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.
npx agentmods add skills/wentong2022-arch/flowforge-skill/flowforgenpx skills add wentong2022-arch/flowforge-skill --skill flowforgegit clone --depth 1 https://github.com/wentong2022-arch/flowforge-skillWrote 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.
[](https://agentmods.dev/skills/wentong2022-arch/flowforge-skill/flowforge)<a href="https://agentmods.dev/skills/wentong2022-arch/flowforge-skill/flowforge"><img src="https://agentmods.dev/badge/skills/wentong2022-arch/flowforge-skill/flowforge.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00153 | $0.03020 |
| Opus 5 | $0.00077 | $0.01510 |
| Sonnet 5 | $0.00031 | $0.00604 |
| Haiku 4.5 | $0.00015 | $0.00302 |
Grade A, and why
FlowForge 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.
How it starts
The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FlowForge — Draw.io Diagram Skill
Generate professional diagrams as draw.io XML files. Supports 13 diagram types: flows, comparisons, layer stacks, cycles, trees, hub-and-spoke, columns, matrices, funnels, timelines, sequence diagrams, and swimlanes.
Usage
/FlowForge "OAuth 2.0 authorization code flow"
/FlowForge path/to/design-doc.md
/FlowForge "CI/CD pipeline" --type loop
/FlowForge "Monolith vs Microservices" --type compare --theme morandi
/FlowForge "System Architecture" --lang en
Workflow
Step 1: Understand & Propose (one confirmation, not three)
If given a document: read it fully, identify 1–3 places that benefit from a diagram, and for each note the insert position, the topic (one sentence), and the recommended type (see Diagram Type Reference).
If given a concept directly: identify the core message and pick the type via the Selection Guide.
Then present one combined proposal and ask for confirmation once. The proposal contains:
- Diagram type and theme (default: tech-blue; other options: morandi, mint, terracotta, indigo)
- An ASCII sketch: all nodes with labels, arrow directions and labels, grouping, color-role tags, layout direction
Example sketch:
Direction: left-to-right | Nodes: 4 | Type: flow | Theme: tech-blue
[primary] Code Commit → [process] Build → [process] Test → [accent] Deploy
↓ (fail)
[error] Alert
Skip the confirmation entirely when the request already pins everything down (user gave --type/--theme or an unambiguous description), or when no human can respond (subagent, batch, CI). In that case proceed with defaults and state your assumptions in the final report.
Step 2: Generate draw.io XML
- Read references/layouts.md — the layout algorithm for the chosen type — and compute all coordinates from its formulas
- Apply theme colors from themes.md
- Use element templates from xml-reference.md
- For an unfamiliar type, read the matching example file listed in examples.md
What ships with it
12 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.
- examples.md 3.2 KB
- examples/compare-monolith-vs-micro.drawio 7.4 KB
- examples/flow-cicd.drawio 3.0 KB
- examples/hub-agent-capabilities.drawio 5.5 KB
- examples/loop-ml-training.drawio 3.4 KB
- examples/timeline-llm-history.drawio 6.2 KB
- examples/tree-storage-decision.drawio 6.4 KB
- references/layouts.md 7.9 KB
- scripts/render.sh 737 B runs code
- scripts/validate.py 12 KB runs code
- themes.md 7.3 KB
- xml-reference.md 6.4 KB
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.
- 4d ago First seen · 241 lines · 153 tokens per session scan A 848a71f649bf
FlowForge is a skill published in the GitHub repository wentong2022-arch/flowforge-skill (134 stars, last pushed 2mo ago), licensed MIT. It adds 153 tokens to every session and 3,020 once invoked, about $0.0008 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.
Other skills, from other repositories
thesis-figure-skill
生成学术论文配图：LaTeX/TikZ 代码（结构化图表，直接嵌入论文）或 draw.io XML （技术路线图、汇报配图）。自动按论文领域风格设计，编译验证后交付。 Use when the user asks for: 论文配图、画架构图、画流程图、TikZ 图、draw.io 学术图、复刻论文图、tikz/latex diagram。.
hue
Meta-skill that generates new design language skills. Works on Claude Code and Codex. Use when the user says 'create a design skill', 'generate design language', 'new design system skill', 'design skill inspired by X', 'design skill from this screenshot', '/hue', or 'use hue'. Also triggers for 'remix my design skill'…
bruce-drawio
Use this skill when the user wants to create any diagram: flowchart, architecture, UML (sequence/class), ER, mindmap, network topology, or any visual diagram. Trigger words: "draw", "diagram", "flowchart", "architecture", "UML", "sequence diagram", "mindmap", "ER diagram", "network topology", "visualize", "draw.io"…
aws-architecture-diagram
Generate AWS architecture diagrams in draw.io format. Activates when the user asks to create, generate, or build an architecture diagram, system diagram, or draw.io diagram for AWS services.
network-topologies
Create animated network topology and infrastructure diagrams using the Excalimate MCP server. Use when asked to visualize network architecture, server infrastructure, cloud deployments, Kubernetes clusters, VPC layouts, firewall rules, load balancing, or any physical/logical network topology.
tikz-figure-code
写出高质量、一次过编译、编辑安全的 TikZ/LaTeX 配图代码的工程基础技能。 教 agent 用「按构造布局」(positioning/fit/chains/anchor) 而非「手填绝对坐标」， 附 8 条硬约束、canonical 箭头、before/after 范例、一个静态检查入口 (lint.sh)。 Use when: 写/审 TikZ 或 LaTeX 图代码、修图的排版/对齐/溢出/箭头问题、 tikz layout、latex figure code、tikz 编译报错、CJK 中文图渲染成色块。.