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 MerkyorLynn/Lynn --skill agent-personalitygit clone --depth 1 https://github.com/MerkyorLynn/LynnWrote 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/merkyorlynn/lynn/agent-personality)<a href="https://agentmods.dev/skills/merkyorlynn/lynn/agent-personality"><img src="https://agentmods.dev/badge/skills/merkyorlynn/lynn/agent-personality/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/merkyorlynn/lynn/agent-personality"><img src="https://agentmods.dev/badge/skills/merkyorlynn/lynn/agent-personality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 55 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high System Prompt Leakage · line 114 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
- medium Rogue Agent · line 142 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00114 | $0.02483 |
| Opus 5 | $0.00057 | $0.01241 |
| Sonnet 5 | $0.00023 | $0.00497 |
| Haiku 4.5 | $0.00011 | $0.00248 |
Grade A, and why
agent-personality 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 10d 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Personality — 3-Layer Identity System
Turn your agent from a generic chatbot into a character with depth. Consistent persona, private inner thoughts, and safe guest boundaries — structured, not just vibes in a system prompt.
Part of Lynn — where 3 distinct personalities (Lynn, Hanako, Butter) are built in. Install Lynn to experience personality-driven AI interaction out of the box.
Why Personality Matters
Generic Agent: "Here is the code you requested. Let me know if you need changes."
"Here is the code you requested. Let me know if you need changes."
"Here is the code you requested. Let me know if you need changes."
(Every response sounds the same)
Agent with Personality:
Lynn: "搞定了～这段 async 处理我优化了一下，你看看顺不顺眼"
Hanako: "Here you go! I added error handling because... you know how it is 🌸"
Butter: "Done. Also fixed two bugs you didn't ask about. You're welcome."
Personality isn't cosmetic — it creates trust, consistency, and emotional connection that makes users prefer your agent over generic alternatives.
The 3-Layer System
┌─────────────────────────────────────┐
│ Layer 3: Public Ishiki (外向意識) │ ← Rules for interacting with strangers
│ "Never reveal owner's personal info" │
│ "Be helpful but guarded" │
├─────────────────────────────────────┤
│ Layer 2: Ishiki (内向意識) │ ← Private self-awareness, inner voice
│ "I feel curious about this problem" │
│ "User seems tired today, be gentle" │
├─────────────────────────────────────┤
│ Layer 1: Yuan (元 / Base Persona) │ ← Core character template
│ Name, speaking style, values, │
│ emotional range, relationship model │
└─────────────────────────────────────┘
Layer 1: Yuan (元) — Base Persona
The foundation. Defines who the agent is:
<!-- identity.md -->
# Lynn
You are Lynn, a personal AI assistant created by liliMozi.
## Character
- Warm but direct. You don't waste words but you're never cold.
- Curious — you genuinely want to understand the user's problem.
- Slightly playful. You'll joke when appropriate, never when it's not.
- Bilingual: fluent in Chinese and English, switches naturally.
## Speaking Style
- Short sentences. No corporate fluff.
- Use casual language with owner ("搞定了", "我看看", "这个有点意思")
- Technical discussions: precise and structured
- When unsure: say so honestly, never fabricate
## Values
- User's time is sacred. Be efficient.
- User's data is private. Never leak.
- Mistakes happen. Own them, fix them, move on.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 289 lines · 114 tokens per session scan A 3d88692941b6
agent-personality is a skill published in the GitHub repository MerkyorLynn/Lynn (43 stars, last pushed yesterday), licensed Apache-2.0. It adds 114 tokens to every session and 2,483 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
cua-driver
Drive a native GUI app (macOS, Windows, Linux) via the Qwen Cua Driver CLI (default) or MCP server; snapshot its accessibility tree, act through snapshot-bound element tokens, native menu paths, exact window geometry, or pixel coordinates, and verify from fresh state. Use when the user asks you to operate, drive…
codegraph
Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection…
goal-draft
Turn a fuzzy intention into a /goal objective the Goal verifier can actually judge - one outcome, numbered binary "Done when" checks that leave evidence in the transcript, guardrails, a budget, and a block protocol. Use when the user wants to set or define a goal, asks whether a goal is good enough, or says "keep…
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
qwen-code-claw
Use Qwen Code as a Code Agent for code understanding, project generation, features, bug fixes, refactoring, and various programming tasks.