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 inflexa-ai/inflexa --skill drug-repurposinggit clone --depth 1 https://github.com/inflexa-ai/inflexaWrote 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/inflexa-ai/inflexa/drug-repurposing)<a href="https://agentmods.dev/skills/inflexa-ai/inflexa/drug-repurposing"><img src="https://agentmods.dev/badge/skills/inflexa-ai/inflexa/drug-repurposing/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/inflexa-ai/inflexa/drug-repurposing"><img src="https://agentmods.dev/badge/skills/inflexa-ai/inflexa/drug-repurposing.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 | $0.00030 | $0.02171 |
| Opus 5 | $0.00015 | $0.01086 |
| Sonnet 5 | $0.00006 | $0.00434 |
| Haiku 4.5 | $0.00003 | $0.00217 |
Grade A, and why
drug-repurposing 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 yesterday.
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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drug Repurposing
This skill guides systematic identification of existing drugs for new therapeutic indications using computational methods. Covers signature- based, target-based, network-based, and genetics-based approaches.
Strategy Selection Decision Tree
Choose the repurposing strategy based on available data:
-
Signature-based repurposing (have: disease DE signature)
- Query a disease transcriptomic signature against drug perturbation profiles (CMap-style connectivity scoring).
- Drugs that REVERSE the disease signature are therapeutic candidates. Drugs that MIMIC it may exacerbate.
- See
references/repurposing-methods.mdfor connectivity scoring with gseapy.prerank and permutation testing. - Input: ranked gene list from DE analysis (sign(log2FC) * -log10(pvalue)), plus a set of drug perturbation profiles.
- Reference-data caveat: a drug-perturbation signature collection is in the reference inventory as an opt-in download, so resolve it up front and expect it may not be staged. It arrives as directional gene sets — one up set and one down set per experiment — and connectivity is the difference between their two enrichment scores, so pair them by their shared term prefix and never score one alone. Failing that, search the workspace for staged perturbation data. If neither is present, say so and switch to a target-, network-, or genetics-based strategy — do not invent a signature path, and do not substitute drug-target gene sets for perturbation profiles and still call the output a connectivity score.
- Output: ranked drugs by connectivity score with FDR.
-
Target-based repurposing (have: validated target gene list)
- Map disease-relevant targets to known drugs via ChEMBL, DrugBank, and Open Targets.
- Workflow: a. Resolve gene symbols to ChEMBL target identifiers. b. Find compounds with bioactivity against each of those targets. c. Check approval status and existing indications for each drug. d. Verify the mechanism of action is relevant to the disease. e. Where DrugBank lookup is available, add indication, interaction, and pharmacology data.
- Prioritize: approved drugs > Phase 3 > Phase 2 > Phase 1 > preclinical.
- Flag drugs already indicated for the target disease (not repurposing candidates).
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.
- yesterday First seen · 210 lines · 30 tokens per session scan A 147fc97945d2
drug-repurposing is a skill published in the GitHub repository inflexa-ai/inflexa (33 stars, last pushed today), licensed Apache-2.0. It adds 30 tokens to every session and 2,171 once invoked, about $0.0002 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 2026-09-09.
Other skills, from other repositories
biosymphony-structure-factory
Use when planning structural biology campaigns, binder-design triage, model comparison, structure mapping, RunPod or cloud GPU stage contracts, or Symphony or Linear task packs for long-running biological agent work.
binder-lane-round
Plan and run study-shaped protein-binder rounds with interchangeable toolchains, execution profiles, license gates, output checks, and result boundaries.
chem-tools
Computational chemistry workflow guide for DeepChem, PySCF, RDKit, assay-table normalization, PDBbind-style structure datasets, QSAR and structure benchmarks, DrugBank lookup, ligand-only and structure-aware affinity prediction, ADMET triage, bioactivity prediction, virtual screening, and docking follow-up.
docking-tools
Molecular docking workflow guide and reusable pipeline template for AutoDock Vina, Open Babel, and PyMOL.
bio-tools
Bioinformatics workflow guide for sequence analysis, QC, plotting, structure rendering, and literature search.
pharma-db-tools
Query public drug-discovery and translational-research databases including PubChem, ChEMBL, BindingDB, openFDA, ClinicalTrials.gov, and OpenAlex. Use when the user asks to look up compounds, measured binding affinities, regulatory labels or adverse events, clinical trials, or drug-discovery literature from public APIs…