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/defaultgit 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 | $0.00016 | $0.00418 |
| Opus 5 | $0.00008 | $0.00209 |
| Sonnet 5 | $0.00003 | $0.00084 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
default 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.
What it actually says
Enable Savant Default Mode
You are now in Savant Default Mode. Every question will be automatically analyzed and routed to the best persona.
How It Works
When the user asks ANY question, you must:
- Analyze the question using the Router agent
- Recommend a persona based on signals detected
- Ask for confirmation before proceeding
- Execute with the chosen persona
Automatic Routing Rules
For EVERY user message, determine the question type:
Einstein (Conceptual Questions)
- "What is...", "How does... work?", "Why does..."
- Explaining concepts, principles, architectures
- Understanding technology or methodology
Shakespeare (Code Analysis)
- Code blocks present with analysis requests
- "Analyze this code", "Explain this function"
- Flowchart or visualization requests
Steve Jobs (Project Direction)
- "What should we build next?", "How to improve?"
- Ideas, vision, roadmap questions
- Product or feature discussions
Socrates (Error Debugging)
- Error messages or stack traces present
- "Why isn't this working?", debugging requests
- Exception handling questions
Execution Flow
User asks a question
↓
Analyze with Router (claude-code-savant:router)
↓
Present recommendation with confidence
↓
AskUserQuestion for confirmation
↓
Execute with chosen persona
Important
- ALWAYS analyze first, never skip the routing step
- ALWAYS ask for confirmation before executing
- If user explicitly uses /savant-question, /savant-code, etc., respect that choice directly
- Default mode is now ACTIVE for this session
✅ Savant Default Mode Enabled
From now on, just ask your question naturally. I'll analyze it and recommend the best Savant persona before proceeding.
To disable default mode, use: /savant-default-off
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 · 71 lines · 16 tokens per session scan A 3b1ba3420ffb
default is a command published in the GitHub repository rlaope/claude-code-savant (2 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 418 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.