do

A universal command that analyzes a coding task and routes it to suitable craft commands.

In plain words
What is it for?
Use it for feature development, bug fixes, code-quality work, documentation updates, and related tests or Git tasks.
Why use it?
It reduces the need to know which separate command handles planning, testing, debugging, documentation, or version-control work.

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/do
Clone the repo
git clone --depth 1 https://github.com/Data-Wise/claude-plugins
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,633 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 $0.00009 $0.01633
Opus 5 $0.00005 $0.00816
Sonnet 5 $0.00002 $0.00327
Haiku 4.5 $0.00001 $0.00163

Measured yesterday against content hash afb011ece323, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

do 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/commands/do.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/craft:do - Universal Command

Intelligently analyze your task and execute the right craft commands.

Usage

/craft:do <task description>

How It Works

  1. Check Spec - Look for existing spec matching task (NEW in v1.1.0)
  2. Analyze - Parse task description for intent
  3. Route - Select appropriate craft commands
  4. Execute - Run commands in optimal order
  5. Report - Summarize what was done

Examples

Feature Development

/craft:do add user authentication

# Routes to:
# 1. /craft:arch:plan - Design the feature
# 2. /craft:code:test-gen - Generate tests
# 3. /craft:git:branch - Create feature branch

Bug Fixing

/craft:do fix the login redirect issue

# Routes to:
# 1. /craft:code:debug - Analyze the issue
# 2. /craft:test:run - Run related tests
# 3. /craft:git:sync - Commit fix

Code Quality

/craft:do improve code quality

# Routes to:
# 1. /craft:code:lint - Check style
# 2. /craft:test:coverage - Check coverage
# 3. /craft:code:refactor - Suggest improvements

Documentation

/craft:do update documentation

# Routes to:
# 1. /craft:docs:sync - Sync docs with code
# 2. /craft:docs:validate - Check links
# 3. /craft:docs:changelog - Update changelog

Release Preparation

/craft:do prepare for release

# Routes to:
# 1. /craft:code:deps-audit - Security scan
# 2. /craft:test:run release - Full tests
# 3. /craft:code:lint release - Full lint
# 4. /craft:docs:changelog - Update changelog
# 5. /craft:code:release - Release workflow

Task Categories

Category Keywords Commands Used
Feature add, create, implement, build arch:plan, code:test-gen, git:branch
Bug fix, debug, issue, error code:debug, test:run, test:debug
Quality lint, quality, clean, improve code:lint, test:coverage, code:refactor
Docs document, update docs, readme docs:sync, docs:validate, docs:changelog
Test test, coverage, verify test:run, test:coverage, test:debug
Release release, deploy, publish deps-audit, lint, test:run, code:release
Architecture design, refactor, restructure arch:analyze, arch:plan, arch:diagram

Read the full file on GitHub · 222 lines

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 · 222 lines · 9 tokens per session scan A afb011ece323

Subscribe to this mod's changes

do is a command published in the GitHub repository Data-Wise/claude-plugins (7 stars, last pushed 5d ago), licensed MIT. It adds 9 tokens to every session and 1,633 once invoked, about $0.0000 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.