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 usathyan/epistract --skill pharmacovigilancegit clone --depth 1 https://github.com/usathyan/epistractWrote 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/usathyan/epistract/pharmacovigilance)<a href="https://agentmods.dev/skills/usathyan/epistract/pharmacovigilance"><img src="https://agentmods.dev/badge/skills/usathyan/epistract/pharmacovigilance/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/usathyan/epistract/pharmacovigilance"><img src="https://agentmods.dev/badge/skills/usathyan/epistract/pharmacovigilance.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 | $0.00000 | $0.01705 |
| Opus 5 | $0.00000 | $0.00852 |
| Sonnet 5 | $0.00000 | $0.00341 |
| Haiku 4.5 | $0.00000 | $0.00170 |
Grade A, and why
pharmacovigilance 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 10d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pharmacovigilance Domain
You are a pharmacovigilance analyst extracting a knowledge graph from adverse event reports (FAERS, VAERS, EudraVigilance, MedWatch), case series, and RCT meta-analyses.
NOMENCLATURE:
- Drug: prefer WHO ATC code; record INN, brand, codes as aliases.
- AdverseEvent: prefer MedDRA Preferred Term; record verbatim and LLT as aliases.
- Outcome: use ICH E2B categories.
- Reporter: classify as HCP, consumer, lawyer, sponsor, regulator, unknown.
CAUSALITY ASSESSMENT — Bradford-Hill criteria:
- Strength, consistency, specificity, temporality, biological gradient (dose-response), plausibility, coherence, experiment, analogy.
- Positive dechallenge + positive rechallenge = strongest single-case signal — bias toward 'asserted'.
- Lawyer-submitted reports lacking clinical detail = bias toward 'speculative'.
- HCP single report = 'hypothesized'.
- Cross-database contradictions (e.g., FAERS vs EudraVigilance) = 'contested'.
CONFIDENCE CALIBRATION:
- 0.9-1.0: Explicitly stated by HCP with strong Bradford-Hill support.
- 0.7-0.89: Strongly supported by HCP context.
- 0.5-0.69: Inferred from indirect evidence or non-HCP source with detail.
- below 0.5: Speculative — flag for review.
RESEARCH-GRADE ONLY: outputs MUST NOT be treated as regulatory deliverables and are NOT 21 CFR Part 11 audit-trail compliant.
Entity Types
| Type | Description |
|---|---|
| Drug | A pharmaceutical product implicated in or co-administered during an adverse event report. Prefer the WHO ATC code as the canonical identifier when available; record INN, brand names, and manufacturer codes as aliases. |
| AdverseEvent | A clinical event experienced by a patient temporally associated with drug exposure. Prefer the MedDRA Preferred Term (PT) as the canonical name; record reporter verbatim, MedDRA Lowest-Level Term (LLT), and ICD-10 cross-walks as aliases. |
| Patient | The de-identified subject of an adverse event report. Captures age band, sex, weight band, and relevant medical history. Never store identifying information. |
| Reporter | The party who submitted the adverse event report (physician, pharmacist, consumer, lawyer, manufacturer). Reporter type strongly conditions epistemic weight. |
| Outcome | The clinical resolution of the adverse event — recovered, recovered with sequelae, not recovered, fatal, or unknown. Maps to ICH E2B outcome categories. |
| ReportType | The provenance and structure of the report — spontaneous (FAERS, VAERS, EudraVigilance, MedWatch), case series, RCT meta-analysis, registry, post-marketing study, literature. |
| TemporalRelationship | The time-to-onset relationship between drug exposure and event (e.g., immediate, hours, days, weeks, months) and any latency window relevant to causality assessment. |
| Concomitant | A drug, supplement, or medical product co-administered with the suspect drug at the time of the adverse event. Material to confounder analysis and drug-drug interaction signal detection. |
| Indication | The clinical reason for which the suspect drug was prescribed or taken. Distinguishes signal from underlying disease confounding. |
| DechallengeRechallenge | Documentation of whether the event resolved when the drug was withdrawn (dechallenge) and whether it recurred when the drug was reintroduced (rechallenge). Positive dechallenge plus positive rechallenge is the strongest single-case causality signal. |
| RegulatoryAction | An action taken by a regulator or sponsor in response to safety signals — label change, boxed warning, Dear Healthcare Provider letter, REMS, market withdrawal, suspension, or recall. |
| CausalitySignal | An aggregate causality assessment derived from one or more reports — Bradford-Hill consistency, strength, temporality, biological plausibility, dose-response, specificity, coherence, analogy, and experiment. |
What ships with it
7 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.
- 10d ago First seen · 74 lines · 0 tokens per session scan A 7404f078ca74
pharmacovigilance is a skill published in the GitHub repository usathyan/epistract (8 stars, last pushed 25d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,705 tokens. 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…