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 oaustegard/claude-skills --skill informed-patientgit clone --depth 1 https://github.com/oaustegard/claude-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/oaustegard/claude-skills/informed-patient)<a href="https://agentmods.dev/skills/oaustegard/claude-skills/informed-patient"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/informed-patient/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/oaustegard/claude-skills/informed-patient"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/informed-patient.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 | $0.00061 | $0.01795 |
| Opus 5 | $0.00030 | $0.00898 |
| Sonnet 5 | $0.00012 | $0.00359 |
| Haiku 4.5 | $0.00006 | $0.00179 |
Grade A, and why
informed-patient 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 2d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Informed Patient
Turns a user's own health experience into a document they can hand to a clinician: a structured symptom picture, a mini literature review with quality-tagged sources, competing hypotheses, and questions they picked themselves. The user shows up to the appointment with organized thinking and sharper questions.
Written for people developing an understanding of new or persistent symptoms, people mid-diagnostic-journey, people evaluating the evidence behind a diagnosis they already have, and people who want to track symptoms systematically enough to communicate them well.
Without guardrails, AI-assisted medical searching produces anchoring on one hypothesis, overgeneralization from thin evidence, no source quality control, and no awareness of understudied conditions or evidence that has shifted over time. The structure below exists to counter those four failure modes.
Attribution
Written by Cat Hicks (github.com/DrCatHicks/informed-patient), CC BY 4.0
(https://creativecommons.org/licenses/by/4.0/). Changed from upstream: the
single 34KB SKILL.md was split into a resident core and per-phase references
loaded on demand. Procedure text is upstream's, verbatim. Full licence in
LICENSE.txt.
Scope
In: physical health conditions, evidence evaluation, symptom organization, appointment preparation.
Out: mental-health self-diagnosis or therapy, emotional processing, acute emergencies (direct to 911/emergency services), treatment decisions.
You can assess the research evidence behind a treatment. Do not recommend one. Direct the user toward a specific actionable question about it instead.
When a user expresses distress, acknowledge it in one sentence and continue the structured work. Doing the work with them is itself the support. Do not therapize.
Rules that hold in every phase
These are resident because a phase reference that fails to load must not take a guardrail with it.
- Do not diagnose. "I can help you organize your thinking and evaluate evidence, but I can't tell you what you have."
- Do not recommend treatments. The decision is between the user and their medical team.
- Do not replace clinicians. The goal is a better-prepared appointment, not a resolution reached alone.
- Do not assess mental health. If psychological symptoms are part of the clinical picture, note the connection for the medical team and move on.
- Citation integrity. Every source in the artifact carries the URL the search tool actually returned. Never reconstruct a PMID or DOI from memory. No verifiable URL — describe the source and flag that the link could not be retrieved. Do not cite anything you did not retrieve.
- Absence of evidence is a finding. A thin search result gets reported explicitly and prominently. A source type that returned nothing gets reported too — a null result from Cochrane or AHRQ is itself evidence about the condition.
- Do not resolve contested evidence. Name the disagreement, present both sides, hand it to the clinician as a question.
- Say when you don't know. Do not fill the gap with speculation.
- The artifact is a file. Rendering it in the conversation only does not count as delivering it.
What ships with it
11 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.
- CHANGELOG.md 427 B
- LICENSE.txt 18 KB
- README.md 3.5 KB
- references/evidence-hierarchy.md 11 KB
- references/literature-search-strategy.md 5.0 KB
- references/output-template.md 5.0 KB
- references/phase-1-interview.md 6.3 KB
- references/phase-2-search.md 12 KB
- references/phase-3-evaluation.md 6.2 KB
- references/red-flags.md 8.5 KB
- references/symptom-inventory-methodology.md 13 KB
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.
- 2d ago Changed · +3 lines 4180e3b067cb
- 4d ago First seen · 170 lines · 61 tokens per session scan A f822f57a38e1
informed-patient is a skill published in the GitHub repository oaustegard/claude-skills (148 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 1,795 once invoked, about $0.0003 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 2026-09-08.
Other skills, from other repositories
superdesign
Design or redesign frontend UI, presentations, and graphics on the Superdesign canvas with a choice of leading AI models. Use whenever the user wants to design a page, feature, flow, slide deck, or brand-new product; improve or reproduce existing UI; compare design results across top models; explore visual variants…
Linear
Managing Linear issues, projects, and teams. Use when working with Linear tasks, creating issues, updating status, querying projects, or managing team workflows.
chanlun-engine-skill
A Chinese-language stock-analysis skill based on Chan theory, a method for interpreting price-chart structures such as turning points and trading ranges.
youtube-summary
Summarize a YouTube video into structured notes — TL;DR, key takeaways, chapter-by-chapter breakdown, and reference links. Use when the user shares a YouTube URL (or invokes /youtube-summary ) and wants a summary, takeaways, transcript notes, or a write-up of a talk, lecture, or tutorial. Fetches the transcript and…
plangate
Use for any non-trivial task with 2+ open decisions/tradeoffs OR multiple implementation steps — instead of deliberating one question at a time in chat, write a structured plan to a file and let the user review it inline in vim with > Q: / > A: blockquote markers, then revise until agreed before touching any code.…
coinmarketcap
Expert assistant for CoinMarketCap Pro API — price quotes, listings, historical OHLCV, market metrics, Fear & Greed Index, CMC100/CMC20 indices, exchange data, DEX data, airdrops, trending, community sentiment. Covers 10+ endpoint categories across REST + MCP + x402 pay-per-call modes. Use when the user wants: current…