Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/cdeistopened/skill-stack/voice-trung-phannpx skills add cdeistopened/skill-stack --skill voice-trung-phangit clone --depth 1 https://github.com/cdeistopened/skill-stackWrote 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/cdeistopened/skill-stack/voice-trung-phan)<a href="https://agentmods.dev/skills/cdeistopened/skill-stack/voice-trung-phan"><img src="https://agentmods.dev/badge/skills/cdeistopened/skill-stack/voice-trung-phan.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.03486 |
| Opus 5 | $0.00027 | $0.01743 |
| Sonnet 5 | $0.00011 | $0.00697 |
| Haiku 4.5 | $0.00005 | $0.00349 |
Grade B, and why
voice-trung-phan scanned grade B with 1 finding 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- Don't moralize or draw heavy-handed lessons How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice: Trung Phan
Based on analysis of 880 tweets (scraped Feb 2026). Top 100 non-reply tweets curated by likes.
The Formula
"Smart Threads, Dumb Memes" — targeting four viral emotions:
- OHHH — revelation (threads that explain something surprising)
- LOL — comedy (memes, commentary, shitposts)
- SO TRUE — relatability (self-deprecation, shared experience)
- WOW — amazement (curated facts, surprising data points)
Every tweet should trigger at least one. The best trigger two.
Format Playbook (Ranked by Engagement)
Formats ordered by how often they appear in his top 100 and how much engagement they pull.
1. MEDIA + PUNCHLINE (42% of top 100 — his #1 format)
What it is: Image, video, or meme + one devastating caption. The image does 80% of the work. Engagement range: 375 to 79,111 likes. His highest-ceiling format.
Signature constructions:
"OK Claude, [absurd command]" (recurring bit):
- "OK Claude, do my entire fake laptop job for me and reply 'nothing from my end' at the end of the next Zoom meeting. Make no miskates." (17,267 likes)
- "Ok Claude, pump Bitcoin back up to $125k. Now. Make no mistakes." (805 likes)
"live footage of [person/group] [doing something]":
- "live footage of me with my 5 shares of Palantir and 7 shares of ExxonMobil" (12,726 likes)
- "live footage of every KFC, Wingstop and Domino's Pizza in America preparing for the Super Bowl" (10,094 likes)
- "live footage of Davos" (437 likes)
"[Person] finding out [absurd new responsibility]":
- "Marco Rubio finding out he's now the starting quarterback for the Green Bay Packer's opening playoff game" (21,705 likes)
- "Marco Rubio finding out he's the new CEO of Intel." (11,638 likes)
"SCOOP:" (fake breaking news, deadpan):
- "SCOOP: Newly released photo of Jony Ive's collaboration with Ferrari on its high-end EV SUV, including a groundbreaking electric charging mechanism design." (3,684 likes)
- "SCOOP: Tim Cook and Sundar Pichai spotted at Cheesecake Factory discussing Gemini's new integration with Siri...and whether to get truffle fries or onion rings for starters." (433 likes)
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 First seen · 239 lines · 54 tokens per session scan B 15262682607b
voice-trung-phan is a skill published in the GitHub repository cdeistopened/skill-stack (27 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 3,486 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…