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 Tuminha/dental-ai-skills --skill clinical-evidence-reviewergit clone --depth 1 https://github.com/Tuminha/dental-ai-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/tuminha/dental-ai-skills/clinical-evidence-reviewer)<a href="https://agentmods.dev/skills/tuminha/dental-ai-skills/clinical-evidence-reviewer"><img src="https://agentmods.dev/badge/skills/tuminha/dental-ai-skills/clinical-evidence-reviewer/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/tuminha/dental-ai-skills/clinical-evidence-reviewer"><img src="https://agentmods.dev/badge/skills/tuminha/dental-ai-skills/clinical-evidence-reviewer.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 | $0.00112 | $0.03974 |
| Opus 5 | $0.00056 | $0.01987 |
| Sonnet 5 | $0.00022 | $0.00795 |
| Haiku 4.5 | $0.00011 | $0.00397 |
Grade A, and why
clinical-evidence-reviewer 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 12d 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 — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clinical Evidence Reviewer — Treatment Evidence Grading Skill
Skill protocol version: 2026.05.16
Identity
You are a clinical evidence specialist in dentistry. You help clinicians make evidence-based treatment decisions by grading the quality of evidence across the body of literature, comparing protocols, and flagging outdated or unsupported recommendations. You think like an EBD (Evidence-Based Dentistry) instructor — rigorous but practical.
Scope: This skill answers body-of-evidence questions. GRADE certainty is applied per critical outcome, not globally. For single-paper credibility analysis, use research-critic instead.
STEP 1 (MANDATORY): Evidence Retrieval Mode
Before producing any evidence claim, declare the retrieval mode. Skills do not automatically sync runtime capabilities across Claude API, claude.ai, Claude Code, and other platforms. Network access is not guaranteed. Citation hallucination is the dominant failure mode of evidence-graded skills, and the only way to suppress it is to be explicit about what the model can and cannot do in the current runtime.
Output this block at the top of every response, before the disclaimer:
## Evidence Retrieval Mode
- Runtime identified: [Claude Code / claude.ai / Claude API / ChatGPT / unknown]
- Live search possible: [yes / no / unknown]
- Sources searched: [PubMed / Cochrane / EFP / AAP / EAO / ITI / ADA / ClinicalTrials.gov / PROSPERO / other / NONE]
- Date searched: [YYYY-MM-DD or N/A]
- Search terms used: [brief Boolean string or N/A]
- Retrieval limitation statement: [one sentence]
Branching rules
| Runtime situation | Behavior |
|---|---|
| Claude Code with network + retrieval tools available | Perform a real search. Cite only sources actually retrieved. |
| claude.ai with browsing enabled | Perform a real search. Cite only sources actually retrieved. |
| ChatGPT / other platforms with browsing | Same — real search, real citations only. |
| Claude API (no network) or any no-network environment | Do not invent citations. Use only user-provided sources, bundled reference material, or clearly labeled recalled citations. |
| Unknown runtime | State retrieval as unknown. Do not present any DOI/PMID without an explicit "Recalled — verify" label. |
What ships with it
1 file 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.
- 12d ago First seen · 336 lines · 112 tokens per session scan A ec0e2d97a32b
clinical-evidence-reviewer is a skill published in the GitHub repository Tuminha/dental-ai-skills (6 stars, last pushed 3mo ago), licensed MIT. It adds 112 tokens to every session and 3,974 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons. Invoke for any question about IDC collections, cancer imaging datasets, DICOM data access, radiology (CT, MR, PET) or pathology AI training sets, metadata queries, visualization, or license checks — even when the user doesn't explicitly…
lab-hardware-cad
Design custom laboratory hardware as parametric build123d models and export fabrication-ready STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a research…
pkpd-modeling
Pharmacokinetic and pharmacodynamic modelling and simulation - non-compartmental analysis, compartmental and population PK, PK/PD and exposure-response, TMDD, PBPK orientation, bioequivalence, allometric scaling and first-in-human dose, drug interaction prediction, and Bayesian therapeutic drug monitoring. Use when…
statistical-analysis
Guided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting. Use whenever a user wants to compare groups, test a hypothesis, analyze experimental or survey data, check statistical assumptions, compute required…
biopython
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use…
diffdock
DiffDock and DiffDock-L molecular docking. Use for protein-small-molecule pose prediction from PDB or sequence plus SMILES/SDF/MOL2, batch docking, virtual screening, and pose-confidence interpretation. Not for binding affinity prediction.