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 ohong/agent-skills --skill create-mascotgit clone --depth 1 https://github.com/ohong/agent-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/ohong/agent-skills/create-mascot)<a href="https://agentmods.dev/skills/ohong/agent-skills/create-mascot"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/create-mascot/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/ohong/agent-skills/create-mascot"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/create-mascot.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 | $0.00052 | $0.00818 |
| Opus 5.5 | $0.00021 | $0.00327 |
| Sonnet 5.5 | $0.00010 | $0.00164 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
create-mascot 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 1mo 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Mascot
Develop a character whose silhouette, expressions, and movement belong to the product.
The final deliverables are <mascot-name>.blend and <mascot-name>.md, a mascot description of at most 300 words.
Concept previews and verification renders support development; they do not replace the Blender deliverable.
Understand the role
Read taste.md for the distinct research lenses, then concept-development.md before drafting concepts. Use the supplied project, brand, audience, placement, and reference assets. Inspect relevant product context when available. Establish the mascot's relationship to the user: peer, pet, guide, tool, ambient presence, or another role. Ask early when that choice or another missing constraint would materially change the character; infer routine choices from the brief. Do not reuse another project's name, palette, or relationship model by default. Check Blender availability before promising production; see blender-production.md.
Make the performance visible
Prefer a simple silhouette, characteristic action, and three readable expressions before surface detail. Unless the user already chose a direction or delegated selection, show about three genuinely distinct options. Vary silhouette, expression mechanics, and movement; recolors are not separate concepts. Prefer built-in image generation for useful concept previews, following its current tool instructions. Describe each option's expression and motion plan, brand fit, and likely modeling tradeoffs. Keep images labeled as concepts. They do not demonstrate a working rig or animation.
Carry the selected identity into Blender
Obtain a selected direction before expensive Blender production. Prior selection or explicit delegation of selection counts. Do not select silently or repeat approval. When delegated, show the chosen direction and rationale, then proceed; otherwise ask for the missing selection. Record the chosen proportions, silhouette, face placement, material character, and signature action. Read blender-production.md to build and verify that same design as native geometry with usable controls. Choose rigid parts, deforming bones, shape keys, or a hybrid according to the anatomy and performance; flat graphic aesthetics are welcome. If the chosen appearance cannot survive the proposed rig, revise the construction; resolve substantial design changes within the user's selection authority. Provide a useful neutral/rest state and independently adjustable face, gaze, and body where those features exist. Retain named sample actions: ordinarily one loop and two distinct reactions, adapted to the brief. Read motion-and-web.md for timing, interruption, expression, and optional product behavior.
What ships with it
7 files 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.
- 1mo ago First seen · 55 lines · 52 tokens per session scan A a12272fbf469
create-mascot is a skill published in the GitHub repository ohong/agent-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 818 once invoked, about $0.0002 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 2026-09-15.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.