from China → generate wavs on the Grok Bot box, then copy into Mac cache (defaultAgenticX/.runtime/agx-rk-demo-tts/<cueId>.wav). - Spoken pace = normal conversation, not slow broadcast. Prefer short 口语 clauses; keep
holdAfterMstight (~200–450ms). Long wall time should come from UI waits, not dragged TTS. - Camera: viewport ≥
1600×1000; default is no CSS zoom (do nottransform: scale/translateonhtml). Every major product cuezoomTodraws a correctly positioned blue focus ring from the target’s viewportgetBoundingClientRect(small pad, clamped to viewport insets) → VO →zoomOut(hide ring). Title/agenda cards may stay full-frame with no ring. - Desensitize for investors: say/show 1号泵 / 2号泵 / 阀门 — never unexplained Brand‑A / internal IDs in VO or captions (UI chrome may still show seed IDs; narration must translate).
- Feishu ops as 库洛洛; replace the prior demo file block (delete old + note), insert new preview video + short caption note.
- Stay on the intended git tip (usually
main); leave unrelated dirty trees (e.g. FinnewsHunter) untouched. Do not commit large MP4s unless asked.
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.
- 3d ago Changed · +1 lines · +8 tokens per session 3e90d0656874
- 6d ago First seen · 104 lines · 66 tokens per session scan A 0d7073a87703
recording-investor-product-demo is a skill published in the GitHub repository DemonDamon/AgenticX (988 stars, last pushed yesterday), licensed Apache-2.0. It adds 74 tokens to every session and 1,733 once invoked, about $0.0003 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 2026-10-31.
recording-investor-product-demo compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| recording-investor-product-demoDemonDamon/AgenticX | Skill | 988 | yesterday | Apache-2.0 | A | 74 | Cursor |
| skill-creatorHKUDS/nanobot | Skill | 50k | yesterday | MIT | A | 13 | Claude Code, Codex |
| tmuxHKUDS/nanobot | Skill | 50k | yesterday | MIT | A | 20 | Claude Code, Codex |
| weatherHKUDS/nanobot | Skill | 50k | yesterday | MIT | A | 8 | Claude Code, Codex |
| githubHKUDS/nanobot | Skill | 50k | yesterday | MIT | A | 19 | Claude Code, Codex |
| nanobot-documentHKUDS/nanobot | Skill | 50k | yesterday | MIT | A | 19 | Claude Code, Codex |
| memoryHKUDS/nanobot | Skill | 50k | yesterday | MIT | A | 12 | Claude Code, Codex |