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 agentmods add instructions/aizech/clinical-skills/agents-mdgit clone --depth 1 https://github.com/aizech/clinical-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/instructions/aizech/clinical-skills/agents-md)<a href="https://agentmods.dev/instructions/aizech/clinical-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/aizech/clinical-skills/agents-md.svg" alt="Measured on agentmods" 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 | $0.01574 | $0.01574 |
| Opus 5 | $0.00787 | $0.00787 |
| Sonnet 5 | $0.00315 | $0.00315 |
| Haiku 4.5 | $0.00157 | $0.00157 |
Grade A, and why
clinical-skills AGENTS.md 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 5d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidelines for AI agents working in this repository. For contributing guidelines, see CLAUDE.md.
Repository Overview
- Name: Clinical Skills
- GitHub: aizech/clinical-skills
- Creator: Corpus Analytica
- Focus: Radiological Analytics
- License: MIT
- Version: 1.0.1 (2026-04-04)
- Status: 26 skills, 30+ integration docs, 12 CLI tools, 85 tests
Repository Structure
clinical-skills/
├── .claude-plugin/
│ └── marketplace.json # Plugin marketplace manifest
├── skills/ # Agent Skills (26 skills)
│ ├── core/ # Foundational skills
│ ├── clinical-documentation/
│ ├── patient-communication/
│ ├── workflow-coordination/
│ ├── analytics-quality/
│ ├── research-evidence/
│ ├── platform-integration/
│ ├── ai-assistants/
│ └── dataset/
├── tools/
│ ├── integrations/ # 30+ platform integration docs
│ ├── clis/ # 12 Python CLI tools
│ │ ├── shared/ # Shared utilities (base_cli, api_client, json_formatter)
│ │ └── tests/ # Comprehensive test suite (85 tests)
├── docs/ # Development documentation
│ ├── DEVELOPMENT.md
│ ├── TROUBLESHOOTING.md
│ ├── WORKFLOW_EXAMPLES.md
│ ├── CLI_API.md
│ └── DOCKER.md
├── scripts/ # Validation scripts
└── .github/ # GitHub config (5 workflows including CLI tests)
Skill Categories
| Category | Skills |
|---|---|
| Core | modality-detection, radiology-context |
| Clinical Documentation | radiology-report-analysis, structured-reporting, imaging-study-review |
| Patient Communication | patient-results-letter, patient-education-material |
| Workflow Coordination | imaging-referral, followup-tracking, care-gap-closure |
| Platform Integration | pacs-workflow, pubmed-search, dicom-web-query |
| AI Assistants | ai-report-assist, ai-detection-pipeline, llm-radiology-use, ai-quality-review |
| Analytics Quality | radiology-metrics, image-quality-audit, report-quality-review |
| Research Evidence | guideline-integration, cross-reference-linking, radiology-research |
| Dataset | radiology-dataset-guide, dataset-preprocessing, model-validation |
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.
- 5d ago First seen · 198 lines · 1,574 tokens per session scan A 1f9578943617
clinical-skills AGENTS.md is an instructions file published in the GitHub repository aizech/clinical-skills (4 stars, last pushed 2mo ago), licensed MIT. It adds 1,574 tokens to every session, about $0.0079 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 instructions, from other repositories
codex-autoresearch AGENTS.md
Instructions for TheGreenCedar/codex-autoresearch, covering agents.md, purpose and scope, canonical sources, stable product boundaries and source and package boundaries.
llm-wiki AGENTS.md
Instructions for BogdanovychA/llm-wiki, covering інструкції для агентів: хранитель llm wiki, 1. структура каталогів, 2. загальні конвенції, 3. шаблони сторінок та стандарти форматування and назви файлів.
arandu CLAUDE.md
Instructions for vdittgen/arandu, covering arandu, architecture, top-level packages, commands and coding standards.
nbp-skillforge AGENTS.md
Instructions for nbpadilha/nbp-skillforge, covering agents.md, what this is, the one rule that matters, before you finish a change and conventions.
openlegion CLAUDE.md
Claude Code instructions for openlegion-ai/openlegion, covering claude.md — engine, commands & testing, git workflow, work patterns and architecture.
Attest CLAUDE.md
Instructions for Cyrus580529/Attest, covering attest 开发规则, 一、架构红线（永不违反）, 二、开发流程（按改动大小裁剪，别一刀切）, 二·五、评测纪律（用户定调，2026-07-03；能力校准 2026-07-04） and 三、测试与验收（最重要的教训）.