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/smart-ai-memory/attune-ai/wizardgit clone --depth 1 https://github.com/Smart-AI-Memory/attune-aiWrote 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.
[](https://agentmods.dev/commands/smart-ai-memory/attune-ai/wizard)<a href="https://agentmods.dev/commands/smart-ai-memory/attune-ai/wizard"><img src="https://agentmods.dev/badge/commands/smart-ai-memory/attune-ai/wizard.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00013 | $0.02149 |
| Opus 5 | $0.00006 | $0.01074 |
| Sonnet 5 | $0.00003 | $0.00430 |
| Haiku 4.5 | $0.00001 | $0.00215 |
Grade A, and why
wizard 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.
How it starts
The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wizard
Create, manage, and run guided multi-step wizards with XML task decomposition.
Quick Shortcuts
| Shortcut | Action |
|---|---|
/wizard run <id> |
Execute a wizard (debug, test-gen, refactor, security, release-prep) |
/wizard list |
Show all available wizards (built-in + custom) |
/wizard create |
Define a new custom wizard step by step |
/wizard edit <id> |
Modify a custom wizard's configuration |
Natural Language
Describe what you need:
- "run the debug wizard"
- "show me available wizards"
- "create a new wizard for code migration"
- "edit my custom wizard"
CRITICAL: Workflow Execution Instructions
When this command is invoked with arguments, you MUST execute the action, not answer ad-hoc.
Shortcut Routing (EXECUTE THESE)
| Input | Action |
|---|---|
/wizard run <id> |
Execute the wizard's multi-step flow |
/wizard list |
List all registered wizards as a table |
/wizard create |
Start the guided wizard creation flow |
/wizard edit <id> |
Load and modify a custom wizard |
Natural Language Routing (EXECUTE THESE)
| Pattern | Action |
|---|---|
| "run", "execute", "start" | Run wizard by ID |
| "list", "show", "available" | List all wizards |
| "create", "new", "define", "build" | Create a new wizard |
| "edit", "modify", "update", "change" | Edit an existing wizard |
IMPORTANT: When arguments are provided, DO NOT just display documentation. EXECUTE the action.
Action: /wizard run <id>
Execute a wizard's guided multi-step flow. Each wizard follows this pattern:
- Gather info — Use AskUserQuestion to collect context from the user
- Analyze — Run LLM analysis with XML-enhanced prompts
- Decompose — Break work into structured XML
<task>specifications - Preview — Show findings and task list for review
- Confirm — Get approval before applying changes
Running a Built-in Wizard
First, use AskUserQuestion to ask which wizard to run (if no ID was specified):
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 · 274 lines · 13 tokens per session scan A 6d0582d9e667
wizard is a command published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 13 tokens to every session and 2,149 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 2026-09-03.
Other commands, from other repositories
doctor
Diagnose a broken llm-router setup.
greet
个性化问候 (例如: /greet 张三 程序员).
hello
简单的问候测试命令.
costguard-audit
Audit registered workspaces for CI-minute and cron waste, plus read-only cloud provider billing checks. Quantifies estimated monthly waste and prints a Markdown (or JSON) report.
costguard-fix
Auto-fix CI workflow waste (add timeouts, concurrency, paths-ignore) for registered workspaces. Dry-run preview by default; --apply writes the surgical edits to disk.
campy
Show your campy pet's current status.