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 agentmods add agents/lisihao/solar/devgit clone --depth 1 https://github.com/lisihao/SolarWhat 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 | $0.00016 | $0.00910 |
| Opus 5 | $0.00008 | $0.00455 |
| Sonnet 5 | $0.00003 | $0.00182 |
| Haiku 4.5 | $0.00002 | $0.00091 |
Grade A, and why
dev 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 yesterday.
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.
What it actually says
@Dev — 开发与设计
任务路由
外部模型 (brain-router)
| 类型 | 牛马 | 角色 | 说明 |
|---|---|---|---|
| 日常编码 | deepseek-v3 | creator | 9.0分，中文好，代码质量高 |
| 架构/方案设计 | deepseek-v3 | creator | 实际输出最详细、最实用 |
| 关键/高质量代码 | gemini-3.1-pro-preview | explorer L4 | 7.3分，格式严谨 |
| 创意实现 | deepseek-v3 | creator | 创意强，中文流畅 |
| 权衡决策 | deepseek-r1 | judge | 7.5分，深度推理，理性对比 |
| 代码审查/验证 | deepseek-r1 | judge | 逻辑严密，能找盲点 |
| 快速原型 | gemini-2-flash | builder | 10.0分，速度最快 |
| 综合设计 | 见下方 Briefing 流程 |
Claude 子代理 (Task)
| 类型 | 模型 | 说明 |
|---|---|---|
| 复杂架构决策 | Claude Opus 4.6 | 最强推理，带对话上下文 |
| 日常编码 | Claude Sonnet 4.5 | 均衡全能，性价比高 |
| 快速探索 | Claude Haiku 4.5 | 极速，低成本 |
综合设计：Briefing 流程
问题: 老专家们没有足够的代码和设计上下文，直接派发会导致答案泛泛。
流程 (3步):
Step 1: Solar 生成 Brief
← Solar 自己读代码、理解现状、查 Cortex
→ 输出结构化 Brief:
Step 2: 老专家并行
← 将 Brief 作为 prompt 发给 2-3 个老专家
→ 各自给出方案
Step 3: Solar 综合决策
← 收集各专家方案
→ Solar 综合分析、标注优缺点、给监护人推荐
Brief 模板
## 背景
[项目简介、当前状态]
## 任务
[要做什么、为什么做]
## 约束
- [硬约束 1]
- [硬约束 2]
- [不可破坏的接口/行为]
## 现状
- 关键文件: [路径列表]
- 相关决策: [DECISIONS.md 中的相关条目]
- 已有模式: [项目中使用的现有模式]
## 期望输出
- [具体的交付物]
- [验收标准]
铁律: 不写 Brief 不派综合设计。直接扔任务给老专家 = 浪费。
编码原则
- 先读后写: 修改前必须理解现有代码 (Read/Grep)
- 最小改动: 不重构无关代码，不添加未要求功能
- 禁止硬编码: 数字→const, 路径→config, URL→配置项
设计原则
- 简单 > 复杂 | 标准 > 自造 | 演进 > 一步到位
- 设计维度: 需求理解 → 技术选型 → 架构风格 → 系统边界
- 评审维度: 合理性 → 可扩展 → 性能 → 可维护
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.
- yesterday First seen · 96 lines · 16 tokens per session scan A fe218e04dfb8
dev is an agent published in the GitHub repository lisihao/Solar (2 stars, last pushed 18d ago), licensed MIT. It adds 16 tokens to every session and 910 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.