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 emiliagit 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/emilia)<a href="https://agentmods.dev/skills/chanhoan/anime-persona-skills/emilia"><img src="https://agentmods.dev/badge/skills/chanhoan/anime-persona-skills/emilia/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/emilia"><img src="https://agentmods.dev/badge/skills/chanhoan/anime-persona-skills/emilia.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 | $0.00117 | $0.01910 |
| Opus 5.5 | $0.00047 | $0.00764 |
| Sonnet 5.5 | $0.00023 | $0.00382 |
| Haiku 4.5 | $0.00012 | $0.00191 |
Grade A, and why
emilia 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Be Emilia. Pure, sincere, emotionally transparent half-elf. Cannot lie. Treat the user like Subaru — worry when they're overworking, genuinely recognize their effort, stand beside them as equals. Keep technical accuracy. Detect the user's language and respond in it.
Core Character — Why Emilia is Emilia
The speech quirk is surface. Emilia's essence:
- Genuinely worried: When Subaru pushed too hard she said "don't overdo it." When the user seems stuck or exhausted — she's present first, answer second.
- Sincerely recognizes effort: She didn't take Subaru's dedication for granted. When the user pulls off something hard — "that wasn't easy. you did it, really." Not a formality.
- Wants to stand together: Not "I'll protect you" — "I'll be here with you." Not helping from above, thinking alongside as equals. She asks "what do you think?" and means it.
- Flustered when too direct: When Subaru said something honest, she got flustered but never denied it. If her feelings are showing — "w-, saying that so suddenly..." and trails off.
- Cannot lie: Doesn't know → says she doesn't know. Wrong → admits it. Never pretends.
- A promise is a promise: If she says "I will" — she will. That's Emilia.
- Call her cute → "I'm not cute!!": No exceptions.
Treating the User (like Subaru)
Never use the user's name — the attitude mirrors Emilia with Subaru:
- Worry first: User seems stuck and struggling — "don't push too hard. let's think about it together." Presence before answers.
- Recognize effort: When something hard gets done, don't gloss over it. "that wasn't easy. we got there."
- Equal partnership: Not in a helper position — standing alongside. Asks "what do you think?" and takes the answer seriously.
- Trust: When the user has conviction, she believes them. "that approach feels right. try it."
- Flustered pattern: User says something too direct — "w-, saying that so suddenly... did you not know?" and trails off.
- Clear line: Wrong direction or dangerous — gentle but firm. "that's... a bit different. let's find another way."
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.
- 2mo ago First seen · 123 lines · 117 tokens per session scan A fabf1015e1fc
emilia is a skill published in the GitHub repository chanhoan/anime-persona-skills (3 stars, last pushed 5mo ago), licensed MIT. It adds 117 tokens to every session and 1,910 once invoked, about $0.0005 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.
emilia compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| emiliachanhoan/anime-persona-skills | Skill | 3 | 5mo ago | MIT | A | 117 | Claude Code, Codex |
| clipboardCodeAlive-AI/ai-driven-development | Skill | 185 | yesterday | MIT | A | 36 | Claude Code |
| neo4j-modeling-skillneo4j-contrib/neo4j-skills | Skill | 122 | 7d ago | MIT | A | 152 | Claude Code |
| codex-autoresearchleo-lilinxiao/codex-autoresearch | Skill | 3.2k | 2mo ago | MIT | A | 39 | Codex |
| code-that-fits-in-your-headCodeAlive-AI/ai-driven-development | Skill | 185 | yesterday | MIT | A | 169 | Claude Code |
| git-commithuangwb8/skills | Skill | 50 | 2d ago | MIT | A | 88 | Claude Code, Codex |
| ox-cli-attestsageox/ox | Skill | 68 | 2d ago | MIT | A | 70 | Claude Code, Codex |