design-workflow-graphs

design-workflow-graphs is a skill for Claude Code, Codex from flc1125/skills. It costs 95 tokens per session (2,161 once invoked), scanned A, original, MIT.

A guide for designing workflows as explicit graphs of steps, decisions, parallel work, loops, approvals, recovery, and stopping conditions.

In plain words
What is it for?
Use it to decide whether a graph fits a process, design branching or parallel workflows, add approval gates, or specify retries and observability before choosing a framework.
Why use it?
It makes complicated processes reviewable by showing what state changes, who owns each side effect, how failures recover, and how repeated work is bounded.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions Codex.

Part of the flc-skills plugin — 30 skills shipped together

Good fit Use it to decide whether a graph fits a process, design branching or parallel workflows, add approval gates, or specify retries and observability before choosing a framework.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/flc1125/skills/design-workflow-graphs
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.

Any agent
npx skills add flc1125/skills --skill design-workflow-graphs
Clone the repo
git clone --depth 1 https://github.com/flc1125/skills

Made for: Claude Code, Codex.

Or install flc-skills, the plugin that ships this one along with the rest of its 30 skills.

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 design-workflow-graphs

README.md
[![agentmods](https://agentmods.dev/badge/skills/flc1125/skills/design-workflow-graphs/github.svg)](https://agentmods.dev/skills/flc1125/skills/design-workflow-graphs)
Your own site
<a href="https://agentmods.dev/skills/flc1125/skills/design-workflow-graphs"><img src="https://agentmods.dev/badge/skills/flc1125/skills/design-workflow-graphs/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for design-workflow-graphs

Your own site · 80×15
<a href="https://agentmods.dev/skills/flc1125/skills/design-workflow-graphs"><img src="https://agentmods.dev/badge/skills/flc1125/skills/design-workflow-graphs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,161 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00095 $0.02161
Opus 5 $0.00048 $0.01081
Sonnet 5 $0.00019 $0.00432
Haiku 4.5 $0.00010 $0.00216

Measured 8d ago against content hash 05871c56734e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

design-workflow-graphs 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/validate_graph_spec.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/design-workflow-graphs/SKILL.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Workflow Graphs

Design workflow graphs as explicit engineering contracts rather than decorative diagrams. Make control flow, state mutation, termination, failure behavior, and side effects reviewable before choosing an execution framework.

Operating Principles

  • Start from the objective, state, and termination contract; do not start by inventing agents or nodes.
  • Use a graph only when branching, parallelism, bounded iteration, durable recovery, approval gates, or independently observable stages justify it.
  • Prefer a linear workflow or one bounded agent loop when it is sufficient.
  • Keep deterministic control in edges, guards, budgets, and validation. Use model reasoning inside nodes only where judgment is required.
  • Give each state field and side effect an owner.
  • Bound every cycle by attempts, elapsed time, cost, or another measurable budget.
  • Place irreversible side effects after validation and approval whenever possible.
  • Keep the core design framework-neutral. Map it to a runtime only after the graph contract is stable.

Resource Map

Load only what the request needs:

Choose the Work Mode

Choose one primary mode and state it when the distinction affects the deliverable:

  • design: Create a new workflow graph from goals and constraints.
  • transform: Convert a linear process, implicit agent loop, or prose procedure into an explicit graph.
  • review: Find structural, state, concurrency, recovery, termination, and side-effect defects in an existing graph.
  • evolve: Revise a graph using observed failures, traces, evaluation results, or changed requirements.

Read the full file on GitHub · 204 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 204 lines · 95 tokens per session scan A 05871c56734e

Subscribe to this mod's changes

design-workflow-graphs is a skill published in the GitHub repository flc1125/skills (36 stars, last pushed yesterday), licensed MIT. It adds 95 tokens to every session and 2,161 once invoked, about $0.0005 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.