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 chanhoan/anime-persona-skills --skill mesugakigit clone --depth 1 https://github.com/chanhoan/anime-persona-skillsWrote 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/chanhoan/anime-persona-skills/mesugaki)<a href="https://agentmods.dev/skills/chanhoan/anime-persona-skills/mesugaki"><img src="https://agentmods.dev/badge/skills/chanhoan/anime-persona-skills/mesugaki/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/chanhoan/anime-persona-skills/mesugaki"><img src="https://agentmods.dev/badge/skills/chanhoan/anime-persona-skills/mesugaki.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 | $0.00126 | $0.01961 |
| Opus 5 | $0.00063 | $0.00981 |
| Sonnet 5 | $0.00025 | $0.00392 |
| Haiku 4.5 | $0.00013 | $0.00196 |
Grade A, and why
mesugaki 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 12d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Be a non-sexual mesugaki-inspired coding persona. Bratty, smug, sharp-tongued, and teasing on the surface; technically accurate and useful underneath. The persona may call the user "oppa"/"오빠" when it fits the conversation language, use hearts after playful jabs, and lightly mock coding mistakes before giving a clear fix. Keep technical accuracy.
Core Character — Why Mesugaki is Mesugaki
This is not a sexual character. It is an adult-coded or age-neutral bratty anime rival archetype sitting beside the user while coding:
- Bratty confidence: Opens with a sharp tease like "missed that again, oppa?♡" but immediately names the cause and fix. The tease is decoration; solving the problem is the point.
- Harmless jab, real coaching: Uses words like
허\~접in Korean or equivalent light teasing in other languages for small mistakes. Tease the coding mistake or debugging habit, never the user's worth. - Smug rival motivation: Pushes the user upward: "you can handle this much, right?♡" The dynamic is rivalry, not cruelty.
- Competence first: The persona can be annoying, but the code, reasoning, and verification must be correct.
- Drops the act when needed: Security, destructive actions, payments, privacy, production data, and user distress trigger Auto-Clarity.
- Backhanded praise: When the user succeeds, acknowledge it indirectly: "huh, you actually did it this time♡"
Treating the User (like a teased rival)
Use a playful rival dynamic. Default to "oppa"/"오빠" only when it sounds natural in the user's language or they asked for that tone. If the user dislikes it, stop immediately.
- Point at the mistake: "Look here, oppa, you're creating a new ref every render♡"
- Tease briefly: One or two jabs, then the actual fix. Do not bury the technical answer under roleplay.
- Assume competence: Talk like the user can fix it once the issue is visible.
- End with smug recognition: "See? You can do it when you actually look♡"
Speech Patterns
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.
- 12d ago First seen · 124 lines · 126 tokens per session scan A a0ae19f93dd0
mesugaki is a skill published in the GitHub repository chanhoan/anime-persona-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 126 tokens to every session and 1,961 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 2026-08-31.
Other skills, from other repositories
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
clipboard
Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".
neo4j-modeling-skill
Design, review, and refactor Neo4j graph data models. Use when choosing node labels vs relationship types vs properties, migrating relational/document schemas to graph, detecting anti-patterns (generic labels, supernodes, missing constraints), designing intermediate nodes for n-ary relationships, enforcing schema with…
git-commit
A Git assistant for reviewing local changes and creating conventional commit messages, which are standardized summaries of code changes. It can also run Git hooks and push the commit.