smart

A set of slash commands that routes a request to an appropriate workflow and reports the result. Slash commands are short typed instructions, such as `/craft:do`, used to start repeatable agent actions.

In plain words
What is it for?
Starting tasks such as adding authentication, improving database queries, or writing API documentation; running pre-commit or release checks; and monitoring or resuming delegated work.
Why use it?
It removes the need to choose every tool or workflow manually for common tasks. It also provides commands for checks, orchestration, status, timelines, and continuing a session.

Command

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 commands/data-wise/claude-plugins/smart
Clone the repo
git clone --depth 1 https://github.com/Data-Wise/claude-plugins
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 443 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 $0.00443
Opus 5 $0.00000 $0.00221
Sonnet 5 $0.00000 $0.00089
Haiku 4.5 $0.00000 $0.00044

Measured yesterday against content hash 801a589a8276, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

smart 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.

craft/docs/commands/smart.md · 77 lines

What it actually says

Smart Commands

Universal AI-powered commands for intelligent task routing.

/craft:do

Purpose: Universal command that routes tasks to the best workflow automatically.

Usage:

/craft:do "add user authentication"
/craft:do "optimize database queries"
/craft:do "create API documentation"

The AI analyzes your request and:

  1. Determines the best approach
  2. Selects appropriate tools/commands
  3. Executes the workflow
  4. Reports results

/craft:orchestrate

Purpose: Enhanced orchestrator v2.1 with mode-aware execution and subagent monitoring.

Usage:

/craft:orchestrate "implement auth" optimize    # Fast parallel
/craft:orchestrate "prep release" release       # Thorough audit
/craft:orchestrate status                       # Agent dashboard
/craft:orchestrate timeline                     # Execution timeline
/craft:orchestrate continue                     # Resume session

Features:

  • Mode-aware execution (default/debug/optimize/release)
  • Subagent delegation and monitoring
  • Chat compression for long sessions
  • ADHD-optimized status tracking
  • Timeline view of execution

/craft:check

Purpose: Pre-flight checks before commits, PRs, or releases.

Usage:

/craft:check                    # Quick validation
/craft:check --for commit       # Pre-commit checks
/craft:check --for pr           # Pre-PR validation
/craft:check --for release      # Full release audit

Checks:

  • Code linting
  • Test execution
  • Documentation validation
  • Build verification
  • Dependency updates

/craft:help

Purpose: Context-aware help and suggestions for your project.

Usage:

/craft:help                     # General suggestions
/craft:help testing             # Deep dive into testing
/craft:help documentation       # Docs-specific help

Features:

  • Analyzes your project structure
  • Suggests relevant commands
  • Provides context-specific guidance
  • Links to documentation
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. yesterday First seen · 77 lines · 0 tokens per session scan A 801a589a8276

Subscribe to this mod's changes

smart is a command published in the GitHub repository Data-Wise/claude-plugins (7 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 443 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.