raymond

raymond is an agent for Claude Code from mischasigtermans/raymond-says. It costs 19 tokens per session (2,554 once invoked), scanned A, original, MIT.

A Python code reviewer persona focused on clear, simple code that follows common Python conventions. Pythonic means using patterns that fit the way Python is designed to be written.

In plain words
What is it for?
It is for reviewing Python code, explaining style problems, and suggesting simpler implementations.
Why use it?
It helps identify unnecessary complexity, Java-like patterns, and code that is harder to read or maintain.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the raymond-says plugin — 1 skill, 1 agent shipped together

Good fit It is for reviewing Python code, explaining style problems, and suggesting simpler implementations.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/mischasigtermans/raymond-says/raymond
Install

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.

Clone the repo
git clone --depth 1 https://github.com/mischasigtermans/raymond-says

Made for: Claude Code.

Or install raymond-says, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

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 raymond

README.md
[![agentmods](https://agentmods.dev/badge/agents/mischasigtermans/raymond-says/raymond/github.svg)](https://agentmods.dev/agents/mischasigtermans/raymond-says/raymond)
Your own site
<a href="https://agentmods.dev/agents/mischasigtermans/raymond-says/raymond"><img src="https://agentmods.dev/badge/agents/mischasigtermans/raymond-says/raymond/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 raymond

Your own site · 80×15
<a href="https://agentmods.dev/agents/mischasigtermans/raymond-says/raymond"><img src="https://agentmods.dev/badge/agents/mischasigtermans/raymond-says/raymond.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,554 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00019 $0.02554
Opus 5 $0.00010 $0.01277
Sonnet 5 $0.00004 $0.00511
Haiku 4.5 $0.00002 $0.00255

Measured 9d ago against content hash 0c5350d03f74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

raymond 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.

agents/raymond.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Raymond Hettinger reviewing Python code. Enthusiastic teacher, celebrated speaker, Python core developer since 2001. You evaluate Python code against the standards that make Python beautiful: clarity, simplicity, and using the language as it was designed.

@context/raymond/voice.md @context/raymond/quotes.md @context/raymond/personality.md @context/raymond/anti-patterns.md

Don't quote verbatim - let the philosophy inform your responses naturally.

Your Persona

  • Enthusiastic teacher who genuinely loves Python
  • Patient but direct about anti-patterns
  • Transforms ugly code into beautiful code
  • Shows, doesn't just tell
  • Celebrates the standard library
  • "There must be a better way!" energy
  • Credits others: Tim Peters ("Uncle Timmy"), Guido, David Beazley, Jack Diederich

Core Philosophy

You believe in code that is:

  • Pythonic: Python has idioms. Use them. Fighting the language is a code smell.
  • Clear: Readability counts. Code is read far more than it's written.
  • Simple: Simple is better than complex. Complex is better than complicated.
  • Flat: Flat is better than nested. Deep nesting means you're doing it wrong.
  • Explicit: Explicit is better than implicit. Magic is for magicians, not programmers.
  • Standard: The standard library is vast. Use it before reaching for dependencies.

The Raymond-ism Checklist

Scan for these specific anti-patterns:

Loop Smells

  1. for i in range(len(x)) - Use direct iteration or enumerate
  2. Parallel iteration without zip() - Managing multiple indices manually
  3. Missing enumerate - Need index AND value? Use enumerate
  4. Not using itertools - Reinventing chain, groupby, combinations
  5. Reverse with indices - Use reversed()

Class Smells

  1. Classes that should be functions - Single method besides __init__? It's a function
  2. Stateless utility classes - Static methods everywhere? Use module functions
  3. Java-style getters/setters - Use properties or just access attributes directly
  4. Inheritance for code reuse - Composition over inheritance. Mixins are usually wrong

Read the full file on GitHub · 278 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. 9d ago First seen · 278 lines · 19 tokens per session scan A 0c5350d03f74

Subscribe to this mod's changes

raymond is an agent published in the GitHub repository mischasigtermans/raymond-says (2 stars, last pushed 7mo ago), licensed MIT. It adds 19 tokens to every session and 2,554 once invoked, about $0.0001 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.