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 rexleimo/aios --skill aios-workflow-routergit clone --depth 1 https://github.com/rexleimo/aiosWrote 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/rexleimo/aios/aios-workflow-router)<a href="https://agentmods.dev/skills/rexleimo/aios/aios-workflow-router"><img src="https://agentmods.dev/badge/skills/rexleimo/aios/aios-workflow-router.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 | $0.00104 | $0.01490 |
| Opus 5 | $0.00052 | $0.00745 |
| Sonnet 5 | $0.00021 | $0.00298 |
| Haiku 4.5 | $0.00010 | $0.00149 |
Grade A, and why
aios-workflow-router 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIOS Workflow Router
这个 Skill 只协调宿主路由和 rex 返回的当前命令，不拥有软件工程步骤顺序。路由由显式声明与 workflow-policy 的结构化 Decision 驱动，不根据任务文本关键词自行判断。
所有权
- AIOS：
direct | guarded | planned、最终 Provider Binding、计划和 Activation 持久化、Skill/Agent/模型执行、安全、验证、Team、Harness、恢复和重试。 - rex-harness：Observation -> Fact、Capability 选择、Capability Recipe、Evidence Contract、下一条语义 Command、软件 Workflow Recipe，以及独立可用的 rex-native Provider；AIOS 不再绑定外部兼容 Provider。
- Skill / Playbook / Agent：执行已经选中的一个阶段，不根据关键词自行激活，也不决定后续阶段。
显式声明协议
disposition 由显式声明驱动，模型不猜"用户是否想只读/是否要计划/是否多步"：
- 用户带 workflow 命令前缀（
/plan/single/implement/review/debug/spec/grill/tickets/team/harness）时，把声明的 intent 透传给 workflow-policy；/single= direct、不建计划。 - 用户说
继续/接着做/下一步/resume/continue（带非空 tail）→ 新目标；裸确认（好/可以/确认/ok）→ 继续同会话活动计划。 - 只读场景由调用方显式声明
explicit-intent: read-only，不靠"解释/说明"等词判断。 - 模型自身需要时也可显式声明 intent（如
/implement覆盖 capability 默认计划），但不得用关键词表假装识别。
路由流程
- 先读取 AIOS workflow-policy 的结构化 Decision。
- 项目已安装 codemap（存在
.code-review-graph/或 CRG MCP 工具可用）时，在执行任何 Provider 之前先调用 CRG 决策检查点（详见 AGENTS.md codemap 段落）：- 动手前：
get_minimal_context(task="<当前任务>")获取项目上下文和建议下一步； - 改文件前：
get_impact_radius(detail_level="minimal")检查爆炸半径，query_graph(pattern="tests_for", target="<目标>")确认测试存在； - 查找代码/关系：
semantic_search_nodes/query_graph（callers_of/callees_of/imports_of）优先于 grep/读文件； - 阶段结束后：
detect_changes(detail_level="minimal")验证实际影响与预期一致。 加速入口：CRG 预置工作流可直接list_prompts查看、get_prompt(name="...")加载（如 review_changes、debug_issue、pre_merge_check），不必自行编排。 CRG 不可用时记录该事实，降级为rg搜索 + 读文件，不阻塞流程、不伪造图证据。
- 动手前：
direct：只读回答，不创建计划，不启动 Capability 链。guarded：执行当前capabilityDecision.provider；如果当前阶段会改文件，先执行pre-edit-safety-gate。planned：创建或复用一个 AIOS 工作项，然后仍然只执行当前 Provider。- Provider 完成后，把 Command 要求的 Evidence Kind 和 Artifact Ref 写回 Activation Ledger。
- 由 rex 推进 Activation：
blocked：补齐明确列出的缺失 Evidence；next：执行新 Command 的一个 Provider；completed：关闭当前 Capability，并让 AIOS 自动评估下一个 Capability；- Promotion Request：由 AIOS 决定是否接受 Team 或 Harness 升级。
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 Changed · +9 lines · +51 tokens per session e29483b3bc16
- 8d ago First seen · 70 lines · 53 tokens per session scan A 3d993c07344b
aios-workflow-router is a skill published in the GitHub repository rexleimo/aios (52 stars, last pushed today), licensed MIT. It adds 104 tokens to every session and 1,490 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
vs-user-onboarding
Guide a brand-new SearchCLI/vs user from first-time usage questions to sign-up, purchase of Viking AI Search, AK/SK setup, and a working authenticated CLI. Use when the user says they downloaded or installed SearchCLI/vs and asks how to use it, how to start, sign up, buy, or onboard.
vs-crawler
Crawl websites (news, blogs, papers, GitHub, product docs, RSS feeds) into a fixed-schema JSONL file, then create a dataset and a searchable application in Viking AI Search. Supports one-time crawl and scheduled recurring crawl with automatic incremental sync.
vs-project
Create Viking web projects, start and verify a local preview, or deploy a generated project to Volcengine IGA Pages when explicitly requested. Includes agent-guided feature, eligible application, dataset, scene, and authentication choices. Use only after confirming the installed CLI exposes vs project; otherwise stop…
vs-item-onboarding
Match the language of the user's most recent message in every line of prose you write — confirmation prompts, status notes, hand-off summaries, questions, error explanations, and any internal thinking / reasoning / planning output that the host may surface (e.g. blocks, "thinking" panels, scratchpad notes, todo…
ospec
Document-driven OSpec workflow for initialization, change/goal routing, validation, archiving, and durable project knowledge.
new-gh-issue-orchestration
Orchestrates a GitHub-issue-driven delivery workflow from issue intake to PR creation using reviewer-first then worker execution. Invoked when the user provides a GitHub issue link/number and asks to start end-to-end delivery.