workflow-creator

workflow-creator is a skill for Claude Code, Codex from accuknox/agentZ. It costs 36 tokens per session (1,689 once invoked), scanned A, original, Apache-2.0.

A guide for creating saved workflows as directed acyclic graphs: connected step-by-step procedures where each step runs once and paths do not loop back.

In plain words
What is it for?
Use it when creating or revising recurring automations, scheduled jobs, or reusable procedures, including their steps, branches, start, and finish conditions.
Why use it?
It prevents reusable workflows from being saved before they have been manually tested, fully defined, and checked end to end.

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/accuknox/agentz/workflow-creator
Any agent
npx skills add accuknox/agentZ --skill workflow-creator
Clone the repo
git clone --depth 1 https://github.com/accuknox/agentZ

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 workflow-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/accuknox/agentz/workflow-creator.svg)](https://agentmods.dev/skills/accuknox/agentz/workflow-creator)
Your own site
<a href="https://agentmods.dev/skills/accuknox/agentz/workflow-creator"><img src="https://agentmods.dev/badge/skills/accuknox/agentz/workflow-creator.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,689 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 $0.00036 $0.01689
Opus 5 $0.00018 $0.00844
Sonnet 5 $0.00007 $0.00338
Haiku 4.5 $0.00004 $0.00169

Measured 4d ago against content hash 6796f2aa6b69, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workflow-creator 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.

opencode/skills/core/workflow-creator/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workflow Creator

Treat the workflow as a saved directed acyclic graph:

  • each node is one execution step
  • each edge is one allowed transition
  • branching belongs on edges, not inside node instructions

Authoring Rules

  • Treat recurring automation, scheduled execution, and reusable procedures as workflow-authoring tasks, not graph-only tasks.
  • Before calling create_workflow, execute the requested task manually once with the concrete user inputs or the closest accessible substitute.
  • For non-trivial reusable logic, create or update a skill or script before saving the workflow so the repeated behavior lives in one deterministic place.
  • End-to-end verification is required before saving the workflow. Brief or shallow checks are not enough.
  • Finalize the full graph before calling create_workflow.
  • Keep workflow_name to a DNS label up to 32 characters, for example repo-triage.
  • Keep each node.name unique and in the same DNS-label format.
  • Ensure the graph is connected and acyclic.
  • Ensure the graph has at least one start node and one terminal node.
  • Keep node instructions concrete. Each node must define instructions, goal, and done_criteria.
  • Add preferred_skills when a node should load specific OpenCode skills before execution.
  • Add preferred_tools only when it gives real execution guidance.

Input Schema Rules

  • Omit inputs and arbitrary_json when the workflow takes no parameters.
  • Use exactly one input contract: either typed inputs or arbitrary_json, never both.
  • Use arbitrary_json when the workflow should accept one free-form JSON payload. Its allowed fields are description and default_payload.
  • arbitrary_json.default_payload is a prefill example, not a runtime fallback.
  • When present, inputs must be a flat object keyed by input name.
  • Each input must be a schema object with at least type and required.
  • Supported input types are scalar only: string, integer, number, boolean.
  • Allowed input keys are: type, description, required, default, enum, minLength, maxLength, pattern, format, minimum, maximum, exclusiveMinimum, exclusiveMaximum, multipleOf.
  • Put required inside each input schema object. Do not use top-level JSON Schema required arrays inside one input definition.
  • Do not use nested object or array schemas.
  • Do not include extra JSON Schema metadata such as $schema, title, properties, items, additionalProperties, oneOf, anyOf, or allOf.
  • Workflow definition inputs declare the schema only. Runtime workflow inputs are separate JSON values validated against that schema later.

Read the full file on GitHub · 179 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 · 179 lines · 36 tokens per session scan A 6796f2aa6b69

Subscribe to this mod's changes

workflow-creator is a skill published in the GitHub repository accuknox/agentZ (41 stars, last pushed 6d ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,689 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

github-ci-fix-onboarding

Onboards and troubleshoots GitHub PR CI fixing by configuring GitHub CLI authentication, a non-exposed GitHub token, a matching local checkout, and a ready coding agent before running fixgithubprci. Use for first-time setup, failed prerequisites, demos, or action-shaped requests to onboard the user onto the local…

Tracer-Cloud/opensre · 85 tokens

greptimedb-development-docker-image

Builds a development-only GreptimeDB Docker image from a local debug binary for local-cluster testing, and optionally pushes it to a development registry. Use when the user asks to package, build, tag, publish, or cross-build a non-release GreptimeDB or GreptimeDB Enterprise image for debugging.

GreptimeTeam/greptimedb · 71 tokens

greptimedb-release

Runbook for publishing a new GreptimeDB version (tag + GitHub release + docs release-note PR) on the upstream GreptimeTeam/greptimedb repo. Use when asked to "release" / "publish" a GreptimeDB version (e.g. v1.1.0, v1.0.3).

GreptimeTeam/greptimedb · 75 tokens

yandex-cloud

Read Yandex Cloud through its REST API. Applies to any question about VMs, metrics, logs, audit events, Kubernetes, managed databases, serverless, networking or any other Yandex Cloud resource. Never shell out to the yc CLI — it is not how this agent reaches Yandex Cloud and is usually not installed.

Tracer-Cloud/opensre · 71 tokens

morning-report

Weather + news morning briefing: fetch live weather and headlines, compose a plain-text briefing, deliver it. Multi-step; load before acting.

Tracer-Cloud/opensre · 32 tokens

github-security-fix

Remediate GitHub security / Dependabot / CodeQL / code-quality alerts via fixgithubsecurityalert.

Tracer-Cloud/opensre · 27 tokens