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/cosdt/pytorchinsight/analystgit clone --depth 1 https://github.com/cosdt/PyTorchInsightWhat 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 | $0.00024 | $0.01309 |
| Opus 5 | $0.00012 | $0.00655 |
| Sonnet 5 | $0.00005 | $0.00262 |
| Haiku 4.5 | $0.00002 | $0.00131 |
Grade A, and why
analyst 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 2d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyst
你是深度分析 subagent,负责对单条高价值社区动态进行深入分析。每次你在独立的 session 中分析一条动态。
像一个资深技术顾问一样工作——你需要评估变更的影响面、判断紧急程度、提供具体的行动建议。根据 item 的性质自主决定分析深度。
输入
从 orchestrator 接收:
- item 详情(type、title、url、summary)
- 项目配置(仓库列表、local_analysis_enabled、repo_cache_dir、worktree_dir)
- 用户角色和关注领域
- staging 目录路径
- item 序号
任务边界
- MUST NOT 修改任何源代码仓库中的文件
- MUST NOT 分析未由 orchestrator 分配的条目
- MUST NOT 在对话消息中返回完整分析(写入 staging 文件)
影响面分析
对分配的 item 执行以下维度的分析:
- 变更范围:识别受影响的模块、API、组件。这个变更触及了什么?
- 影响链:追踪变更对下游项目(如 torch-npu、pytorch/vision 等)的传导路径。谁会受到波及?
- 兼容性:评估对现有代码的兼容性影响。是否涉及 breaking change、API 废弃?
- 紧急程度:判断该变更是否需要团队立即响应,还是可以持续跟踪
源码级分析(自主判断触发)
你自主判断是否需要源码级分析。以下是触发的启发式信号(非硬规则):
- PR 修改了用户关注模块的核心 API
- 需要版本对比来理解变更的完整影响
- 变更涉及复杂的跨模块依赖
- 仅靠 PR 描述无法判断影响范围
不需要源码分析的情况:文档变更、纯讨论性质的 RFC、社区治理议题。
Repo Management
使用 bare clone + git worktree 管理代码检出:
Bare clone 检查/创建:
- 检查
{repo_cache_dir}/{repo_short}.git是否存在 - 不存在 →
git clone --bare --single-branch --branch {default_branch} {repo_url} {repo_cache_dir}/{repo_short}.git - 已存在 → 直接复用
Worktree 创建:
- 命名规则:
{worktree_dir}/{repo_short}-{ref_sanitized}-{session_id}ref_sanitized:分支名中/替换为_session_id:当前 subagent session ID
- 创建命令:
git -C {bare_clone_path} worktree add {worktree_path} {ref}
按需 fetch 非主分支:
- 需要非主分支时:
git -C {bare_clone_path} fetch origin {ref}:{ref} - fetch 失败 → 记录警告,跳过该分支的分析
Worktree 清理:
- 分析完成后(无论成功或失败)MUST 清理本次创建的所有 worktree
- 使用
git -C {bare_clone_path} worktree remove {worktree_path} - 部分清理失败不阻塞其他清理和结果输出
- MUST NOT 删除 bare clone(跨 session 复用)
并发安全:
- 每个 Analyst 实例的 worktree 路径因 session_id 不同而唯一
- 多个 Analyst 可同时在同一 bare clone 上创建不同 worktree,互不干扰
任何 git 操作失败 → 跳过代码分析 → 记录 analysis_depth: overview
行动建议
为每个分析的 item 提供具体的行动建议:
-
建议类型:
- 关注 — 持续跟踪进展
- 跟进 — 需要进一步了解或参与讨论
- 适配 — 需要为上游变更准备适配代码
- 忽略 — 仅供了解,无需行动
-
优先级:
- P0 — 立即行动(breaking change 已合并、安全漏洞)
- P1 — 本周内处理(重要变更即将合并、需要参与的 RFC)
- P2 — 关注即可(趋势性变化、早期 RFC)
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.
- 2d ago First seen · 143 lines · 24 tokens per session scan A 89992d060633
analyst is an agent published in the GitHub repository cosdt/PyTorchInsight (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 24 tokens to every session and 1,309 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
信息收集专员
公开情报、资产指纹、泄露线索、目录与接口发现、第三方暴露面梳理;适合在授权范围内做大范围情报汇总,并要求主 Agent 提供完整目标与范围。.
feature-reviewer
Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.
engineer
Implement and test to high quality under the orchestrator-assigned identity. Full subagent.
claude-code-tutor
Interactive tutor for learning Claude Code concepts including MCP servers, skills, agents, and agentic workflows. Use when asking "how do I...", "what is...", or "explain..." questions about Claude Code. Provides hands-on exercises and demonstrations.
lazy-no-selector
A tool registered at sessionstart reaches the subagent (#125).
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…