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.
npx agentmods add commands/rlaope/claude-code-savant/installgit clone --depth 1 https://github.com/rlaope/claude-code-savantWhat 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 | $0.00011 | $0.01492 |
| Opus 5 | $0.00005 | $0.00746 |
| Sonnet 5 | $0.00002 | $0.00298 |
| Haiku 4.5 | $0.00001 | $0.00149 |
Grade A, and why
install 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Welcome to Claude Code Savant! 🎭
Thank you for installing Claude Code Savant - your expert AI personas for better explanations!
Let's Set Up Your Preferences
I'll help you configure Savant with a quick setup.
Step 1: Language Selection
Use AskUserQuestion:
AskUserQuestion:
- question: "Which language should Savant respond in?"
- header: "Language"
- options:
- label: "English (Recommended)"
description: "Responses in English"
- label: "한국어 (Korean)"
description: "한국어로 응답합니다"
- label: "日本語 (Japanese)"
description: "日本語で応答します"
- label: "中文 (Chinese)"
description: "用中文回复"
Step 2: Default Mode
Use AskUserQuestion:
AskUserQuestion:
- question: "Enable auto-routing? (Analyzes ALL questions automatically)"
- header: "Default Mode"
- options:
- label: "Yes, enable auto-routing (Recommended)"
description: "Every question automatically goes to the best persona"
- label: "No, I'll use commands manually"
description: "Use /savant or specific commands when needed"
Step 3: Show Welcome Message
Based on selected language, display the appropriate welcome:
English
## ✅ Setup Complete!
### Your Savant Personas:
| Persona | Command | Specialty |
|---------|---------|-----------|
| 🧠 Einstein | /savant-question | Deep conceptual explanations |
| 🎭 Shakespeare | /savant-code | Code narratives with flowcharts |
| 💡 Steve Jobs | /savant-new | Visionary project direction |
| 🔍 Socrates | /savant-fix | Error debugging & root cause |
### Quick Start:
[If default mode enabled]
Just ask any question naturally! I'll analyze and route it automatically.
[If default mode disabled]
Use `/savant [question]` for smart routing, or use specific commands above.
### Settings:
- `/savant-lang` - Change language
- `/savant-default` / `/savant-default-off` - Toggle auto-routing
Enjoy! 🚀
Korean (한국어)
## ✅ 설정 완료!
### Savant 페르소나:
| 페르소나 | 명령어 | 전문 분야 |
|---------|--------|----------|
| 🧠 아인슈타인 | /savant-question | 깊은 개념 설명 |
| 🎭 셰익스피어 | /savant-code | 코드 분석 & 플로우차트 |
| 💡 스티브 잡스 | /savant-new | 프로젝트 방향 & 비전 |
| 🔍 소크라테스 | /savant-fix | 에러 디버깅 & 근본 원인 |
### 시작하기:
[디폴트 모드 활성화 시]
그냥 질문하세요! 자동으로 분석해서 최적의 페르소나로 연결합니다.
[디폴트 모드 비활성화 시]
`/savant [질문]`으로 스마트 라우팅하거나, 위의 명령어를 직접 사용하세요.
### 설정 변경:
- `/savant-lang` - 언어 변경
- `/savant-default` / `/savant-default-off` - 자동 라우팅 토글
즐겁게 사용하세요! 🚀
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.
- 2d ago First seen · 201 lines · 11 tokens per session scan A fdca4806a696
install is a command published in the GitHub repository rlaope/claude-code-savant (2 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 1,492 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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.