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/go1c/workflow-plugin/workflow-executenpx skills add Go1c/workflow-plugin --skill workflow-executegit clone --depth 1 https://github.com/Go1c/workflow-pluginWhat 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 | $0.00150 | $0.02384 |
| Opus 5 | $0.00075 | $0.01192 |
| Sonnet 5 | $0.00030 | $0.00477 |
| Haiku 4.5 | $0.00015 | $0.00238 |
Grade A, and why
workflow-execute scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
流程细节与全部 curl 模板见 [references/execute-flow.md](references/execute-flow.md)。 How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
workflow-execute — 拿单、执行、交回
以执行者身份消费一张已存在的单：找到它 → 读全它 → 核对前置 → 梳理需求、把决策点摆给用户讨论 → 流转开工 → 干活（能并行就并行子 Agent）→ 回写证据 → 流转待验收 → 交回。拿单不是落单：本技能不创建需求/Room，发现该建新单时报给用户转 workflow-ops 或 workflow-planning；唯一的建单义务是收尾时的遗留补单（这次不做的 TODO / 降优先级项），也必须经用户确认后按 card-spec 走 workflow-ops 落单，不许扩写范围。
读取 permission-modes.md 和 draft-format.md。状态流转、证据评论、附件和遗留补单的 PM 写入先进入 bundle；auto 在当前卡的写回清单上一次确认，full 自动上传，plan 只返回交回报告，manual 逐组确认。
硬闸门（命中即停）
以下 7 条是停止条件，不是风格建议；与正文其他要求冲突时以这里为准（出处 workflow-ops/references/gates.md）。
| # | 触发条件 | 动作 |
|---|---|---|
| G1 | project.subdomainPrefix、实际 API Host、.workflow 所选 profile 的子域三者任一不一致；或 publicDemo=true；或 .workflow 存在却解析不出 profile |
停止，转 workflow-setup 重新绑定。绝不把数据写进错误项目 |
| G2 | 用户尚未针对确切的项目 + 对象清单 + 数量给出明确肯定答复，且当前模式没有有效的用户级 full standing authorization |
不得 POST/PATCH。内容认可、说"不错"、说"继续"都不是写入授权；full 也只覆盖已校验的 manifest；范围一变授权即失效 |
| G3 | 写操作之后没有 GET 读回，或读回未核对字段与子资源数量 |
不得声称「已创建 / 已修改」。部分成功如实报部分成功 |
| G4 | 需要在命令、日志、报告、蓝图里出现 token | 只走环境变量携带；任何输出里只以 wfp_ + 前 8 位指代，绝不回显完整值 |
| G5 | 出现拆 WorkItem、流转状态、建分支/Worktree、跑目标仓库测试、改代码或资产的冲动 | 停止。落单不等于开工，本插件只负责 PM 对象 |
| G6 | 需要填工作流状态、验收类型/状态、成员 ID、缺陷自定义字段等项目自定义的值 | 必须现查。查不到或不唯一就留空并告诉用户，绝不猜一个值填进去 |
| G7 | 要在报告里写某项验证「通过」 | 只写实际执行过的命令与其真实输出；没跑的写「未执行」，不得用计划中的验证冒充结果 |
G1、G3、G4、G6、G7 全程适用。G2 的写入授权由用户明确指派这张单给出；若当前是用户级 full，standing authorization 只覆盖 manifest 中这张卡的确切操作清单，范围一变重新确认。G5 在本技能是授权例外——它管的是落单场景，而执行恰恰要开工，但例外只覆盖两件事：承接的这张卡自己的状态流转 + 完成后的证据回写（评论/附件）。改代码、建分支、跑测试发生在目标仓库、由派遣任务本身授权，不归本插件管辖；仍然禁止：替未承接的卡流转、把拿单扩写成落单或拆卡、改单据 description、动验收项状态（那是验收方的 run_acceptance）、验收自己的交付（转 workflow-qa 或人工验收）。
第一步：判定执行模式（先于一切 API 调用）
按 connection.md 解析凭证，然后分流：
- 模式一 · 自持凭证直连：环境变量或
.workflow两级解析成功且/me、/projects/current验证通过 → 读写全程自己做。 - 模式二 · 无凭证，调度方代写：派遣 prompt 明示「凭证在调度方 / 由调度方回写」，或本机解析不出凭证 → 不调任何 Workflow API。卡内容以派遣 prompt 附带的为准；交回物是 references/handoff.md 第二节的结构化报告，由调度方代做全部回写。不要求用户或调度方把 token 贴进会话（要配凭证转 workflow-setup）。
What ships with it
2 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.
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 First seen · 54 lines · 150 tokens per session scan A 37f53d5f72f8
workflow-execute is a skill published in the GitHub repository Go1c/workflow-plugin (2 stars, last pushed 2d ago), licensed MIT. It adds 150 tokens to every session and 2,384 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
golden-rss
Use when testing the rss golden build.
omh-code-review
This is a Hermes-native code-review workflow skill.
hyperpod-version-checker
Check and compare software component versions on SageMaker HyperPod cluster nodes - NVIDIA drivers, CUDA toolkit, cuDNN, NCCL, EFA, AWS OFI NCCL, GDRCopy, MPI, Neuron SDK (Trainium/Inferentia), Python, and PyTorch. Use when checking component versions, verifying CUDA/driver compatibility, detecting version mismatches…
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.