create-workflow

create-workflow is a skill for Claude Code, Codex from LazyAGI/LazyMind. It costs 0 tokens per session (2,110 once invoked), scanned A, original, Apache-2.0.

Instructions for creating and repairing LazyMind Workflow files. A Workflow is a structured automation or process that can be designed, converted, polished, or fixed.

In plain words
What is it for?
Use it to create, convert, repair, or polish Workflow artifacts and their related schemas, scripts, briefs, and warnings.
Why use it?
It explains which process to follow for interactive Workflow drafts and for internal generation or repair tasks. This prevents the wrong type of output or workflow process being used.

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/lazyagi/lazymind/create-workflow
Any agent
npx skills add LazyAGI/LazyMind --skill create-workflow
Clone the repo
git clone --depth 1 https://github.com/LazyAGI/LazyMind

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for create-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/lazyagi/lazymind/create-workflow.svg)](https://agentmods.dev/skills/lazyagi/lazymind/create-workflow)
Your own site
<a href="https://agentmods.dev/skills/lazyagi/lazymind/create-workflow"><img src="https://agentmods.dev/badge/skills/lazyagi/lazymind/create-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,110 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 $0.02110
Opus 5 $0.00000 $0.01055
Sonnet 5 $0.00000 $0.00422
Haiku 4.5 $0.00000 $0.00211

Measured 4d ago against content hash 5941a82de6af, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-workflow 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 4d 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.

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.

algorithm/lazymind/skills/create-workflow/SKILL.md · 264 lines

How it starts

The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Workflow Skill

Purpose

Use this skill to design, create, generate, convert, polish, or repair LazyMind Workflow artifacts.

This skill supports two execution contexts:

  • ChatAgent authoring: an end user asks in chat to create a new Workflow.
  • Platform task generation: an internal non-streaming llm-task job asks for one phase of Workflow generation, conversion, repair, or metadata polish.

First identify the execution context, then follow only the matching section.

Context Dispatch

Use Platform Task Mode when the prompt or input says any of the following:

  • task_type starts with workflow.
  • The caller requests a JSON schema such as workflow_yaml, state_yaml, scenario_md, scripts, edits, design_brief, or remaining_warnings.
  • The caller says it is an internal platform job, backend task, non-streaming task, generation phase, repair phase, or conversion phase.

Use ChatAgent Authoring Mode only when a human user is currently asking in chat to create a new Workflow draft.

If both modes appear applicable, prefer Platform Task Mode. Backend jobs must never be turned into an interactive chat flow.

ChatAgent Authoring Mode

When To Use

Use this mode only when the user explicitly asks to create a new Workflow.

Trigger conditions:

  • "帮我创建一个…插件"
  • "新建一个插件"
  • "我想做一个插件"
  • Any similar request that clearly asks to author a brand-new Workflow.

Do not use this mode when:

  • The user wants to modify or fix an existing Workflow.
  • The user is asking about how Workflows work.
  • The user mentions a Workflow in passing but is not requesting creation.
  • The caller is a platform/background task.

Step 1 - Generate A Summary

Read the user's request carefully. Output a natural-language summary in this exact format:

插件名称:<display name>
功能描述:<one or two sentences describing what the workflow does>
输入槽位:<slot_id>(<type>,<cardinality>)<label>  - one per line
输出槽位:<slot_id>(<type>,<cardinality>)<label>  - one per line
主要步骤:1. <step_id>  2. <step_id>  3. <step_id>  ...

Read the full file on GitHub · 264 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. 4d ago First seen · 264 lines · 0 tokens per session scan A 5941a82de6af

Subscribe to this mod's changes

create-workflow is a skill published in the GitHub repository LazyAGI/LazyMind (74 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,110 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 2026-08-30.

Related

Other skills, from other repositories

star-plan-decomposer

Break a research plan down into executable sub-plans with concrete, checkable steps — turning its method or milestones into actionable tasks. Reads the parent plan (written by star-plan-coach and living under metds/plans/), picks a decomposition axis (phase / component / evidence), confirms the unit list, then by…

wanghao9610/STAR · 202 tokens

star-plan-executor

Execute or implement a leaf research sub-plan: turn it into code and run light validation. Orients in the codebase using .env, turns the sub-plan from metds/plans/ into a concrete checked execution plan, implements it with surgical changes, keeps intermediate working files under a plan-specific tasks directory…

wanghao9610/STAR · 171 tokens

star-refs-reviewer

Literature review and related work: per-paper analysis notes plus a verified reference.bib. Builds an auditable base — 5–10 close papers read into notes, plus a classified reference.bib of ≥50 verified entries. No argument finds the method in metds/ and runs the full pass, resuming if metds/refs/ exists; a PLANNAME or…

wanghao9610/STAR · 226 tokens

star-code-release

Open-source or publish the project: gather scattered code, polish it, compile README.md. Consolidates into ${CODENAME}/, sweeping tasks/, wkdrs/ and the root, promoting only code passing a three-part evidence test (the README cites it, an executed leaf needs it, or it reproduces a results.md number), placed by…

wanghao9610/STAR · 195 tokens

star-code-reviewer

Review code quality, docstrings, and whether a plan's code matches what it promised. No argument reviews all of ${CODENAME}/; a PLANNAME (slug / prefix / filename) reviews that plan's files plus conformance (§3 tasks, §4 deliverables, §5 done-criterion); a path reviews that path; diff or a git range reviews changed…

wanghao9610/STAR · 198 tokens

star-expt-digest

Summarize experiment progress since last time — the periodic digest a progress report is written from, in date order. No argument resumes from the last digest; a PLANNAME covers that node's whole family — ancestors for context, descendants for evidence; d or a date covers a window; all covers everything. Collects each…

wanghao9610/STAR · 205 tokens