aios-exec

aios-exec is a skill for Claude Code, Codex from ArchSightLabs/archsight-aios. It costs 54 tokens per session (1,511 once invoked), scanned A, original, Apache-2.0.

A controlled workflow for carrying out clearly defined changes and checks in a project workspace. It covers code, bug fixes, documentation, scripts, tests, linting, type checks, builds, interface changes, and deployment preparation.

In plain words
What is it for?
Use it to implement a requested change, run the project’s checks, investigate failed tests or review comments, prepare deployment work, and report the modified files and verification results.
Why use it?
It keeps changes within an agreed scope and records how the result was verified. It also protects existing uncommitted work and makes failures, remaining risks, and human review needs visible.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions AGENTS.md; mentions Gemini CLI.

Part of the archsight-aios plugin — 33 skills shipped together

Good fit Use it to implement a requested change, run the project’s checks, investigate failed tests or review comments, prepare deployment work, and report the modified files and verification results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/archsightlabs/archsight-aios/aios-exec
Install

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.

Any agent
npx skills add ArchSightLabs/archsight-aios --skill aios-exec
Clone the repo
git clone --depth 1 https://github.com/ArchSightLabs/archsight-aios

Made for: Claude Code, Codex.

Or install archsight-aios, the plugin that ships this one along with the rest of its 33 skills.

Wrote 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.

agentmods badge for aios-exec

README.md
[![agentmods](https://agentmods.dev/badge/skills/archsightlabs/archsight-aios/aios-exec.svg)](https://agentmods.dev/skills/archsightlabs/archsight-aios/aios-exec)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,511 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.01511
Opus 5 $0.00027 $0.00756
Sonnet 5 $0.00011 $0.00302
Haiku 4.5 $0.00005 $0.00151

Measured 8d ago against content hash 350be1fd4dbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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 8d 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.

skills/aios-exec/SKILL.md · 122 lines

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

  1. 读取项目约定:优先 AGENTS.mdGEMINI.md、README、Makefile、scripts。
  2. 明确验收标准:功能、测试、构建、文档或人工验证。
  3. 定位相关文件;不要无差别重构。
  4. 做最小改动;复用现有工具和模式。
  5. 运行合适验证:lint、typecheck、test、build、脚本或人工检查。
  6. 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。
  7. 验证失败时继续迭代;无法继续时说明阻塞和证据。
  8. 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:

  1. 先扫描路由、导航、API、共享契约、测试和构建依赖。
  2. 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。
  3. 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。
  4. 同步清理无效依赖、构建分包、测试和文档事实。
  5. 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:

  1. 读取最终 diff,确认没有混入用户原有变更。
  2. 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。
  3. 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。
  4. 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。
  5. 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:

  1. 变更摘要
  2. 修改文件
  3. 验证结果
  4. Tool Result / Decision
  5. 剩余风险
  6. 后续动作

Read the full file on GitHub · 122 lines

Files

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.

Changes

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.

  1. 8d ago First seen · 122 lines · 54 tokens per session scan A 350be1fd4dbf

Subscribe to this mod's changes

aios-exec is a skill published in the GitHub repository ArchSightLabs/archsight-aios (14 stars, last pushed 11d ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,511 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 2026-08-30.

Related

Other skills, from other repositories

tauri-errors-ipc

Use when encountering invoke errors, serialization failures, or IPC-related panics in Tauri 2. Prevents silent type mismatches between Rust and JavaScript and missing Serialize on error types. Covers serialization failures, command not found, argument type mismatches, permission denied, async panics, and thiserror…

OpenAEC-Foundation/OpenAEC-Workspace-Composer · 94 tokens

tauri-errors-permissions

Use when encountering permission denied errors, CSP violations, or capability configuration issues in Tauri 2. Prevents confusing core permissions with plugin permissions and missing scope restrictions on sensitive plugins. Covers capability misconfiguration, missing plugin permissions, scope violations, CSP…

OpenAEC-Foundation/OpenAEC-Workspace-Composer · 82 tokens

tauri-errors-runtime

Use when encountering runtime panics, state errors, or unexpected app crashes in Tauri 2. Prevents unhandled unwrap() panics in production and unmanaged state type mismatches that crash the app. Covers window not found, state not managed panics, plugin not initialized, asset resolution, event name validation, and…

OpenAEC-Foundation/OpenAEC-Workspace-Composer · 97 tokens

vite-errors-dev-server

Use when encountering dev server startup failures, HMR issues, proxy errors, CORS blocks, or module not found errors during development. Prevents misconfiguring server.hmr behind reverse proxies and forgetting appType: 'custom' in middleware mode. Covers HMR full-reload debugging, proxy configuration, CORS setup…

OpenAEC-Foundation/OpenAEC-Workspace-Composer · 124 tokens

solid-core-reactivity-model

Use when reasoning about SolidJS reactivity, debugging tracking issues, or understanding why components run once. Prevents React mental model contamination such as expecting re-renders, virtual DOM diffing, or stale closure patterns. Covers reactive dependency graph, tracking contexts, ownership tree, synchronous…

OpenAEC-Foundation/OpenAEC-Workspace-Composer · 97 tokens

solid-errors-reactivity-debugging

Use when SolidJS reactivity is broken, effects are not firing, or store updates are not reflected in the UI. Prevents lost tracking from destructuring, conditional signal access, async tracking loss, and stale closures. Covers diagnostic flowcharts, solid-devtools debugging, effect tracking issues, store propagation…

OpenAEC-Foundation/OpenAEC-Workspace-Composer · 104 tokens