create-workflow

A guided builder for a profile’s /workflow command, which is a saved sequence of steps for recurring work.

In plain words
What is it for?
Use it to add or redesign a workflow such as planning, scaffolding, implementation, verification, and shipping.
Why use it?
It turns a multi-step process into a predictable flow while letting you confirm or adjust each stage before it is saved.

Skill for Claude CodeCodex

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 skills/mduffy37/claudeworks/create-workflow
Any agent
npx skills add Mduffy37/claudeworks --skill create-workflow
Clone the repo
git clone --depth 1 https://github.com/Mduffy37/claudeworks

Made for: Claude Code, Codex.

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,608 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00069 $0.04608
Opus 5 $0.00034 $0.02304
Sonnet 5 $0.00014 $0.00922
Haiku 4.5 $0.00007 $0.00461

Measured 2d ago against content hash f1ce58fbca9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

create-workflow scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

!`cat "${CLAUDE_PLUGIN_ROOT:-$HOME/.claude/plugins/marketplaces/claudeworks/plugins/profiles-manager}/data/workflow-shapes.json"`
src/builtin-plugin/skills/create-workflow/SKILL.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are creating or revising the /workflow command for a ClaudeWorks profile. /workflow is a dormant slash command stored in the profile's workflow field in ~/.claudeworks/profiles.json — when the user types /workflow inside a session running under that profile, Claude Code walks through a specific orchestration of the profile's tools (plan → scaffold → implement → verify → ship, or whatever sequence you co-design with the user).

You always run interactively. You never draft the body unilaterally — you propose one stage at a time and let the user confirm, tweak, or add. This is true whether the user invoked the skill themselves (e.g. "add a /workflow to my frontend-dev profile") or create-profile chained it during new-profile assembly.

The default path is direct invocation: the skill reads the user's current profile (from CLAUDE_CONFIG_DIR), walks them through shape + sequencing, and patches profiles.json in place. There is one special case — parent mode — when create-profile hands over a context block so new-profile assembly can include the workflow in a single write. The rest of this SKILL.md spells out how to handle that handoff; everything else is the default.

  • Parent modecreate-profile hands over a context block with the profile description, the picked plugins, the chosen workflow shape, and the stage list. You skip profile selection and shape picking and go straight to sequencing. When done, you emit the final body between marker lines so the parent skill can capture it as P_WORKFLOW and fold it into its own write-profile.js call.

Step 0 — Detect invocation mode

Look for a block in the incoming prompt of the following shape (this is what create-profile emits when it hands off):

CREATE_WORKFLOW_CONTEXT
{
  "profileDescription": "...",
  "profileName": "...",
  "pickedPlugins": [{"id":"...","displayName":"...","enabledItems":{"skills":[...],"commands":[...],"agents":[...]}}, ...],
  "shapeId": "feature-development",
  "stages": [{"id":"plan","name":"Plan","intent":"...","keywords":[...]}, ...]
}
END_CREATE_WORKFLOW_CONTEXT
  • If the block is present, parse it and jump straight to Step 3 (sequencing). Use profileDescription, pickedPlugins, and stages from the block — do not ask the user to restate any of these.
  • If the block is absent, proceed to Step 1.

Do not mix modes — either the parent hands over context, or the user drives the whole flow. Never fall through "half-handed-over" because the block was malformed; if parsing fails, tell the user the handoff broke and ask them to re-run create-profile, rather than silently restarting the direct flow inside a half-completed profile creation.

Read the full file on GitHub · 228 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. 2d ago First seen · 228 lines · 69 tokens per session scan B f1ce58fbca9b

Subscribe to this mod's changes

create-workflow is a skill published in the GitHub repository Mduffy37/claudeworks (11 stars, last pushed 3mo ago), licensed MIT. It adds 69 tokens to every session and 4,608 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

snip

You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.

edouard-claude/snip · 0 tokens

todos

This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…

JetBrains/thinkrail · 127 tokens

writing-workflow-skills

Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.

JetBrains/thinkrail · 60 tokens

reviewing-changes

Use when a review package asks you to review a plan step's change set (todo.startReview): you are the REVIEWER, not the author. How to judge an agent-written diff, file findings with addreviewcomment, and settle with exactly one reviewverdict.

JetBrains/thinkrail · 59 tokens

setting-up-a-project

Use whenever asked to set up, onboard, initialize, or spec a project — the front door when the workspace has no spec graph yet (brand-new or an existing codebase); also seeded by the app's Set-up-project card (/skill:setting-up-a-project). Not for feature work in an already-specced project — use the brainstorming…

JetBrains/thinkrail · 76 tokens

writing-specs

Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.

JetBrains/thinkrail · 59 tokens