agentmods.dev

oncoteam: Instructions file for Claude Code

CLAUDE.md

oncoteam CLAUDE.md is an instructions file for Claude Code from peter-fusek/oncoteam. It costs 10,100 tokens per session, scanned A, original, MIT.

Project instructions for Oncoteam, a cancer-treatment management agent that searches medical studies, checks clinical-trial eligibility, and tracks treatment information. They describe the codebase, commands, and working rules.

In plain words
What is it for?
Use them when developing, testing, or running Oncoteam and its MCP server, dashboard, WhatsApp, agent, webhook, or administration features.
Why use it?
They give coding agents the project context needed to work consistently with its medical data, tests, services, and persistence system.

Instructions file for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: positional $N argument.

This is peter-fusek/oncoteam's own configuration. It tells Claude Code how to work on oncoteam itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything oncoteam configures →

not rated 6repo 6mo ago A scan 10,100 tokens original MIT
View source ↗ peter-fusek/oncoteam oncoteam.cloud
Reuse

Borrowing it

Nothing to install: this file belongs to peter-fusek/oncoteam. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/peter-fusek/oncoteam/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/peter-fusek/oncoteam

Made for: Claude Code.

Wrote 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.

agentmods badge for oncoteam CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/peter-fusek/oncoteam/claude-md/github.svg)](https://agentmods.dev/instructions/peter-fusek/oncoteam/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/peter-fusek/oncoteam/claude-md"><img src="https://agentmods.dev/badge/instructions/peter-fusek/oncoteam/claude-md/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.

agentmods 80×15 button for oncoteam CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/peter-fusek/oncoteam/claude-md"><img src="https://agentmods.dev/badge/instructions/peter-fusek/oncoteam/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10,100 This file is loaded in full into every session.
When invoked 10,100 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.10100 $0.10100
Opus 5.5 $0.04040 $0.04040
Sonnet 5.5 $0.02020 $0.02020
Haiku 4.5 $0.01010 $0.01010

Measured 2mo ago against content hash bb7836262492, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

oncoteam CLAUDE.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 2mo 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.

CLAUDE.md · 338 lines

How it starts

The opening of the file, as written. The whole thing — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.

oncoteam

Persistent AI agent for cancer treatment management. Searches PubMed and ClinicalTrials.gov, checks trial eligibility, tracks treatment data. All persistence goes through oncofiles MCP.

Quick start

uv sync --extra dev
uv run pytest          # 744 tests
uv run ruff check
uv run oncoteam-mcp    # stdio mode

Project structure

  • src/oncoteam/server.py — MCP server, 26 tools + dashboard API route registration, system instructions with biomarker rules + QA protocol
  • src/oncoteam/dashboard_api.py — Dashboard JSON API: clinical handlers (timeline, labs, protocol, patient, research, sessions, briefings, toxicity, medications, etc.) + shared infrastructure (auth, caching, rate limiting, CORS)
  • src/oncoteam/api_whatsapp.py — WhatsApp handlers: log, chat, resolve-patient, media, voice, history, status + thread memory + approved phones
  • src/oncoteam/api_agents.py — Agent/autonomous handlers: autonomous status/cost, agent list/config/runs, diagnostics
  • src/oncoteam/api_webhooks.py — Webhook handlers: bug-report, document-webhook, trigger-agent
  • src/oncoteam/api_admin.py — Admin handlers: patients, onboard-patient, approve-user, access-rights
  • src/oncoteam/api_research.py — Research handlers: research list, assess-funnel, funnel-stages GET/POST
  • src/oncoteam/request_context.py — Request-scoped utilities: correlation ID, patient token resolution (extracted to break circular imports)
  • src/oncoteam/clinical_protocol.py — Embedded clinical protocol: lab thresholds, reference ranges, dose mods, cumulative dose thresholds, cycle delay rules, nutrition escalation, milestones, safety flags, 2L options
  • src/oncoteam/autonomous.py — Claude API autonomous agent loop with extended thinking
  • src/oncoteam/autonomous_tasks.py — 24 autonomous task wrappers + document pipeline orchestrator with cooldown guards and WhatsApp notifications (count matches agent_registry.py; update both when adding agents)
  • src/oncoteam/agent_registry.py — AgentConfig Pydantic model, all 24 agent definitions + document_pipeline, schedule/cooldown/model config
  • src/oncoteam/tags.py — Canonical tag vocabulary with prefix:value format (sys:, clin:, bio:, tx:, res:, task:, safety:, src:)
  • src/oncoteam/activity_logger.py — @log_activity decorator, suppressed error buffer, diary helpers
  • src/oncoteam/eligibility.py — biomarker-aware trial eligibility checker
  • src/oncoteam/github_client.py — GitHub REST API for issue creation
  • src/oncoteam/clinicaltrials_client.py — ClinicalTrials.gov API v2
  • src/oncoteam/pubmed_client.py — PubMed/NCBI E-utilities
  • src/oncoteam/oncofiles_client.py — Oncofiles MCP client (StreamableHttpTransport)
  • src/oncoteam/patient_context.py — Patient profile, research terms, biomarker data
  • src/oncoteam/models.py — Pydantic models
  • src/oncoteam/config.py — Environment variable configuration
  • tests/ — pytest tests with respx mocks
  • landing/ — Static landing page (nginx, Railway). robots.txt, sitemap.xml, llms.txt, og-image.png
  • dashboard/ — Nuxt 4 dashboard (SSR, Railway). dashboard.oncoteam.cloud

Read the full file on GitHub · 338 lines

Changes

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.

  1. 2mo ago First seen · 338 lines · 10,100 tokens per session scan A bb7836262492

Subscribe to this mod's changes

oncoteam CLAUDE.md is an instructions file published in the GitHub repository peter-fusek/oncoteam (6 stars, last pushed 6mo ago), licensed MIT. It adds 10,100 tokens to every session, about $0.0404 per session on Opus 5.5. 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.

Building agentsanthropicclinical-trialsfastmcpmcpmedicaloncology
Related

oncoteam CLAUDE.md compared with instructions from other repositories

oncoteam CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
oncoteam CLAUDE.mdpeter-fusek/oncoteamInstructions file66mo agoMITA10,100Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot