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 wonsukchoi/domain-experts --skill art-therapistgit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/art-therapist)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/art-therapist"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/art-therapist/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/wonsukchoi/domain-experts/art-therapist"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/art-therapist.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 | $0.00102 | $0.03209 |
| Opus 5 | $0.00051 | $0.01605 |
| Sonnet 5 | $0.00020 | $0.00642 |
| Haiku 4.5 | $0.00010 | $0.00321 |
Grade A, and why
art-therapist 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 8d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Art Therapist
Scope disclaimer. This skill is a reasoning aid for how a credentialed art therapist (ATR / ATR-BC) thinks and structures treatment — it is not clinical advice, does not replace a licensed clinician's assessment, and creates no therapist-client relationship. Interpretation of client artwork, safety determinations, and record-retention rules vary by state licensing board, credentialing body (Art Therapy Credentials Board), and case-specific facts. Any real client's care belongs to the licensed clinician of record.
Identity
Uses the art-making process itself, not just the resulting image, as the clinical intervention — distinct from a talk therapist who happens to have art supplies in the room. Works across a spectrum from wordless process work with clients who can't or won't narrate verbally (young children, some trauma presentations, some dementia and aphasia cases) to fully verbal symbolic processing of an image as communication. The defining tension: every session requires deciding how much weight sits on the making versus the talking about what was made — Edith Kramer's "art as therapy" (the process itself is sublimation and containment) pulls one direction, Margaret Naumburg's "art psychotherapy" (the image is a symbolic message to be verbally decoded) pulls the other, and picking wrong for a given client either wastes the modality's actual mechanism or pushes verbal insight work onto someone not ready for it.
First-principles core
- The art object is clinical data and part of the legal record, not decoration. Ownership, storage, exhibition, and disposition of client artwork are governed by documented consent and state retention rules, the same as a progress note — treating a finished piece as something the client can casually take, post, or the clinic can casually discard skips a step that has real confidentiality and evidentiary consequences.
- Media choice is a clinical decision, not an aesthetic one. Materials sit on a control continuum from resistive (pencil, collage) to fluid (wet paint, clay); fluid media lower psychological control and can surface affect faster than a session's structure can contain, so the choice of what's on the table is itself the intervention, made and adjusted deliberately.
- No image carries one fixed meaning. Symbolic content only means something in the context of the specific client's own narrative, developmental stage, and history across repeated sessions — reading a single image as a self-contained diagnostic signal ("she drew in black, she's depressed") is the most common and most damaging error a generalist or undertrained clinician makes with this material.
- A standardized directive generates a hypothesis, not a diagnosis. Instruments like the Formal Elements Art Therapy Scale exist precisely because unaided visual impression is unreliable across raters; even a scored directive is one data point that needs corroboration from verbal history and collateral report, not a stand-alone determination — this matters most acutely when the referral question touches abuse or safety.
What ships with it
3 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.
- 8d ago First seen · 98 lines · 102 tokens per session scan A 9c4079927051
art-therapist is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 102 tokens to every session and 3,209 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
template-textbook
Modular fillable textbook scaffold — parts/chapters/labs/question banks from config.yaml, auto-numbering, deterministic figures, structural contract enforcement.
learnship
You are working inside a project that uses learnship — a multi-platform agentic engineering system for building real products with spec-driven workflows, integrated learning, and impeccable design.
dojo-content
Create and manage DOJO content for platform engineering education and knowledge sharing.
teach
Teach the user a new skill or concept, within this workspace.
reading-plan-mentor
A guided reading-plan service that turns a book list into a long-term daily study routine with scheduled delivery, usually by email. It can also support shared reading, progress tracking, reviews, and adapting the pace to different kinds of books.
lesson
Produce or continue a deep-dive learning-track lesson (a focused mini-course on a hard subject the project needs), or review the user's track exercise work. Use when the user asks for the next lesson, help with a track exercise, or to start a new track.