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 translational-safetygit 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/translational-safety)<a href="https://agentmods.dev/skills/inflexa-ai/inflexa/translational-safety"><img src="https://agentmods.dev/badge/skills/inflexa-ai/inflexa/translational-safety/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/translational-safety"><img src="https://agentmods.dev/badge/skills/inflexa-ai/inflexa/translational-safety.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 | $0.00033 | $0.03040 |
| Opus 5 | $0.00016 | $0.01520 |
| Sonnet 5 | $0.00007 | $0.00608 |
| Haiku 4.5 | $0.00003 | $0.00304 |
Grade A, and why
translational-safety 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Translational Safety
This skill guides safety assessment for translational medicine, covering computational toxicology, safety biomarker interpretation, and adverse event classification.
CTCAE v5 Grading (Common Terminology Criteria for Adverse Events)
When clinical or laboratory safety data includes adverse event severity, use CTCAE v5 grading:
| Grade | Description | Clinical Action |
|---|---|---|
| 1 | Mild; asymptomatic or mild symptoms | Observation only |
| 2 | Moderate; minimal intervention indicated | Outpatient management |
| 3 | Severe; hospitalization indicated | Dose modification/interruption |
| 4 | Life-threatening | Urgent intervention |
| 5 | Death related to AE | — |
When grading lab values:
Hepatotoxicity (Drug-Induced Liver Injury)
- ALT/AST: Grade 1: >ULN–3x ULN, Grade 2: 3–5x ULN, Grade 3: 5–20x ULN, Grade 4: >20x ULN
- Total bilirubin: Grade 1: >ULN–1.5x ULN, Grade 2: 1.5–3x ULN, Grade 3: 3–10x ULN, Grade 4: >10x ULN
- Hy's Law: ALT >3x ULN AND bilirubin >2x ULN (without ALP >2x ULN) — high risk of fatal DILI
- RUCAM score: Use to assess causality (drug vs other cause)
Nephrotoxicity
- Creatinine: Grade 1: >ULN–1.5x baseline, Grade 2: 1.5–3x baseline, Grade 3: 3–6x baseline, Grade 4: >6x baseline
- eGFR: Monitor trend; acute decline >25% is concerning
- Proteinuria: Grade 1: +1, Grade 2: +2–3, Grade 3: nephrotic range
Cardiotoxicity
- Troponin: Any elevation above ULN warrants investigation
- LVEF: Grade 1: asymptomatic decline, Grade 2: <50% or decline >10%, Grade 3: symptomatic CHF
- QTc prolongation: Grade 1: 450–480ms, Grade 2: 481–500ms, Grade 3: >500ms or >60ms increase
Hematological Toxicity
- Neutrophils: Grade 1: <LLN–1500, Grade 2: 1000–1500, Grade 3: 500–1000, Grade 4: <500
- Platelets: Grade 1: <LLN–75000, Grade 2: 50000–75000, Grade 3: 25000–50000, Grade 4: <25000
Safety Target Panel Quick Lookup
A curated secondary-pharmacology off-target safety panel (~30 well-established liability targets, organ-tagged) is available to you. Use it as a fast first-pass screen before reaching for live tools.
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.
- 2d ago First seen · 256 lines · 33 tokens per session scan A 867ed7ffb74b
translational-safety is a skill published in the GitHub repository inflexa-ai/inflexa (33 stars, last pushed yesterday), licensed Apache-2.0. It adds 33 tokens to every session and 3,040 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
drug-drug-interaction-analysis
Analyze potential drug-drug interactions (DDI) for up to 5 drugs using KEGG DDI database. Use this skill when: (1) Checking interactions between multiple medications, (2) Assessing DDI risk for drug combinations, (3) Understanding interaction mechanisms and severity, (4) Analyzing CYP enzyme involvement in DDIs.
precision-bio-tests
Expert guide for testing bioinformatics MCP servers. Covers pytest, DRYRUN modes, and PatientOne simulation scenarios.
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.
precision-bio-docs
Expert guide for project-specific documentation and clinical reporting. Maintains consistency across persona-based guides and automated reports.
patient-data-ops
Guide for managing patient data and bioinformatics datasets (h5ad, CSV). Standardizes data loading, preprocessing, and path management.