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/setupgit 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 | $0.00012 | $0.00475 |
| Opus 5 | $0.00006 | $0.00237 |
| Sonnet 5 | $0.00002 | $0.00095 |
| Haiku 4.5 | $0.00001 | $0.00047 |
Grade A, and why
setup 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 yesterday.
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.
What it actually says
Savant Setup Wizard
Welcome to Claude Code Savant! Let's configure your preferences.
Setup Process
Use AskUserQuestion to configure the following settings:
Step 1: Language Selection
AskUserQuestion:
- question: "Which language should Savant respond in?"
- header: "Language"
- options:
- label: "English"
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
AskUserQuestion:
- question: "Enable Savant Default Mode? (Auto-route all questions)"
- header: "Default Mode"
- options:
- label: "Yes, enable (Recommended)"
description: "All questions automatically analyzed and routed to best persona"
- label: "No, manual only"
description: "Use /savant or specific commands when needed"
Step 3: Confirmation
After collecting preferences, display:
## ✅ Savant Setup Complete!
### Your Settings:
- **Language**: [Selected Language]
- **Default Mode**: [Enabled/Disabled]
### Quick Start:
[If default mode enabled]
Just ask any question! I'll automatically route it to the best persona.
[If default mode disabled]
Use these commands:
- `/savant [question]` - Smart router
- `/savant-question` - Einstein (concepts)
- `/savant-code` - Shakespeare (code analysis)
- `/savant-new` - Steve Jobs (direction)
- `/savant-fix` - Socrates (debugging)
### Change Settings Anytime:
- `/savant-lang` - Change language
- `/savant-default` - Enable default mode
- `/savant-default-off` - Disable default mode
Enjoy using Savant! 🎭
Language Instruction
Based on language selection, inform the user that all Savant responses will be in their chosen language. Store this preference for the session.
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.
- yesterday First seen · 77 lines · 12 tokens per session scan A ec1ae21ea462
setup is a command published in the GitHub repository rlaope/claude-code-savant (2 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 475 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
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.