savants

savants is an agent for coding agents from rcdelacruz/claude-code-agents. It costs 0 tokens per session (4,225 once invoked), scanned A, original, MIT.

A group of coordinating agents with broad knowledge across a technology ecosystem, from application code to databases and deployment.

In plain words
What is it for?
Use it for architecture choices, technology selection, cross-cutting problems, full-stack work, integration planning, and trade-off analysis.
Why use it?
It helps with decisions and problems that span several technical areas and require coordination between specialists.

Agent

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.

agentmods
npx agentmods add agents/rcdelacruz/claude-code-agents/savants
Clone the repo
git clone --depth 1 https://github.com/rcdelacruz/claude-code-agents

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 savants

README.md
[![agentmods](https://agentmods.dev/badge/agents/rcdelacruz/claude-code-agents/savants.svg)](https://agentmods.dev/agents/rcdelacruz/claude-code-agents/savants)
Your own site
<a href="https://agentmods.dev/agents/rcdelacruz/claude-code-agents/savants"><img src="https://agentmods.dev/badge/agents/rcdelacruz/claude-code-agents/savants.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,225 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.04225
Opus 5 $0.00000 $0.02112
Sonnet 5 $0.00000 $0.00845
Haiku 4.5 $0.00000 $0.00422

Measured 3d ago against content hash 96487a6970fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

savants 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 3d 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.

docs/agents/savants.md · 691 lines

How it starts

The opening of the file, as written. The whole thing — 691 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Savant Agents

Savant agents are master orchestrators with broad, deep knowledge across entire technology ecosystems. They make architectural decisions, choose technologies, and coordinate specialist agents for complex implementations.

What Makes a Savant?

Savants combine:

  • Breadth: Knowledge across the entire ecosystem (frontend, backend, database, deployment)
  • Depth: Deep understanding of each framework and tool
  • Decision-Making: Technology selection and architectural patterns
  • Orchestration: Coordinates multiple specialists
  • Best Practices: Industry-standard patterns and recommendations

When to Use Savants

Use savants when you need:

  • Architectural decisions - Choosing between frameworks, patterns, and approaches
  • Technology selection - Deciding on the tech stack for new projects
  • Complex problems - Cross-cutting issues spanning multiple domains
  • Full-stack coordination - Building features that touch database, API, and UI
  • High-level guidance - Understanding tradeoffs and best practices
  • Integration planning - How different pieces fit together

Current Savants

react-native-savant

Name: react-native-savant

Description: Master expert in React Native and mobile cross-platform development. Deep knowledge of React Native, Expo, React Navigation, native modules, iOS and Android development.

Core Expertise

React Native Framework (0.73+):

  • Core Architecture (Fabric, Turbo Modules, JSI, Bridge)
  • Components (FlatList, SectionList, Pressable, Modal)
  • Hooks (useState, useEffect, useCallback, useMemo)
  • Native Modules (Bridging, Turbo Modules, JSI)
  • Performance (Hermes, FlatList optimization, bundle size)
  • New Architecture (Fabric renderer, CodeGen)

Expo Framework (SDK 50+):

  • Expo Router (File-based routing, layouts, deep linking)
  • EAS Build (Cloud builds, development builds, preview builds)
  • EAS Submit (App Store and Play Store automation)
  • EAS Update (Over-the-air updates, channels, rollbacks)
  • Expo Prebuild (Generate native projects, config plugins)
  • Expo Modules API (Swift/Kotlin native modules)

Read the full file on GitHub · 691 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. 3d ago First seen · 691 lines · 0 tokens per session scan A 96487a6970fc

Subscribe to this mod's changes

savants is an agent published in the GitHub repository rcdelacruz/claude-code-agents (2 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,225 tokens. 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.