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 instructions/bukowskireal/trace/claude-mdgit clone --depth 1 https://github.com/BUKOWSKIREAL/traceWhat 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 | $0.00560 | $0.00560 |
| Opus 5 | $0.00280 | $0.00280 |
| Sonnet 5 | $0.00112 | $0.00112 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
trace CLAUDE.md 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.
What it actually says
CLAUDE.md
本项目是 Trace，一个 Python + SQLite + watchdog + Textual 的多 CLI Agent 协作版本追踪器。
常用命令
uv sync
uv run python -m unittest discover -s tests
uv run python code/main.py --workspace test_workspace
uv run python code/main.py --workspace test_workspace --headless
uv run python code/main.py --choose
bash scripts/demo.sh
TUI 操作台：
uv run python code/main.py --workspace test_workspace
MCP 服务器测试：
python run_mcp_server.py --workspace test_workspace
uv run python -m unittest tests.test_trace_mcp_server
项目约定
- Python 依赖通过
uv管理，不要手动创建新的 venv 方案。 - Phase 6 后 Trace 是纯 Python / Textual TUI 产品；不要重新引入旧桌面前端、系统托盘或平台打包链。
test_workspace/是本地演示目录，不进入版本控制。.trace/是运行时仓库目录，不进入版本控制。dist/和build/是本地构建产物目录，不进入版本控制。- 文件版本存储以字节 blob 为准，handler 只负责 UI diff 展示。
.docx/.pptx/.xlsx/.pdf/image等格式有专门 handler；未知格式走BinaryHandler。- 修改 watcher、repository、batcher 时要跑完整测试。
MCP 功能
- MCP 服务器位于
code/mcp/trace_server.py，提供trace_record_files工具。 - 项目根目录的
.mcp.json为 Claude Code CLI 提供配置。 run_mcp_server.py是通用的 Python 包装脚本，自动设置 PYTHONPATH。scripts/start_mcp_server.sh是 Bash 启动脚本。- MCP 配置详见
MCP_SETUP.md。 - 修改 MCP 相关代码后必须运行
tests/test_trace_mcp_server.py验证。
验证重点
Repository.commit()必须保持全量 manifest 语义。checkout_commit()必须删除目标 manifest 中不存在的已跟踪文件。- watcher 删除事件必须走
kind="delete"，不能被 modify 事件去重吞掉。 - 多 agent 防抖必须保持每个 agent 独立 timer。
- MCP 服务器必须能在不同 agent 环境（Claude、Codex、Cursor 等）中正常运行。
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 · 56 lines · 560 tokens per session scan A d5fc733a0a8d
trace CLAUDE.md is an instructions file published in the GitHub repository BUKOWSKIREAL/trace (5 stars, last pushed 1mo ago), licensed MIT. It adds 560 tokens to every session, about $0.0028 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 instructions, from other repositories
vscode tree-widgets.instructions.md
Use when asked to consume workbench tree widgets in VS Code.
vscode accessibility.instructions.md
Use when implementing accessibility features, ARIA labels, screen reader support, accessible help dialogs, or keybinding scoping for accessibility. Covers AccessibleContentProvider, CONTEXTACCESSIBILITYMODEENABLED, verbosity settings, and announcement patterns.
vscode source-code-organization.instructions.md
VS Code source code organization — layers, target environments, dependency injection, and folder structure conventions. Reference when adding new modules, services, or contributions.
vscode design-philosophy.instructions.md
VS Code design philosophy — the shared Values→Principles→Moves vocabulary for reasoning about UI in design terms rather than raw pixels. Use when creating, editing, or reviewing any visual surface (CSS, DOM, theming, icons, motion). Name the value/principle before reaching for a token.
vscode css-best-practices.instructions.md
CSS best practices for selector performance and maintainable state styling. Use when writing or reviewing CSS.
vscode kusto.instructions.md
Kusto exploration and telemetry analysis instructions.