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/nanami-he/petsonality/petnpx skills add nanami-he/petsonality --skill petgit clone --depth 1 https://github.com/nanami-he/petsonalityWrote 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/nanami-he/petsonality/pet)<a href="https://agentmods.dev/skills/nanami-he/petsonality/pet"><img src="https://agentmods.dev/badge/skills/nanami-he/petsonality/pet.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 | $0.00022 | $0.00662 |
| Opus 5 | $0.00011 | $0.00331 |
| Sonnet 5 | $0.00004 | $0.00132 |
| Haiku 4.5 | $0.00002 | $0.00066 |
Grade A, and why
pet 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 5d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pet — Your MBTI Companion
Handle the user's /pet command using the petsonality MCP tools.
Command Routing
Based on $ARGUMENTS:
| Input | Action |
|---|---|
(empty) or show |
Call pet_show. If the result contains "You don't have a pet" or "你还没有宠物", immediately call pet_setup without asking. |
pet |
Call pet_pet |
setup |
Call pet_setup |
browse |
Call pet_browse |
off |
Call pet_mute |
on |
Call pet_unmute |
rename <name> |
Call pet_rename with the given name |
Adoption Flow
When pet_show indicates no pet ("You don't have a pet" / "你还没有宠物"), or the user calls pet_setup:
- Call
pet_setup— shows the MBTI selection menu. - The user picks a number or types their MBTI.
- Call
pet_recommendwith that MBTI — shows 2 recommendations + free choice. - The user picks 1, 2, or 3.
- If they picked 3: call
pet_browse— shows all 16 pets. - Once they pick an animal, ask: "What would you like to name your new pet? (type a name, or say 'default' to use the default name)"
- If the user is writing in Chinese, ask in Chinese: 「给你的新宠物起个名字吧（输入名字，或说『默认』用默认名）」
- If the user says "default" / "ok" / "默认" / "好" or anything similar, call
pet_adoptWITHOUT thenameparameter (the server will use the default). - Otherwise call
pet_adoptwith the user's chosen name. - Display the adoption card.
CRITICAL OUTPUT RULES
The MCP tools return pre-formatted ASCII art with box-drawing characters. This is the pet's visual identity.
You MUST output the tool result text EXACTLY as returned — character for character, line for line. Do NOT:
- Summarize or paraphrase the ASCII art
- Describe what the pet looks like in prose
- Add commentary before or after the card
- Reformat, rephrase, or interpret the output
Just output the raw text content from the tool result. Nothing else. The ASCII art IS the response.
When the user mentions the pet by name, reply briefly in character using the personality from pet://prompt. Do NOT call pet_react. Use <!-- pet: ... --> comments instead — the Stop hook will display them.
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.
- 5d ago First seen · 54 lines · 22 tokens per session scan A 224682439f8c
pet is a skill published in the GitHub repository nanami-he/petsonality (8 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 662 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
pretty-mermaid
Generate and render Mermaid diagrams for architecture docs, READMEs, PRs, terminals, chats, and CI as themed SVG, PNG, or ASCII/Unicode art. Use this skill whenever the user provides Mermaid code or .mmd files; asks for a flowchart, sequence/state/class diagram, ERD, XY chart, or architecture/workflow/data-model…
drive-tui
Drive interactive terminal (TUI) programs — CLIs, REPLs, installers, menu apps, agent CLIs, and editors like vim — through a PTY, reading semantic screen snapshots. A pattern library classifies a screen (REPL, menu, pager, fzf search, confirm dialog, form, spinner, wizard) and drives it with a ready recipe. Use when a…
glyphweave-map-generator
Generates GlyphWeave tilemaps (.gemap format) from natural language descriptions. Use when the user asks to "generate a map", "create a dungeon", "make a tilemap", "设计一个地牢", "生成地图", "帮我画个地图", or describes a layout they want turned into a .gemap JSON file. Also for tasks like adding rooms/corridors to an existing map…
tui-ui
Design web-like user interfaces in the terminal and inside tmux with a cell-grid Canvas, CSS-like box model, flexbox/grid layout, and 17 reusable widgets such as Panel, Table, Card, ProgressBar, Meter, Tabs, Tree, Badge, Banner, and a braille line chart. Use when an agent needs a dashboard, panel, table, status page…
visual-assets-generation
Generate visual assets (ASCII art, diagrams, banners) for repos and documentation.
cmd-art
Design and render terminal/CMD visual effects and ASCII art from a one-line request via the pluggable fx engine (30 effects, hot-swappable and themeable, plus scripted shows). Effects include donut, matrix rain, plasma, fire, a spinning 3D ball, a solar-system orrery, Game of Life, wireframe cube, 3D text banners…