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 skills add mrpulor-gh/nuphus --skill workflow-designgit clone --depth 1 https://github.com/mrpulor-gh/nuphusWrote 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/mrpulor-gh/nuphus/workflow-design)<a href="https://agentmods.dev/skills/mrpulor-gh/nuphus/workflow-design"><img src="https://agentmods.dev/badge/skills/mrpulor-gh/nuphus/workflow-design.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00000 | $0.03653 |
| Opus 5 | $0.00000 | $0.01826 |
| Sonnet 5 | $0.00000 | $0.00731 |
| Haiku 4.5 | $0.00000 | $0.00365 |
Grade A, and why
workflow-design 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 yesterday.
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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
工作流设计经验手册
完整工作流编排能力：步骤 schema、变量语法、条件表达式、params 固化、设计模式、验证闭环、经验闭环。 L2 提示词只给阶段门禁与交互纪律；本文档是可执行的方法论全集。
〇、编排闭环总览
接收任务
├─ [查] ui_maps_search 检索同类经验 → 有 screen/experience 直接复用，跳过重复探索
├─ [探] 逐屏探索 → ui_maps_save_screen 固化布局（每屏经用户确认）
├─ [固] 生成 params.json + workflow.json + guide.md（参数即契约，全部有界面证据）
├─ [验] workflow_validate 编译校验 → workflow_run 执行 → 连续 3 次一致 + 至少一个异常路径
└─ [馈] 跑通后 ui_maps_save_experience 提炼经验；新异常回写 params.json exceptions
任务输入形态（先识别再走闭环）：
- 用户输入带
[意图表单→工作流]前缀，或来自request_user_input(step_form)的{stage, steps}：这些阶段/子步骤是用户确认的意图骨架。表单阶段 = 流程主线分组（写入 workflow.json 保留为用户心智的阶段注释）；每个子步骤 = 一条探索任务，逐条走 [探]→[固]→[设]→[验]；骨架为权威输入，不得重新向用户收集流程、整体重构或丢弃补录 steps。 - 自由对话描述：起步先问「先填意图表单（阶段+子步骤），还是我直接按您的目标探索？」——选填表 →
request_user_input(input_type="step_form", default_stage=当前阶段名)；选探索 → 走闭环。探索中途需用户补子步骤 → 同样弹 step_form。 - 表单行意图是纯文本，无工具参数；工具参数（selector/坐标/窗口等）由你探索后固化进
params.json/with字段。
一、步骤 Schema（V2，唯一真相源 src/workflow/step_schema.json）
公共字段
| 字段 | 必填 | 说明 |
|---|---|---|
id |
✅ | 步骤唯一标识（断点续连按 id 跳过已完成步骤） |
name |
✅ | 人类可读名称 |
description |
可选 | 详细说明 |
on_error |
可选 | "abort"(默认) / "skip" / {retry:{max,backoff_ms?,backoff_multiplier?}} / {allow_codes:{codes:[...]}} |
capture |
可选 | 字符串：步骤输出存入变量名（无对象格式） |
timeout_secs |
可选 | 步骤超时秒数 |
do |
✅ | 动作定义，仅下列一种 key |
动作类型（do 的 13 种形态）
| kind | 写法 | 要点 |
|---|---|---|
| tool | {"tool":"desktop_mouse","with":{...}} |
with 支持 {{var}} 模板 |
| seq | {"seq":[...]} |
顺序容器，可嵌套 |
| loop | {"loop":{"for_each"|"repeat"|"until":..., "max":100, "do":[...]}} |
until=条件满足即停；max 防死循环 |
| if | {"if":{"condition":{...},"then":[...],"else":[...]}} |
else 可省略 |
| call | {"call":"wf-id","with":{"inputs":{...},"outputs":{...}}} |
inputs 传子变量；outputs 子变量名→父变量名回写 |
| wait | {"wait":"提示语","auto":[...]} |
auto=等待期自动执行步骤（可选） |
| chat | {"chat":"LLM任务描述","with":{...}} |
LLM 决策节点（原 chat_agent） |
| script | {"script":{"runtime":"python"|"node"|"ahk"|"pwsh","code":"...","cwd":"?"}} |
code 支持 {{var}} 替换 |
| assert | {"assert":{"condition":{...},"message":"?"}} |
on_error=skip 时变非阻断校验 |
| mcp | {"mcp":{"server":"key","tool":"name","with":{...}}} |
server 对应 servers.yaml |
| sleep | {"sleep":N} |
秒，0.1–3600 |
| break | {"break":true} |
跳出当前循环 |
| continue | {"continue":true} |
跳过当前迭代 |
What ships with it
1 file 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.
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.
- yesterday Changed · +4 lines f2a1c3614a5c
- 8d ago First seen · 255 lines · 0 tokens per session scan A 9f4a96d5b0a2
workflow-design is a skill published in the GitHub repository mrpulor-gh/nuphus (56 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,653 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.
Other skills, from other repositories
agent-builder
Load before calling build-agent for a new or existing n8n Agent. Governs prerequisite creation, faithful handoff of the user's request, agent targeting across turns, builder questions, testing, and publishing. Use directly for routine follow-ups when the conversation already targets an Agent; rerun intent-recognition…
config-evals
Builds and maintains configuration-based evaluations on a workflow with the eval-config tool. Use when the user asks to set up, add, view, change, or remove an evaluation, score, grade, or judge a workflow's output, or measure answer quality against a test dataset. This is the only eval form Instance AI handles — it…
layer-testing
Generate comprehensive tests for architectural layers with coverage-first analysis. Use when testing specific layers (core, domain, application, infrastructure, boundary). Reads testing strategy from playbook or uses interactive template selection.
verify-no-regressions
Verify no behavioral regressions after implementation. Spawns parallel subagents for semantic diff review + test execution. Use when: user says "verify no regressions", "check for regressions", "make sure nothing broke".
await-merge
Wait for a PR's checks, merge it with linear history, update the local base branch.
screen-use
A Windows desktop automation skill for clicking controls, entering text, using keyboard shortcuts, scrolling, and taking screenshots. It can also carry out multi-step tasks through visual guidance.