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 skills add syangchester-lab/build-your-persona --skill persona-generationgit clone --depth 1 https://github.com/syangchester-lab/build-your-personaWrote 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/syangchester-lab/build-your-persona/persona-generation)<a href="https://agentmods.dev/skills/syangchester-lab/build-your-persona/persona-generation"><img src="https://agentmods.dev/badge/skills/syangchester-lab/build-your-persona/persona-generation/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/syangchester-lab/build-your-persona/persona-generation"><img src="https://agentmods.dev/badge/skills/syangchester-lab/build-your-persona/persona-generation.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 | $0.00145 | $0.00984 |
| Opus 5.5 | $0.00058 | $0.00394 |
| Sonnet 5.5 | $0.00029 | $0.00197 |
| Haiku 4.5 | $0.00015 | $0.00098 |
Grade A, and why
persona-generation 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 2mo 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona Generator — Private Persona
You've loaded the persona generator. I'll guide you through building an AI thinking partner calibrated to how you specifically reason.
At the end of this session, you'll have a SKILL.md file you can install and use in any future Claude session.
First: which mode?
Express (30–60 min): I ask you 5 questions. You answer honestly. I extract your patterns.
Rigorous (2–4 hrs): You supply real work data — transcripts, decisions, written documents. I extract patterns inductively from what you actually do, not what you think you do.
Rigorous produces more accurate results. Express is a good starting point.
Which do you want to start with?
Express Mode — 5 Questions
Answer these as honestly as you can. The goal is to capture real patterns, not an idealised version of how you think.
Q1: When you're at your best in a meeting or working session, what are you actually doing? (Not what you should be doing — what you notice yourself doing that seems to work.)
Q2: What's a type of problem you solve faster than most people around you? What do you do differently?
Q3: What's a mistake you stopped making that you still see others around you make? What changed?
Q4: When someone presents an argument you find unconvincing, what's usually missing from it?
Q5: Describe a recent decision you made under uncertainty. How did you actually approach it — not the polished version, the real version?
Rigorous Mode — Data Collection
Provide at least 2 of the following:
- Meeting or conversation transcripts where you were making decisions (not just reporting or presenting)
- Written strategy documents you authored under time pressure
- Email threads where you were negotiating or advising
- A "thinking out loud" session — just talk through a recent problem and I'll record the patterns
More data = better accuracy. The key is capturing you when you're working, not when you're explaining yourself.
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.
- 2mo ago First seen · 117 lines · 145 tokens per session scan A 6ed4dd783c2c
persona-generation is a skill published in the GitHub repository syangchester-lab/build-your-persona (2 stars, last pushed 5mo ago), licensed MIT. It adds 145 tokens to every session and 984 once invoked, about $0.0006 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.
persona-generation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| persona-generationsyangchester-lab/build-your-persona | Skill | 2 | 5mo ago | MIT | A | 145 | Claude Code, Codex |
| knowledge-ingestopenclaw/openclaw | Skill | 394k | today | MIT | A | 80 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 69k | yesterday | Apache-2.0 | A | 217 | Claude Code, Codex |
| forgetasgeirtj/system_prompts_leaks | Skill | 71k | today | CC0-1.0 | A | 0 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | 2d ago | MIT | A | 184 | Claude Code |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | today | MIT | A | 115 | Claude Code, Codex |
| memoryopensquilla/opensquilla | Skill | 7.1k | 7d ago | Apache-2.0 | A | 44 | Claude Code, Codex |