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-recoverygit 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-recovery)<a href="https://agentmods.dev/skills/mrpulor-gh/nuphus/workflow-recovery"><img src="https://agentmods.dev/badge/skills/mrpulor-gh/nuphus/workflow-recovery/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.
<a href="https://agentmods.dev/skills/mrpulor-gh/nuphus/workflow-recovery"><img src="https://agentmods.dev/badge/skills/mrpulor-gh/nuphus/workflow-recovery.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00868 |
| Opus 5.5 | $0.00000 | $0.00347 |
| Sonnet 5.5 | $0.00000 | $0.00174 |
| Haiku 4.5 | $0.00000 | $0.00087 |
Grade A, and why
workflow-recovery 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 3d 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.
What it actually says
工作流故障恢复
何时读：
workflow_run返回{"failed":true,...}时。 核心判界：运行时阻塞就地解决，设计缺陷才改文件。
处置顺序
- 识别阻塞：解析
error归类——验证码 / 弹窗 / 登录态 / 网络 / 元素未出现。 - 就地解决（优先级从高到低）：
- 工具列表存在
desktop_agent_step（增强模式）→ 每个新桌面决策先调它；needs_primary_decision主模型直接从action_space选并执行；needs_input_value主模型补value；needs_observation先读新界面不重发。 - 无增强入口但有语义工具 →
desktop_semantic_observe/desktop_semantic_execute。 - 语义不可用 → 截图/OCR/坐标工具（最后手段）。
- 浏览器场景继续
browser_*。 - 探索成功后把候选返回的
workflow_step原样固化为desktop_semantic_action；禁止保存临时 token / candidate ID。 - 解决后状态即保留。
- 工具列表存在
- 断点续连：重新
workflow_run传同一 id——引擎自动跳过completed_steps，从失败步骤继续。禁止新建/复制/改名工作流来「重跑」。⚠️ 同 id 重跑复现同一失败时，先读下方「断点续连状态污染」，不要连续重试。 - 改文件判界：只有确认设计缺陷（参数/选择器/步骤逻辑错误）才改 workflow / params；运行时阻塞（验证码、弹窗、外部状态变化）一律就地解决，不靠改工作流规避。
- 重试上限：同一步骤同一阻塞连续失败 3 次 → 停止重试，用
completed_steps向用户汇报已完成进度与阻塞原因，等待指示。禁止无限重跑或整单重开。
失败重跑后
- 若因探索不全导致失败：补探索 → 更新 params.json
exceptions（W4）→ 再续跑。 - 恢复经验（非显而易见的解法）→
ui_maps_save_experience。
断点续连状态污染（capture 步骤被跳过）
症状：同 id 连续重跑在同一处失败（completed_steps 完全一致），修正参数/就地解决均无效。
根因：续跑跳过上次已成功的 capture 步骤且不重新生成其变量——下游读到的是上一次 run 的陈旧值（失效 hwnd、旧 query、旧坐标），必然复现同一失败。
判别证据（三占其二即可判定，不要继续改 workflow/params）：
- 本应产出的截图/文件不存在，重跑后仍未生成 → capture 步骤被跳过；
- 变量池里是陈旧值（对照上次 run 的时间戳）；
- 失败步骤的
run_history时长异常短（秒级）却列出大量步骤。
处置：清空该工作流的 run_history（置 []）→ 同 id 重跑，从头完整执行。
禁止：靠改步骤 id 绕过（上游 capture 变量依旧陈旧）；把它误判为设计缺陷去改 params。
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.
- 3d ago First seen · 43 lines · 0 tokens per session scan A bbc1c959ea85
workflow-recovery is a skill published in the GitHub repository mrpulor-gh/nuphus (85 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 868 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 2026-10-15.
Other skills, from other repositories
clawdcursor
FALLBACK ONLY — do not invoke unless you have already ruled out (1) a native API (Gmail API, GitHub API, Slack API …), (2) a CLI (git, gh, aws, npm, curl …), (3) direct file editing, and (4) existing browser automation (Playwright, Puppeteer). Only when all four are unavailable or have already failed should you use…
chrome-devtools
Expert-level browser automation, debugging, and performance analysis using Chrome DevTools MCP. Use for interacting with web pages, capturing screenshots, analyzing network traffic, and profiling performance.
computer-use
A set of rules for controlling Windows desktop applications through screen observation and simulated mouse and keyboard actions. It also describes how to find and launch installed applications and verify the results.
web-navigator
A browser-automation routing guide for web tasks. It directs navigation, page inspection, and actions such as clicking or filling forms to the appropriate browser tool.
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.
exo-control
Use when any AI needs eyes and hands on Windows — desktop UIA, browser CDP, files, registry, OS ops via Exo Control (MCP, CLI, or Python). Harness-agnostic.