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-docsnpx skills add Go1c/workflow-plugin --skill workflow-docsgit 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 | $0.00056 | $0.00975 |
| Opus 5 | $0.00028 | $0.00487 |
| Sonnet 5 | $0.00011 | $0.00195 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
workflow-docs 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.
- 涉及具体端点时,给出 **operationId** 和人读参考页链接:`https://workflow.games/wiki/api/<operationId>`(页面上有 curl 示例,用户可直接照抄)。 What it actually says
workflow-docs — 查 Workflow 文档并作答
铁律:必须抓取来源作答,不凭记忆
平台迭代快,你记忆里的端点、字段、枚举很可能已经过期。每个答案都要有当次抓取的来源支撑;抓不到就说抓不到,不编。
三级下钻
按 workflow-ops/references/connection.md 第三节的 L1 → L2 → L3 阶梯抓取:L1 文档索引 → L2 人读指南(多数问题到这层就够)→ L3 OpenAPI 合同(13000+ 行,grep 定位后分段读,不要整读)。「究竟哪个字段必填」「枚举到底有哪些值」以 L3 为准。
回答口径
- 涉及具体端点时,给出 operationId 和人读参考页链接:
https://workflow.games/wiki/api/<operationId>(页面上有 curl 示例,用户可直接照抄)。 - 讲字段含义时注明来源层级(哪份 guide / 合同哪个 schema),让用户可复核。
- 支不支持某能力:以当次抓取的合同为准——合同里没有就回答「当前合同没有这个能力」,不猜测未公开的 roadmap,不替平台承诺「以后会有」。
- 错误码含义:结合 ProblemDetails 结构解释(
title/detail/traceId),常见约定——401 未认证、403 权限不足、422 字段问题、423 项目冻结、429 限流(看Retry-After)。
本地草稿、权限与关系能力
用户询问本地优先创单、权限模式、bundle 上传或依赖关系时,回答前仍必须按本技能的三级阶梯 抓取当次线上指南和 OpenAPI;不要把以下快照当成未来合同:
- 客户端策略支持
plan、manual、auto(默认)和full。它只控制写入授权,不扩大 PAT scope;项目.workflow-policy只能降权,不能把用户级策略升到full。 .workflow-drafts/<bundleId>/是本地 outbox。workflow-upload使用有界并发 worker pool, 默认 4、上限 8;每个操作必须幂等、按 DAG 等待依赖并写后读回。并发上传是客户端行为,不能 从文档推断平台提供“批量事务”或无限并发。- 当前合同中 WorkItem 依赖使用
POST /schedule/relations,仅支持finish_to_start, 通过/schedule/snapshot?sections=relations读回;/object-links不是需求引用写入口。 - Requirement 引用现有正式 API:
bindRequirementReference(PUT)、unbindRequirementReference(DELETE)和getRequirementGraph(GET)。引用是无向且幂等的;依赖方向仍由workflow-dependencies分析,不能从图谱source/target推断。若当次线上 OpenAPI 尚未同步, 以平台正式提示词为暂时契约并在回答中标注部署时差,不改用猜测的其它 endpoint。绑定首次 返回 201、重复绑定 200;解除存在或不存在均返回 204;图谱最多 300 节点,truncated=false才表示完整投影。
从「问」变「做」
用户从询问转为要实际执行操作(建需求、记 bug、改状态……)时,转 workflow-ops 技能;需要先接入或修连接问题时转 workflow-setup。用户不是在问用法,而是要向平台方报问题、提体验或功能建议(平台缺陷、太卡太慢、希望加功能)时,转 workflow-feedback。本技能只答疑,不执行写操作。
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 · 45 lines · 56 tokens per session scan A 843661d3757b
workflow-docs is a skill published in the GitHub repository Go1c/workflow-plugin (2 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 975 once invoked, about $0.0003 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.