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 HorizonRobotics/OE-Skills --skill j6-plugin-model-check-resultgit clone --depth 1 https://github.com/HorizonRobotics/OE-SkillsWrote 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/horizonrobotics/oe-skills/j6-plugin-model-check-result)<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-plugin-model-check-result"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-plugin-model-check-result/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/horizonrobotics/oe-skills/j6-plugin-model-check-result"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-plugin-model-check-result.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00068 | $0.02462 |
| Opus 5 | $0.00034 | $0.01231 |
| Sonnet 5 | $0.00014 | $0.00492 |
| Haiku 4.5 | $0.00007 | $0.00246 |
Grade A, and why
j6-plugin-model-check-result 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 12d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
分析 Horizon model_check_result.txt(模型结构与量化配置检查)
目标
在模型完成 prepare(...) 后,基于运行目录中的 model_check_result.txt,快速发现并解释以下四类问题:
- 算子融合异常(可融合但未融合)
- 共享模块风险(同一 module 多次调用)
- qconfig 配置异常(dtype/高精度输出/可疑 qconfig)
- averaging_constant 非默认值(observer 的 averaging_constant != 0.01)
- 算子输入浮点检查(非 QuantStub/DeQuantStub 算子的输入为浮点类型)
本 Skill 聚焦“检查结果解读与修复建议”,用于连接 prepare 之后的排查阶段。
背景约束(必须知道)
prepare已集成check_qat_model;通常不需要额外手动调用,直接查看model_check_result.txt即可。- 该检查工具会给出“需要你复核”的线索,并非每条提示都一定是错误。
- 真正是否需要修改,必须结合模型拓扑、部署边界、精度对比结果综合判断。
本 Skill 强约束
- 只做结果分析与修复路径建议:不擅自改动大量模型结构。
- 先读结果再下结论:必须依据
model_check_result.txt中的具体表格与条目,不做臆测。 - 分五块输出结论:
- 融合问题
- 共享问题
- qconfig 问题
- averaging_constant 非默认值提示
- 算子输入浮点检查提示
- 给出“是否必改”的判断等级:
- 高优先级(明确错误/高风险)
- 中优先级(可能影响精度/性能)
- 低优先级(提示项,需业务确认)
重点检查项与判定标准
1) 算子融合检查(Fusable modules)
关注 Fusable modules are listed below: 段落。
若存在未融合模块,常见原因如下:
- 动态代码块里涉及替换/融合逻辑,但缺少
dynamic_block标注 - 未融合模块为共享模块。
输出建议时要明确:
- 这是“结构正确性 + 性能/精度”问题,不一定每个未融合都必须改
- 若未融合位置伴随共享或动态逻辑,应优先处理
2) 共享模块检查(Each module called times)
关注 Each module called times: 段落。
基础判定:
called times = 1:正常called times = 0:未调用(需检查是否死分支/配置问题)called times > 1:共享调用
关键解释:
- “共享调用”本身不必然错误
- 只有当多次调用的数据分布差异明显时,才容易因共用一组量化参数导致较大误差
建议流程:
从 called times > 1 列出候选模块,建议用户自行排查决定是否需要拆分共享模块
3) qconfig 正确性检查
重点看以下内容:
Each layer out qconfig:Weight qconfig:input/output dtype statistics:Please check if these OPs qconfigs are expected.
高精度输出判定标准:
检查每个 DeQuantStub 的输入 dtype,按以下三级判定:
- DeQuantStub 输入为
torch.float32:✅ 高精度浮点输出路径已生效。上游算子输出 fp32 直连 DeQuantStub,说明该路径保持了浮点精度。标注为正常行为。 - DeQuantStub 输入为
qint16:✅ 高精度量化输出已开启。上游算子使用 qint16(相比 qint8 提供更高量化精度)进行量化,DeQuantStub 将 qint16 反量化为 float32 是标准的高精度量化输出链路。标注为正常行为,说明模型已开启高精度量化配置。 - DeQuantStub 输入为
qint8:ℹ️ 标准 int8 量化输出。这是常规的 int8 量化配置,DeQuantStub 将 qint8 反量化为 float32 是标准的反量化行为。无异常,但也不属于高精度输出。
常见异常模式:
- DeQuantStub 输入为 qint8 但用户期望高精度输出:需提示用户检查 qconfig 中是否正确设置了 qint16 或 fp32 的高精度输出 dtype
- Fixed scale / 可疑 qconfig 提示(不一定错,但必须复核)
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.
- 12d ago First seen · 207 lines · 68 tokens per session scan A 3a6769bb302e
j6-plugin-model-check-result is a skill published in the GitHub repository HorizonRobotics/OE-Skills (19 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 68 tokens to every session and 2,462 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.
Other skills, from other repositories
spark-optimization
Optimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning. Use when improving Spark performance, debugging slow jobs, or scaling data processing pipelines.
notebooklm
Install, authenticate, troubleshoot, and operate Gemini Notebook through the notebooklm-py CLI or typed async Python API. Use for notebook and source management, grounded chat and research, and artifact generation or download when the user mentions Gemini Notebook, notebooklm-py, the notebooklm CLI, or its Python API.…
debug-inference
Debug inference clients that use an attached provider and its native endpoint, including hosted APIs and host-local Ollama, vLLM, SGLang, TRT-LLM, LM Studio, or NIM. Use for provider attachment, endpoint policy, credential substitution, topology, and migration from the removed inference.local endpoint. Trigger…
oh-my-posh
Install, configure, or troubleshoot Oh My Posh/ohmyposh: shell init, themes, segments, Nerd Font icons, and prompt setup on PowerShell, zsh, bash, or fish.
eagle3-triage
Triage a failed EAGLE3 pipeline run. Identifies which step failed (data synthesis, hidden state dump, training, or benchmark), diagnoses root cause from logs, and suggests fixes. Use when user reports an EAGLE3 pipeline failure or asks why a specific step failed. Also helps debug new model support issues.
trulens-instrumentation
Instrument LLM apps with TruLens OTEL-based tracing - from setup to debugging and optimization.