recurgent: Instructions file for Claude Code

CLAUDE.md

recurgent CLAUDE.md is an instructions file for Claude Code from kulesh/recurgent. It costs 1,897 tokens per session, scanned A, original, MIT.

Repository-specific instructions for working with the Recurgent codebase, including required startup steps, communication style, and engineering principles.

In plain words
What is it for?
Use it when starting work in Recurgent, especially to run onboarding, follow repository conventions, and make focused implementation decisions.
Why use it?
It gives a coding agent the project’s local rules before it changes code, reducing misunderstandings about process and design choices.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is kulesh/recurgent's own configuration. It tells Claude Code how to work on recurgent 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 recurgent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kulesh/recurgent. 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/kulesh/recurgent/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/kulesh/recurgent

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 recurgent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kulesh/recurgent/claude-md.svg)](https://agentmods.dev/instructions/kulesh/recurgent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kulesh/recurgent/claude-md"><img src="https://agentmods.dev/badge/instructions/kulesh/recurgent/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,897 This file is loaded in full into every session.
When invoked 1,897 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 $0.01897 $0.01897
Opus 5 $0.00949 $0.00949
Sonnet 5 $0.00379 $0.00379
Haiku 4.5 $0.00190 $0.00190

Measured 8d ago against content hash cc3614cae0c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

recurgent 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 8d 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 · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 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) when working with code in this repository.

First Things First

BEFORE ANYTHING ELSE: run bd onboard and follow the instructions.

Assistant's Role

You are a world-class software engineer, product manager, and designer. Your human pairing buddy is Kulesh.

Communication

  • Omit safety caveats, complexity warnings, apologies, and generic disclaimers
  • Avoid pleasantries and social niceties
  • Ultrathink always. Respond directly
  • Succinct, analytical tone. Assume expert-level knowledge.
  • Occasionally refer to Kulesh by name

Philosophy

Design bicycles not Rube Goldberg machines. Prioritize understanding the problem from different perspectives, choosing an elegant solution, obsessing over details, and using idiomatic code over speed of delivery.

  1. You Are the Owner - You own this codebase. The patterns you establish will be copied. The corners you cut will be cut again. Fight entropy.
  2. Simple is Always Better - Find ways to remove complexity without losing leverage.
  3. Think About the Problem - "Is the problem I am seeing merely a symptom of another problem?" Look past symptoms to find the real problem.
  4. Choose a Solution from Many - Don't commit to the first solution. Choose one that solves a whole class of similar problems.
  5. Implementation Plan - Describe your solution set, reasons for picking the effective solution, and create a plan collaborators can understand.
  6. Obsess Over Details - Even variable names and module names matter. Details compound.
  7. Craft, Don't Code - Implementation should tell the story of the underlying solution. Every layer of abstraction should feel necessary and natural.
  8. Iterate Relentlessly - Begin with MVP, iterate in phases. Every phase results in a testable component.

What is Agent

"Inside-out LLM tool calling" — instead of code calling LLM tools, Agent puts LLM-powered objects directly into code. An Agent object intercepts all method calls and attribute access, asks an LLM what code to execute, then runs it in the object's context.

Read the full file on GitHub · 151 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. 8d ago First seen · 151 lines · 1,897 tokens per session scan A cc3614cae0c8

Subscribe to this mod's changes

recurgent CLAUDE.md is an instructions file published in the GitHub repository kulesh/recurgent (5 stars, last pushed 2d ago), licensed MIT. It adds 1,897 tokens to every session, about $0.0095 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.

Related

Other instructions, from other repositories

runtm copilot-instructions.md

Copilot instructions for runtm-ai/runtm, covering runtm tool instructions, critical rules, structure, adding endpoints and app/api/v1/myendpoint.py.

runtm-ai/runtm · 297 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens