Scientific Agent Skills is a collection of reusable procedures that give AI agents capabilities for scientific research across areas such as biology, chemistry, medicine, and drug discovery. It is used by researchers and by people building AI scientist workflows with compatible coding agents. The catalogue contains many of the project's skills and supporting instructions.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/K-Dense-AI/scientific-agent-skillsnpx agentmods add skills/k-dense-ai/scientific-agent-skills/treatment-plansWrote 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/k-dense-ai/scientific-agent-skills/treatment-plans)<a href="https://agentmods.dev/skills/k-dense-ai/scientific-agent-skills/treatment-plans"><img src="https://agentmods.dev/badge/skills/k-dense-ai/scientific-agent-skills/treatment-plans/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/k-dense-ai/scientific-agent-skills/treatment-plans"><img src="https://agentmods.dev/badge/skills/k-dense-ai/scientific-agent-skills/treatment-plans.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 91 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00062 | $0.02525 |
| Opus 5.5 | $0.00025 | $0.01010 |
| Sonnet 5.5 | $0.00012 | $0.00505 |
| Haiku 4.5 | $0.00006 | $0.00252 |
Grade A, and why
treatment-plans 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 26d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- treatment-plans — 100% identical, 25 lines differ
- treatment-plans — 89% identical, 25 lines differ
How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Treatment-Plan Documentation
Hard safety boundary
This skill only formats and validates documentation of decisions already made, supplied, and verified by authorized licensed professionals.
Never use it to:
- diagnose, assess, classify, or screen a person;
- select, rank, recommend, substitute, or compare therapies;
- choose a medication, dose, route, frequency, duration, or monitoring threshold;
- start, stop, hold, resume, titrate, taper, or deprescribe anything;
- check interactions, allergies, contraindications, organ-function suitability, or treatment eligibility;
- infer missing clinical content, intervals, dates, targets, escalation criteria, or instructions;
- triage, determine urgency, provide emergency advice, or create a safety plan;
- predict outcomes, prognosis, response, benefit, harm, or clinical appropriateness;
- replace medication reconciliation, pharmacist review, informed consent, clinician review, or an authorized clinical system;
- claim FDA approval, HIPAA compliance, legal compliance, completeness of care, clinical safety, or standard-of-care conformity.
If a request crosses a boundary, stop. Ask for a locally verified clinician-authored record or route the matter to the responsible licensed professional. Do not redirect to another skill to obtain a patient-specific recommendation.
If a concern may be urgent or emergent, stop this workflow and route it through the institution's current clinical escalation or emergency process. This skill does not decide urgency and does not provide emergency instructions.
Required visible notice
Every component and derived schedule must display:
DRAFT — NOT MEDICAL ADVICE — DOCUMENTATION-ONLY — AUTHORIZED CLINICIAN SIGN-OFF REQUIRED
Structural success never removes this notice. Only the authorized local workflow may set the release gate.
Data gate
Prefer synthetic or qualified de-identified structured manifests. Do not place patient names, medical-record numbers, contact details, dates of birth, addresses, free-text notes, images, or other direct identifiers in examples.
What ships with it
22 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.
- assets/clinician_authored_intervention_template.json 408 B
- assets/goals_monitoring_checkpoint_template.json 446 B
- assets/informed_preference_shared_decision_template.json 408 B
- assets/intended_use_handoff_template.json 2.9 KB
- assets/source_fact_manifest_template.json 381 B
- assets/transition_reconciliation_template.json 880 B
- references/documentation_workflow.md 7.5 KB
- references/privacy_governance.md 6.5 KB
- references/README.md 1.4 KB
- references/safety_scope.md 5.3 KB
- references/security_validation.md 5.6 KB
- references/shared_decision_handoff.md 5.5 KB
- references/source_boundaries.md 6.4 KB
- references/source_ledger.md 8.7 KB
- scripts/_common.py 40 KB runs code
- scripts/check_completeness.py 18 KB runs code
- scripts/check_consistency.py 12 KB runs code
- scripts/generate_template.py 3.7 KB runs code
- scripts/privacy_process_check.py 6.4 KB runs code
- scripts/timeline_generator.py 8.4 KB runs code
- scripts/validate_traceability.py 4.5 KB runs code
- scripts/validate_treatment_plan.py 2.5 KB runs code
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.
- 26d ago Changed · +11 lines ebb509854e12
- 27d ago Changed · +2 lines e712c8a74cf1
- 1mo ago First seen · 192 lines · 62 tokens per session scan A 9d806eb6556b
treatment-plans is a skill published in the GitHub repository K-Dense-AI/scientific-agent-skills (54,953 stars, last pushed 2d ago), licensed MIT. It adds 62 tokens to every session and 2,525 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 2026-09-03.
Other skills, from other repositories
meta-ad-policy-checker
Pre-flight policy check for Meta ads. Takes ad copy plus advertiser context, resolves and fetches the relevant Meta transparency-center policy pages at runtime, and returns a Pass / Fix Required / Block verdict with cited findings and rewrites.
claims-gate
Checks every claim in a piece of copy (ads, emails, posts, pages, scripts, briefs) against the claims the brand has approved. Keeps, rewrites or cuts each line, and lists the proof that would bring a cut line back. When a line the copy needs has no approval, it asks for a short sign-off on the 3 or 4 lines that matter…
ectd-xml-compiler
Automatically convert uploaded drug application documents (Word/PDF) into XML skeleton structure compliant with eCTD 4.0/3.2.2 specifications.
ad-policy-check
Checks paid ads against the ad platform's rules (Meta, TikTok, Google, LinkedIn and others) and the brand's category rules: the copy, on-image or on-screen text, pictures and people. Rewrites what can be fixed honestly, adds the disclosures that are needed, and flags anything that needs a human or legal review, with…
save-to-brain
Shared step of the marketing playbooks (research-market, plan-campaign, make-content, analyze-performance): saves a finished file to the brand and makes it searchable. It either replaces older versions or keeps dated history, then checks that the file can be found. Loaded by those playbooks; not for direct use.
email-lifecycle-send-check
Checks a drafted email flow or broadcast before it is loaded: flow logic and exits, overlaps, offer depth and codes, stock, claims, consent and legal footer, SMS rules, rendering, voice and AI-copy tells, and the goal metric. Returns a pass / fixed / open-question table. Use alone when you already have the finished…