Agent skill

Commandkit Workflow

by neplexlabs in neplexlabs/commandkit

Build durable workflow orchestration with @commandkit/workflow.

MITAuto-check passed

Install Commandkit Workflow

skills CLI
$ npx skills add neplexlabs/commandkit --skill commandkit-workflow -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install neplexlabs/commandkit commandkit-workflow --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/neplexlabs/commandkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/commandkit-workflow .claude/skills/commandkit-workflow && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
commandkit-workflow
GitHub stars
165
Token cost
~460 tokens
SKILL.md length
113 words
Files
6 (incl. references)
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

Build durable workflow orchestration with @commandkit/workflow.

  • Works in 4 steps: Register workflow plugin. → Create workflow entrypoint using 'use… → Create step functions using 'use step'. → …
  • Workflow entrypoints
  • SKILL.md covers Activation guidance, Required filesystem expectations, Execution workflow and Guardrails, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Commandkit Workflow is an agent skill from neplexlabs/commandkit. Build durable workflow orchestration with @commandkit/workflow. Use for workflow entrypoints, step design, command-triggered workflow starts, and long-running stateful process handling.

Its SKILL.md is about 460 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `README.md`, `references/00-filesystem-structure.md` and `references/01-plugin-setup.md`).

The repository describes itself as: The discord.js meta-framework with features such as AI-powered command handler, analytics, feature flags, and more. The licence is MIT.

When your agent uses it

  • Workflow entrypoints
  • Command-triggered workflow starts
  • Long-running stateful process handling

Example prompts

  • “/commandkit-workflow”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Register workflow plugin.
  2. Create workflow entrypoint using 'use workflow'.
  3. Create step functions using 'use step'.
  4. Start workflows from commands/events.

What it can do on your machine

Read from SKILL.md and the folder at commit d771e6b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Commandkit Workflow loads about 460 tokens when it runs, and up to ~1.8k if it reads all its reference files. Until then it costs about 51 tokens; SKILL.md has 113 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~460
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from neplexlabs/commandkit at commit d771e6b, republished under its MIT licence (© neplexlabs). 113 words, ~460 tokens.

Download SKILL.mdSave it as .claude/skills/commandkit-workflow/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
commandkit-workflow
description
Build durable workflow orchestration with @commandkit/workflow. Use for workflow entrypoints, step design, command-triggered workflow starts, and long-running stateful process handling.
version
1.2.0
author
neplextech
emoji
🧭
tags
commandkit, workflow, orchestration, durability

CommandKit Workflow Plugin

Activation guidance

Use for multi-step processes that should survive restart and run reliably.

Required filesystem expectations

  • plugin registration in commandkit.config.ts
  • workflow files in src/workflows/**
  • trigger commands/events in src/app/**

Execution workflow

  1. Register workflow plugin.
  2. Create workflow entrypoint using 'use workflow'.
  3. Create step functions using 'use step'.
  4. Start workflows from commands/events.

Guardrails

  • Keep step boundaries explicit and side effects controlled.
  • Keep workflow inputs deterministic and serializable.

Reference index

NameDescription
references/00-filesystem-structure.mdWorkflow/trigger file placement and project layout guidance.
references/01-plugin-setup.mdPlugin wiring baseline.
references/02-workflow-and-step.mdEntry/step design pattern and best practices.
references/03-start-workflow.mdStarting workflows from command handlers.

Tool index

NameDescription
N/AThis skill currently has no helper tool scripts.

© neplexlabs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (references) in skills/commandkit-workflow of neplexlabs/commandkit.

  • SKILL.md
  • README.md
  • references/00-filesystem-structure.md
  • references/01-plugin-setup.md
  • references/02-workflow-and-step.md
  • references/03-start-workflow.md

Open the folder on GitHubat commit d771e6b

Compare with similar skills

Commandkit Workflow next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Commandkit Workflow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Commandkit Workflow this skillneplexlabs/commandkit165—~460Automated safety check: PassMIT
Durable Test Collateralasgeirtj/system_prompts_leaks69k—~687Automated safety check: PassCC0-1.0
Durable Objectscloudflare/skills3k2 repos~1.5kAutomated safety check: PassApache-2.0
AWS Lambda Durable Functionsaws/agent-toolkit-for-aws2.8k—~2.3kAutomated safety check: PassApache-2.0
Durable AgentsLeoYeAI/openclaw-master-skills2.2k—~5kAutomated safety check: PassMIT
Journey Durablebutterbase-ai/butterbase-skills534—~526Automated safety check: PassMIT

Similar skills

  • Durable Test Collateral

    asgeirtj/system_prompts_leaks

    Load the body before the first implementation edit for a bug fix or behavior change, or when the user or governing specification makes reusable tests a deliverable.

    69k GitHub stars~687 tokensUpdated today
    DevelopmentAuto-check passed
  • Durable Objects

    cloudflare/skills

    Official

    Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.

    3k GitHub starsUsed in 2 repos~1.5k tokens
    Backend & APIsAuto-check passed
  • AWS Lambda Durable Functions

    aws/agent-toolkit-for-aws

    Official

    Builds resilient, long-running, multi-step applications with AWS Lambda durable functions with automatic state persistence, retry logic, and orchestration for long-running executions.

    2.8k GitHub stars~2.3k tokensUpdated today
    Backend & APIsAuto-check passed
  • Durable Agents

    LeoYeAI/openclaw-master-skills

    Build autonomous multi-agent pipelines with Mastra (agents only) and Trigger.dev (all workflows and tasks).

    2.2k GitHub stars~5k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed
  • Journey Durable

    butterbase-ai/butterbase-skills

    Use as the durable-objects build stage of the Butterbase journey.

    534 GitHub stars~526 tokensUpdated 3 days ago
    Auto-check passed
  • Choosing between durable and ephemeral agents in a MoonBit Golem project.

    1.5k GitHub stars~1k tokensUpdated today
    Auto-check passed

More from neplexlabs/commandkit

All 13 skills in this repo
  • Commandkit

    neplexlabs/commandkit

    Build and maintain Discord bots with CommandKit core conventions.

    165 GitHub stars~1k tokensUpdated 11 days ago
    Auto-check passed
  • Commandkit AI

    neplexlabs/commandkit

    Build AI-powered command flows with @commandkit/ai. An agent skill from neplexlabs/commandkit.

    165 GitHub stars~547 tokensUpdated 11 days ago
    Auto-check passed
  • Commandkit Analytics

    neplexlabs/commandkit

    Instrument CommandKit bots with @commandkit/analytics. An agent skill from neplexlabs/commandkit.

    165 GitHub stars~485 tokensUpdated 11 days ago
    Auto-check passed
  • Commandkit Cache

    neplexlabs/commandkit

    Implement deterministic caching with @commandkit/cache. An agent skill from neplexlabs/commandkit.

    165 GitHub stars~506 tokensUpdated 11 days ago
    Auto-check passed
  • Commandkit I18n

    neplexlabs/commandkit

    Implement localization with @commandkit/i18n and i18next. An agent skill from neplexlabs/commandkit.

    165 GitHub stars~546 tokensUpdated 11 days ago
    Auto-check passed
  • Commandkit Plugin Development

    neplexlabs/commandkit

    Create CommandKit plugins for runtime and compiler extension points.

    165 GitHub stars~709 tokensUpdated 11 days ago
    Auto-check passed

Questions about Commandkit Workflow

What does Commandkit Workflow do?

Build durable workflow orchestration with @commandkit/workflow. Commandkit Workflow is an agent skill from neplexlabs/commandkit. Build durable workflow orchestration with @commandkit/workflow.

When should I use Commandkit Workflow?

Commandkit Workflow fits situations like: workflow entrypoints; command-triggered workflow starts; long-running stateful process handling.

How do I install Commandkit Workflow in Claude Code?

Run `npx skills add neplexlabs/commandkit --skill commandkit-workflow -a claude-code`. Or copy the skill folder (skills/commandkit-workflow in neplexlabs/commandkit) into .claude/skills/commandkit-workflow in your project. Claude Code loads it when a task matches its description.

How do I install Commandkit Workflow in Codex?

Run `npx skills add neplexlabs/commandkit --skill commandkit-workflow -a codex`. Or copy the skill folder (skills/commandkit-workflow in neplexlabs/commandkit) into .agents/skills/commandkit-workflow in your project. Codex loads it when a task matches its description.

Can I use Commandkit Workflow in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add neplexlabs/commandkit --skill commandkit-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/commandkit-workflow, .gemini/skills/commandkit-workflow, .github/skills/commandkit-workflow and .opencode/skills/commandkit-workflow in your project.

What does Commandkit Workflow need to run?

SKILL.md names no scripts, command-line tools or credentials: Commandkit Workflow is instructions for the agent only.

Does Commandkit Workflow access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Commandkit Workflow safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Commandkit Workflow use?

Commandkit Workflow is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Commandkit Workflow use?

About 460 tokens (SKILL.md is roughly 1.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.3k tokens, read only when the agent opens those files.

What are the alternatives to Commandkit Workflow?

Skills that share tags, products or a category with Commandkit Workflow: Durable Test Collateral (asgeirtj/system_prompts_leaks, 69k stars), Durable Objects (cloudflare/skills, 3k stars), AWS Lambda Durable Functions (aws/agent-toolkit-for-aws, 2.8k stars) and Durable Agents (LeoYeAI/openclaw-master-skills, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Commandkit Workflow?

neplexlabs (a GitHub organization) maintains it in neplexlabs/commandkit, which has 165 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on September 26, 2026.

Source: neplexlabs/commandkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.