What is claude-code-savant CLAUDE.md?

A set of development instructions for a Claude Code plugin containing specialist AI personas and a web chat interface. It documents the project's agents, server files, routing rules, and development workflow.

Use it when developing or maintaining the plugin, especially its personas, smart router, web server, chat interface, or slash commands.

It gives contributors a shared reference for how the plugin is organised and how its parts fit together. This reduces guesswork when modifying the project.

How rlaope/claude-code-savant configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to rlaope/claude-code-savant. 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/rlaope/claude-code-savant/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/rlaope/claude-code-savant

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/rlaope/claude-code-savant/claude-md/github.svg)](https://agentmods.dev/instructions/rlaope/claude-code-savant/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/rlaope/claude-code-savant/claude-md"><img src="https://agentmods.dev/badge/instructions/rlaope/claude-code-savant/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/rlaope/claude-code-savant/claude-md"><img src="https://agentmods.dev/badge/instructions/rlaope/claude-code-savant/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 988 This file is loaded in full into every session.

When invoked 988 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.

Model	Per session	Once invoked
Fable 5.1	$0.00988	$0.00988
Opus 5.5	$0.00395	$0.00395
Sonnet 5.5	$0.00198	$0.00198
Haiku 4.5	$0.00099	$0.00099

Measured 2mo ago against content hash 9aeb4b0f23db, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-code-savant 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 · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Savant - Development Rules

Project Overview

Claude Code plugin with 5 core personas + 16 dev specialist agents + 14 business domain agents (35 total). Includes Web UI (Savant Chat) with Express + SSE streaming.

Agent Categories

Category	Count	Always On	Toggleable
Core Dev	4	Einstein, Shakespeare, Socrates, Steve Jobs	—
Language Optimizers	7	—	JVM, Python, Go, Rust, Node.js, Swift, C/C++
Infra/DevOps	6	—	AWS, K8s, IaC, Observability, CI/CD, Docker
SRE	3	—	System Designer, Performance Detective, SRE Engineer
Biz (gateway)	1	SayNo	—
Biz Domain	14	—	Finance, Growth, Legal, Fashion, Logistics, etc.

Key Files

web/server.ts — Express server, DEV_META/BIZ_META, persona loading, chat/group endpoints
web/public/index.html — SPA chat UI (dev/biz sidebar, activation modals, welcome bubbles)
agents/dev/*/persona.md — Dev persona definitions (21 agents)
agents/biz/*/persona.md — Biz domain agent definitions (14 agents)
agents/router.md — Smart Router with language/infra/SRE detection rules
commands/*.md — Slash command definitions (22 savant commands)
docs/business-agents.md — Full business agents documentation

Git Workflow

Before committing: rlaopegit → commit → push → khopegit

Documentation Sync Rule

When adding, removing, or modifying agents/commands/features/UI:

web/server.ts — Add to DEV_META or BIZ_META (id, name, title, initial, color, krName, krTitle)
web/public/index.html — Welcome bubbles (EN/KO) in getWelcomeBubble()
agents/router.md — Add routing signals for the new agent
README.md — Personas section, commands table, direct agent calls, project structure
docs/business-agents.md — Update if biz agent added/removed

Adding a New Agent

Dev Specialist Agent

Create agents/dev/{id}/ with:
- persona.md — model: sonnet frontmatter + Identity, Domain Expertise, How You Think, Language Style, Core Principle
- templates.md — Response structure with metrics tables, before/after code, runtime explanations
- examples.md — What Makes You Different comparison table + full example response
Add to DEV_META in web/server.ts
Add welcome bubbles (EN/KO) in getWelcomeBubble() in web/public/index.html
Create commands/savant-{name}.md
Update agents/router.md — add detection signals
Update README.md — agent tables, commands, project structure, direct agent calls

Read the full file on GitHub · 81 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.

2mo ago First seen · 81 lines · 988 tokens per session scan A 9aeb4b0f23db

Subscribe to this mod's changes

claude-code-savant CLAUDE.md is an instructions file published in the GitHub repository rlaope/claude-code-savant (2 stars, last pushed 8mo ago), licensed MIT. It adds 988 tokens to every session, about $0.0040 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 agents

claude-code-savant CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-code-savant CLAUDE.mdrlaope/claude-code-savant	Instructions file	2	8mo ago	MIT	A	988	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

claude-code-savant: Instructions file for Claude Code