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-uploadnpx skills add Go1c/workflow-plugin --skill workflow-uploadgit 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 | $0.00050 | $0.01204 |
| Opus 5 | $0.00025 | $0.00602 |
| Sonnet 5 | $0.00010 | $0.00241 |
| Haiku 4.5 | $0.00005 | $0.00120 |
Grade A, and why
workflow-upload 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
workflow-upload — 草稿上传与恢复
处理 .workflow-drafts/<bundleId>/，先读取 draft-format.md、
permission-modes.md、
dependency-model.md 和
relation-provider.md。
上传顺序
- 校验 manifest、卡片、附件、策略快照和操作 DAG；
plan模式在此停止。 - 按 connection 规则验证
/me、/projects/current和三方项目一致性。 - 在任何 POST/PATCH/PUT/DELETE 前重新执行项目级全局搜索；search 未命中仍须翻列表到空。
- 精确 marker/UUID 自动幂等复用；已有单默认追加结构化评论。只有 manifest 明确
update且授权时才 PATCH 原正文，并带expectedUpdatedAt。 - 按依赖拓扑创建 Room、需求、WorkItem/bug 和其它节点；独立 wave 进入并发队列，真实共享 热点与有前置的操作必须等待前置完成。不要把依赖边当成可并行提示。
- 解析真实 UUID/displayKey/deepLink 后创建验收项、评论和附件；不同目标之间可并发，最后
通过 Provider 写入直接边。Requirement direct edge 调用原生
bindRequirementReference，再用getRequirementGraph读回；图谱中的引用边是无向的， 依赖方向仍以 manifest 的 upstream/downstream 为准。 - 每个写操作后立即 GET 读回，更新 checkpoint 和 events.ndjson。完整完成才清理 bundle。
受控并发上传（默认开启）
上传器必须使用有界 worker pool 发出多个异步请求，不得把整批对象一个一个串行上传。 这就是“多线程上传”的协议实现：并发的是网络操作，依赖、幂等和读回仍按单操作维护。
- manifest 可在
upload.concurrency指定并发度；缺失时默认为4，允许范围1–8，超出范围 停止并报告。1仅用于平台临时限流或用户明确要求串行。 - 每个 worker 一次只处理一个
opId。调度器只派发pending且所有dependsOn已verified的 操作；同一资源的 PATCH、附件和评论按资源锁串行，互不相关的资源可同时进行。 - Requirement 引用操作按“引用关系组”归并资源锁；同一无序 UUID 对的 bind/unbind 不能并发，
不同 UUID 对可以并发。
manual只确认关系组，不逐边询问。 - 创建节点必须先完成并读回，再释放其子资源；关系操作必须等待两端 UUID 都已读回。一个 wave
中的失败不会阻塞没有依赖它的其它操作（继续执行没有依赖它的操作），但依赖它的操作保持
blocked，不能越过 DAG。 - 并发请求仍各自使用确定性的幂等 key、超时和重试上限；429 按
Retry-After降低并发或退避， 423/401/403/409/422 按共享失败表处理。不得因为并发而重复发送或复用别的操作的 key。 - 每次请求完成（成功、失败或被阻塞）都原子更新 manifest checkpoint 和
events.ndjson；进程 中断后只恢复未verified的操作。读回必须在 worker 内完成，不能先宣称整批成功再补读。 - 输出和收尾报告同时列
concurrency、已完成/失败/阻塞数量、每个操作的读回结果；部分成功 保留 bundle，不能因某个 worker 失败而删除已落库对象。
模式行为
auto：显式调用本命令后，展示项目、数量、复用/新建清单、边数量和并发度，只确认一次 bundle。manual：每个操作组展示 endpoint、目标、字段 diff 和关系 metadata，逐组确认。full：草稿 ready 后自动进入本流程，不询问，但仍执行所有安全闸门、受控并发和读回。
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 · 62 lines · 50 tokens per session scan A 019ac5f4c8e7
workflow-upload is a skill published in the GitHub repository Go1c/workflow-plugin (2 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 1,204 once invoked, about $0.0003 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 2026-08-31.
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.