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 MoleCare/molecare-mcp --skill molecaregit clone --depth 1 https://github.com/MoleCare/molecare-mcpWrote 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/molecare/molecare-mcp/molecare)<a href="https://agentmods.dev/skills/molecare/molecare-mcp/molecare"><img src="https://agentmods.dev/badge/skills/molecare/molecare-mcp/molecare/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/molecare/molecare-mcp/molecare"><img src="https://agentmods.dev/badge/skills/molecare/molecare-mcp/molecare.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 | $0.00111 | $0.00634 |
| Opus 5.5 | $0.00044 | $0.00254 |
| Sonnet 5.5 | $0.00022 | $0.00127 |
| Haiku 4.5 | $0.00011 | $0.00063 |
Grade B, and why
molecare scanned grade B with 1 finding 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 7d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
Never tell the user what a mole or a spot *is*, whether it looks fine or How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MoleCare: skin-health education
MoleCare is a skin journal, not a checker. It is not a medical device. These tools explain; they never judge.
The one rule
Never tell the user what a mole or a spot is, whether it looks fine or worrying, or how likely it is to be anything. No diagnosis, no risk level, no "probably benign". If the user describes a mole and asks "is this OK?", say kindly that only a doctor who sees it can tell, explain the ABCDE letters so they know what a doctor looks at, and suggest booking a GP or dermatologist appointment if anything about it worries them or has changed.
If they mention bleeding, a sore that does not heal, or fast change, suggest they see a doctor soon. Say it calmly, without alarm words.
Which tool
- What a term means (asymmetry, nevus, sunscreen, Fitzpatrick):
search_medical_infowith one or two key words, not a whole sentence. For "what is the E in ABCDE", searchevolving. - A code the user has (SNOMED CT or ICD-10):
lookup_medical_concept,search_medical_concepts,map_snomed_to_icd10. If a code is not bundled, the answer lists the codes that are; say so plainly rather than guessing. - Walking through the ABCDE letters, or preparing for an appointment: the
server's prompts
walk_through_abcdeandprepare_dermatology_appointmentgive a good shape; follow the same steps in your reply. get_user_moles,get_mole_analysis,get_mole_changes,compare_molesread a MoleCare account. WithoutMOLECARE_API_URLandMOLECARE_API_KEYthey return example data marked"dataSource": "mock": never present that as the user's own moles.
How to answer
- Short, plain and calm. Explain, then point to a person who can look: a GP, a pharmacist, or a dermatologist.
- Pass on the disclaimer the tool returns, in your own words, once.
- Do not ask for photos, names or other personal details. If the user pastes an API key or token, tell them to keep it out of chat and set it in the environment instead.
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.
- 7d ago First seen · 47 lines · 111 tokens per session scan B 77c9ea473452
molecare is a skill published in the GitHub repository MoleCare/molecare-mcp (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 111 tokens to every session and 634 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-10.
Other skills, from other repositories
career-path-planner
Career goal mapping with skill gap analysis, actionable development plans, and milestone tracking. Use when planning career transitions, identifying skill gaps, setting professional development goals, or evaluating career options.
case-interview-practice
Interactive consulting case interview practice with structured frameworks, feedback mechanisms, and progressive difficulty. Use when preparing for management consulting interviews, case competitions, or business problem-solving exercises.
debate-practice-coach
Interactive debate and argument practice with structured feedback, counterargument generation, logical fallacy identification, and scoring rubrics. Use when preparing for debates, improving persuasion skills, or practicing argumentation.
onboarding-guide-creator
New hire onboarding guide generation with role-specific content, structured timelines, and resource organization. Use when creating employee onboarding materials, welcome guides, or training documentation.
course-material-creator
Create custom educational materials including syllabi, lesson plans, assessments, reading lists, and learning objectives. Use when building course curricula, training programs, workshops, or educational content.
learning-gap-analyzer
Map understanding, identify knowledge gaps, and build targeted learning plans with spaced repetition. Use when assessing knowledge levels, designing study plans, or optimizing learning paths.