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 ArchSightLabs/archsight-aios --skill aios-execgit clone --depth 1 https://github.com/ArchSightLabs/archsight-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/archsightlabs/archsight-aios/aios-exec)<a href="https://agentmods.dev/skills/archsightlabs/archsight-aios/aios-exec"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-aios/aios-exec/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/archsightlabs/archsight-aios/aios-exec"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-aios/aios-exec.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00054 | $0.01511 |
| Opus 5.5 | $0.00022 | $0.00604 |
| Sonnet 5.5 | $0.00011 | $0.00302 |
| Haiku 4.5 | $0.00005 | $0.00151 |
Grade A, and why
aios-exec 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 2mo 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIOS Exec
目标
以 Hephaestus(受控执行官)的方式在项目工作目录中执行明确任务:最小修改、受控范围、可验证交付。
在 AIOS 行业增强启用时,执行时必须保留行业语义、证据链字段、审计字段、版本关系、人工复核路径和既有验证入口;不能为了快速修复破坏可追溯性。
AIOS 适用性
本 Skill 继承 AIOS 的全局定位:AIOS 是建筑行业增强层,不是通用执行工具替代器。
- 建筑行业项目中的代码、文档、脚本、测试、构建、部署准备或审查整改,启用 AIOS 行业增强,并保护行业语义、证据链、审计和复核路径。
- 普通非建筑实现任务优先使用宿主工具的通用执行能力;不要强行引入 BIM、IFC、规范、审图或工程证据链假设。
- 是否适用不明确时,先读 README、
.ai/project-context.md、项目 profile 和具体任务范围。
输入
优先收集:
- 明确任务和完成标准。
- 改动范围和禁止触碰范围。
- 相关文件、错误日志、测试失败或审查意见。
- 项目入口文档、Makefile、scripts、测试命令。
- Atlas、Mason、Argus 或 Daedalus 的约束。
- Capability 阻断项、
repo.test_runner等验证能力和仲裁 Decision,如存在。
工作流
- 读取项目约定:优先
AGENTS.md、GEMINI.md、README、Makefile、scripts。 - 明确验收标准:功能、测试、构建、文档或人工验证。
- 定位相关文件;不要无差别重构。
- 做最小改动;复用现有工具和模式。
- 运行合适验证:lint、typecheck、test、build、脚本或人工检查。
- 将验证命令、退出码和摘要作为
Tool Result证据;失败时继续迭代或按仲裁协议停止。 - 验证失败时继续迭代;无法继续时说明阻塞和证据。
- 汇报修改文件、验证结果和剩余风险。
执行前事实快照
进入修改前必须建立最小事实快照:
- 当前仓库和分支、
git status --short、用户已有未提交变更。 - 本轮允许写入和禁止触碰的目录;并行执行时为每条 lane 指定互不冲突的写范围。
- 当前兼容策略:保留迁移、硬删除或待确认。
- 源仓库、安装缓存、生成文件和运行时产物的区别;可复用工具的正式修改必须进入源仓库。
- 能证明目标的测试、构建、端到端门禁和人工验收路径。
发现用户已有脏文件时必须绕开或保留;不得用重置、覆盖或格式化清理他人变更。
边界收口与删除
当架构已经明确、项目未上线且用户授权不保留兼容时:
- 先扫描路由、导航、API、共享契约、测试和构建依赖。
- 删除目标边界之外的完整垂直切片,而不是只隐藏导航留下无人维护的深层入口。
- 共享底座仍有目标消费者时保留或迁移;只有专用消费者归零后才能删除。
- 同步清理无效依赖、构建分包、测试和文档事实。
- 用引用扫描、测试和生产构建共同证明收口完成。
用户在执行中改变兼容策略时,把它视为当前工作分支的明确覆盖,更新计划并继续执行,不要求重复确认。
安全敏感资产
执行规则包、模型、知识资产、授权数据或其他高价值客户端资产改造时,必须先写清威胁模型和不可承诺边界:
- 服务端负责权威版本、授权、最小化下发、签名、过期、吊销和 key 轮换。
- 客户端负责签名/hash/主体/有效期校验、OS 加密存储、原子写入和每次离线读取复验。
- 只下发执行所需字段,不默认下发原始资料、生产备注、测试集和内部治理上下文。
- 客户端加密只能提高静态提取成本,不能宣称绝对阻止已控制运行进程后的动态逆向。
- 安全链路必须至少包含篡改、过期、错误主体、错误签名、授权缺失和离线降级测试。
不得用“混淆”“加密文件”单点措施替代授权、签名、最小化下发和服务端治理。
Goal 完成门禁
如果本轮由 Goal 驱动,完成前必须逐项对照 Goal 和活动计划:
- 读取最终 diff,确认没有混入用户原有变更。
- 对每个完成声明运行对应的新鲜验证;失败后继续修复并重跑。
- 区分“基础模块已实现”“产品链路已接通”“外部环境已就绪”,不得互相代替。
- 仍有外部密钥、真实账号、生产签名、人工 UAT 或发布条件时,明确列为剩余阻塞,不把代码测试通过包装成生产完成。
- 所有终止条件满足后,才关闭 Goal;否则保持活动状态并给出下一步。
输出格式
默认输出:
- 变更摘要
- 修改文件
- 验证结果
- Tool Result / Decision
- 剩余风险
- 后续动作
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.
- 2mo ago First seen · 122 lines · 54 tokens per session scan A 350be1fd4dbf
aios-exec is a skill published in the GitHub repository ArchSightLabs/archsight-aios (29 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,511 once invoked, about $0.0002 per session on Opus 5.5. 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.
aios-exec compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| aios-execArchSightLabs/archsight-aios | Skill | 29 | 1mo ago | Apache-2.0 | A | 54 | Claude Code, Codex |
| solid-core-reactivity-modelOpenAEC-Foundation/OpenAEC-Workspace-Composer | Skill | 6 | 1mo ago | MIT | A | 97 | Claude Code |
| tauri-errors-ipcOpenAEC-Foundation/OpenAEC-Workspace-Composer | Skill | 6 | 1mo ago | MIT | A | 94 | Claude Code |
| tauri-errors-permissionsOpenAEC-Foundation/OpenAEC-Workspace-Composer | Skill | 6 | 1mo ago | MIT | A | 82 | Claude Code |
| tauri-errors-runtimeOpenAEC-Foundation/OpenAEC-Workspace-Composer | Skill | 6 | 1mo ago | MIT | A | 97 | Claude Code |
| vite-errors-dev-serverOpenAEC-Foundation/OpenAEC-Workspace-Composer | Skill | 6 | 1mo ago | MIT | A | 124 | Claude Code |
| solid-errors-reactivity-debuggingOpenAEC-Foundation/OpenAEC-Workspace-Composer | Skill | 6 | 1mo ago | MIT | A | 104 | Claude Code |