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/romeo111/openonco/claude-mdgit clone --depth 1 https://github.com/romeo111/OpenOncoWrote 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/romeo111/openonco/claude-md)<a href="https://agentmods.dev/instructions/romeo111/openonco/claude-md"><img src="https://agentmods.dev/badge/instructions/romeo111/openonco/claude-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 | $0.03324 | $0.03324 |
| Opus 5 | $0.01662 | $0.01662 |
| Sonnet 5 | $0.00665 | $0.00665 |
| Haiku 4.5 | $0.00332 | $0.00332 |
Grade A, and why
OpenOnco 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 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) and similar AI agents (Codex, etc.) when working in this repository. Read this file in full at the start of every session.
Project: OpenOnco
Free public resource for oncology clinical decision support. User uploads a patient profile → receives two alternative treatment plans (standard + aggressive) with full source citations. Plans refresh as new data arrives (new labs, doctor decisions, updated guidelines).
Status: v0.1 draft. KB expansion waves GI-2, GI-3, PUL, HEME-1 complete (2026-05-09). CIViC-primary actionability pivot phases 2-5 still pending. Rule engine + render in progress.
Source of truth hierarchy
When instructions conflict, obey this order:
specs/CHARTER.md— project governance + scope- Other
specs/*.md— clinical, data, schema, source, reference case - This
CLAUDE.md README.md- Anything under
legacy/— not authoritative; historical reference only
legacy/ contains the pre-OpenOnco autoresearch pipeline. Retired (not
deleted) because the LLM-ranks-treatments pattern conflicts with CHARTER
§8.3. Don't use it as a pattern for new work.
Repo layout (top level)
cancer-autoresearch/
├── specs/ # active specifications (UA)
├── knowledge_base/
│ ├── clients/ # SourceClient implementations
│ │ ├── ctgov_client.py # ClinicalTrials.gov v2
│ │ ├── pubmed_client.py
│ │ ├── dailymed_client.py
│ │ ├── openfda_client.py
│ │ └── translate_client.py
│ ├── engine/ # rule engine + render + MDT
│ │ # actionability_{types,client,extract,conflict}.py
│ ├── schemas/ # Pydantic entity schemas
│ ├── validation/ # YAML loader + validators
│ ├── ingestion/ # МОЗ extractor, civic_loader.py, ...
│ └── hosted/
│ ├── content/ # KB YAML data (diseases, regimens, RFs, …)
│ └── civic/<date>/ # CIViC nightly snapshot (CC0)
├── docs/ # built site (openonco.info) + reviews/
├── scripts/ # build_site.py, fill scripts, coverage tools
├── tests/ # pytest suite
├── legacy/ # retired autoresearch pipeline (not authoritative)
├── README.md
└── CLAUDE.md
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 · 275 lines · 3,324 tokens per session scan A 4ae1d01bddf2
OpenOnco CLAUDE.md is an instructions file published in the GitHub repository romeo111/OpenOnco (2 stars, last pushed yesterday), licensed MIT. It adds 3,324 tokens to every session, about $0.0166 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
openscreen AGENTS.md
AGENTS.md instructions for getopenscreen/openscreen, covering agents.md, setup commands, development principles, project layout and code style.
commonly CLAUDE.md
Claude Code instructions for Team-Commonly/commonly, covering claude.md / agents.md, 🧠 product vision & architecture philosophy, what commonly is, the architecture model and key concepts.
Claw3D AGENTS.md
Instructions for iamlukethedev/Claw3D, covering agent instructions, cursor cloud specific instructions, service overview, running the app and lint, typecheck, and tests.
claude-ads CLAUDE.md
Instructions for AgriciDaniel/claude-ads, covering claude ads repository instructions, architecture, development and verification.
openstatus AGENTS.md
AGENTS.md instructions for openstatusHQ/openstatus, covering agents.md, verify your change, toolchain, architecture and tests.
windmill AGENTS.md
AGENTS.md instructions for windmill-labs/windmill, covering windmill, workflow, documentation, dev environment and per-worktree ports and database.