Marvin is a Python framework for producing structured data with language models and coordinating tasks carried out by specialized AI agents. Developers use it to extract, cast, classify, or generate data and to compose observable agentic workflows. The catalogue includes an instruction and an agent for working with Marvin.
Borrowing it
Nothing to install: this file belongs to PrefectHQ/marvin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/PrefectHQ/marvin/main/CLAUDE.mdgit clone --depth 1 https://github.com/PrefectHQ/marvinWrote 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/prefecthq/marvin/claude-md)<a href="https://agentmods.dev/instructions/prefecthq/marvin/claude-md"><img src="https://agentmods.dev/badge/instructions/prefecthq/marvin/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.
<a href="https://agentmods.dev/instructions/prefecthq/marvin/claude-md"><img src="https://agentmods.dev/badge/instructions/prefecthq/marvin/claude-md.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 | $0.00242 | $0.00242 |
| Opus 5.5 | $0.00097 | $0.00097 |
| Sonnet 5.5 | $0.00048 | $0.00048 |
| Haiku 4.5 | $0.00024 | $0.00024 |
Grade A, and why
marvin 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 9d 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.
What it actually says
Working on Marvin
Use uv for dependencies and Python commands. Use X | Y, built-in collection types, and type annotations for new Python code.
uv sync
uv run pytest tests/basic
uv run pre-commit run --all-files
tests/basic does not call LLM providers. tests/ai makes real model requests. Set MARVIN_HOME_PATH to a temporary directory when testing so database and memory tests do not use local data.
The Slack bot is a separate workspace package under examples/slackbot; read its instructions before changing it. Library work should not require bot dependencies or changes to its deployment.
Edit handwritten documentation in docs/. API reference pages are generated from Python signatures and docstrings:
uv run scripts/create_mintlify_api_ref.py
Run the generator after source documentation changes. Keep examples executable, describe actual return types, and check claims against the implementation. Generated examples are not evidence that an API exists.
Use the ignored repros/ directory for issue reproductions. Public API changes, dependency migrations, and release procedures need their own review; keep cleanup changes focused.
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.
- 9d ago Changed · -24 lines · -220 tokens per session fa26db6e6bfb
- 2mo ago First seen · 48 lines · 462 tokens per session scan A 6be3ef99cdcf
marvin CLAUDE.md is an instructions file published in the GitHub repository PrefectHQ/marvin (6,206 stars, last pushed 5d ago), licensed Apache-2.0. It adds 242 tokens to every session, about $0.0010 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 2026-08-30.
marvin CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| marvin CLAUDE.mdPrefectHQ/marvin | Instructions file | 6.2k | 5d ago | Apache-2.0 | A | 242 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |