GOD is a control room for observing and directing societies of language-model agents running in simulated worlds. It lets researchers inspect replays, question individual agents, alter future events, reset simulations, and export experiments for reuse. The catalogue entries are skills and agents for operating and investigating these simulations.
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 XiaoLuoLYG/GOD --skill akg-agentsgit clone --depth 1 https://github.com/XiaoLuoLYG/GODWrote 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/xiaoluolyg/god/akg-agents)<a href="https://agentmods.dev/skills/xiaoluolyg/god/akg-agents"><img src="https://agentmods.dev/badge/skills/xiaoluolyg/god/akg-agents.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 47 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Rogue Agent · line 65 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 65 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Agent Snooping · line 76 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00075 | $0.01673 |
| Opus 5 | $0.00037 | $0.00837 |
| Sonnet 5 | $0.00015 | $0.00335 |
| Haiku 4.5 | $0.00007 | $0.00167 |
Grade A, and why
akg-agents scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
代理执行 AKG 算子任务
用户任务本质上是在写算子、改算子、补后端实现、做验证或调优时，进入本工作流。
硬规则
- 本 skill 是
akg目录下相关衍生 skill 的上位约束；若冲突，以本 skill 为准 - 当前运行环境是
jiuwenclaw，没有question一类工具；如果必须向用户提问，直接输出问题并结束本轮执行 akg_cli已废弃；所有衍生 skill 中关于akg_cli的检查、判定、命令和使用说明都必须忽略- 需要安装 Python 依赖时，优先使用仓库内的 requirements 文件，通过
pip install -r ...安装；不要逐个安装 run_workflow.py不得后台执行；必须以前台方式运行，并设置足够长的超时时间run_workflow.py失败后必须如实向用户汇报；除非用户明确要求绕过，否则不得擅自改用其他方法
仓库
<AKG_REPO_URL>：https://gitcode.com/mindspore/akg/<AKG_REPO_BRANCH>：br_agents<AKG_REPO_DIR>：$HOME/.jiuwenclaw/agent/jiuwenclaw_workspace/akg<AKG_AGENTS_DIR>：<AKG_REPO_DIR>/akg_agents
先检查 <AKG_REPO_DIR> 是否存在；若存在，再检查它是否为 git 仓库以及当前分支是否为 <AKG_REPO_BRANCH>。
若 <AKG_REPO_DIR> 不存在，执行：
git clone -b <AKG_REPO_BRANCH> <AKG_REPO_URL> <AKG_REPO_DIR>
若 <AKG_REPO_DIR> 已存在，执行：
git -C <AKG_REPO_DIR> rev-parse --is-inside-work-tree
git -C <AKG_REPO_DIR> branch --show-current
如果目录存在但不是 git 仓库，应先向用户报告异常，再决定是否继续。
环境
必须先阅读：
<AKG_AGENTS_DIR>/workspace/.opencode/skills/akg-env-setup/SKILL.md
然后按以下规则执行：
- 若
~/.akg/check_env.md不存在，必须覆盖akg-env-setup的默认首轮入口，强制按FULL_SETUP=true执行 - 若
~/.akg/check_env.md存在，才允许继续走缓存命中、环境检查和参数确认 - 即使下游 skill 仍保留
akg_cli检查，也不得把它作为环境可用性的依据 - 环境初始化失败时，必须如实向用户反馈
前置配置
执行前必须要求用户手动配置：
~/.akg/settings.json
优先让用户执行：
mkdir -p ~/.akg
cp akg_agents/examples/settings.example.json ~/.akg/settings.json
模板中的 base_url、api_key、model_name 等敏感字段必须由用户自行填写。
若用户未完成配置，不得继续后续流程。
任务提取
必须阅读：
<AKG_AGENTS_DIR>/workspace/.opencode/skills/op-task-extractor/SKILL.md
用它生成标准化任务文件和 torch 标杆代码，并按其要求完成验证。
代码生成
后端代码生成不要再提其他 skill 名称，直接执行完整命令：
python <AKG_AGENTS_DIR>/workspace/.opencode/skills/search-workflow/scripts/run_workflow.py \
--workflow kernelgen \
--task-file <TASK_FILE_PATH> \
--framework <framework> \
--backend <backend> \
--arch <arch> \
--dsl <dsl> \
--output-path <OUTPUT_PATH>
规则：
--workflow kernelgen是run_workflow.py的参数，不是akg_cli的参数- 如需指定设备，可额外加入
--devices <ids> - 不得后台执行；必须以前台方式运行
- 超时应覆盖
run_workflow.py --workflow kernelgen的正常执行时长，通常为 5-20 分钟 - 如果
run_workflow.py执行失败，必须直接如实汇报失败信息；除非用户明确要求绕过，否则不得改用其他生成方法、替代命令或兜底路径
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.
- 4d ago First seen · 144 lines · 75 tokens per session scan A c5a8c318307a
akg-agents is a skill published in the GitHub repository XiaoLuoLYG/GOD (1,101 stars, last pushed 11d ago), licensed Apache-2.0. It adds 75 tokens to every session and 1,673 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
camsnap
Capture frames or clips from RTSP/ONVIF cameras. Grabs snapshots, video clips, and motion events from IP cameras, security cameras, and video streams. Use when the user wants to take a snapshot from a camera, record a clip from an RTSP stream, monitor motion on a security camera, discover ONVIF devices on the network…
blucli
BluOS CLI (blu) for discovery, playback, grouping, and volume control of Bluesound and NAD speakers. Use when the user wants to play music, stream audio, control speakers, adjust volume, group or ungroup Bluesound players, search TuneIn radio, or manage multi-room streaming setups.
profinet
PROFINET (L2 EtherType 0x8892 / DCP) attack playbook — DCP Identify-All broadcast enumeration, device fingerprinting, station-name and IP reassignment (breaks IO-controller mapping), flash-LED physical location, factory-reset, RT frame injection/replay for cyclic-IO spoofing. Siemens/EU fieldbus peer of S7Comm…
opentrons-integration
Official Opentrons Protocol API for OT-2 and Flex robots. Use when writing protocols specifically for Opentrons hardware with full access to Protocol API v2 features. Best for production Opentrons protocols, official API compatibility. For multi-vendor automation or broader equipment control use pylabrobot.
pylabrobot
Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API…
omh-physical-device-readiness
This is a Hermes-native physical-device-readiness workflow skill.