Borrowing it
Nothing to install: this file belongs to peterfei/ai-agent-team. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/peterfei/ai-agent-team/main/.claude/skills/thread-manager/SKILL.mdgit clone --depth 1 https://github.com/peterfei/ai-agent-teamWrote 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/peterfei/ai-agent-team/thread-manager)<a href="https://agentmods.dev/skills/peterfei/ai-agent-team/thread-manager"><img src="https://agentmods.dev/badge/skills/peterfei/ai-agent-team/thread-manager/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/peterfei/ai-agent-team/thread-manager"><img src="https://agentmods.dev/badge/skills/peterfei/ai-agent-team/thread-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.00458 |
| Opus 5.5 | $0.00000 | $0.00183 |
| Sonnet 5.5 | $0.00000 | $0.00092 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
thread-manager 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 1mo 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
Thread Manager Skill
Thread Manager 为 Claude Code 提供多线程对话管理功能，让你可以并行处理多个任务，保持上下文隔离和专注。
功能特性
- 多线程管理: 创建、切换、更新和删除对话线程。
- 上下文隔离: 每个线程拥有独立的消息历史和上下文。
- 文件变更追踪: 自动记录每个线程中修改的文件和代码行数统计。
- 持久化存储: 使用 SQLite 本地存储所有数据，安全可靠。
- Git 集成: 自动检测文件变更详情。
安装
本 Skill 通常作为 ai-agent-team 项目的一部分安装。如果需要单独安装：
- 确保已安装 Node.js 18+。
- 运行
npm install安装依赖。 - 运行
npm run build编译代码。 - 将本 Skill 添加到 Claude Code 配置文件 (
config.json) 中。
MCP 工具
| 工具名称 | 描述 |
|---|---|
create_thread |
创建新线程 |
list_threads |
列出所有线程 |
switch_thread |
切换到指定线程 |
get_thread |
获取线程详情 |
update_thread |
更新线程信息 |
delete_thread |
删除线程 |
get_current_thread |
获取当前活跃线程 |
track_file_change |
记录文件变更 (支持自动检测) |
search_messages |
基于语义搜索历史消息 (支持自然语言) |
Slash Commands
/thread new "Title": 创建新线程/threads: 列出所有线程/thread <id>: 切换线程/thread info: 查看当前线程详情/memory search "query": 搜索历史消息 (需要调用 search_messages)
数据存储
数据存储在 ~/.claude/threads/threads.db (默认) 或环境变量 THREADS_DB_PATH 指定的位置。
What ships with it
55 files 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.
- .claude/.threads/current-context.md 648 B
- .gitignore 76 B
- .npmignore 138 B
- CHANGELOG.md 1.1 KB
- docs/clt-aliases.md 2.2 KB
- find-module.js 166 B runs code
- jest.config.js 1.1 KB runs code
- models/Xenova/all-MiniLM-L6-v2/config.json 650 B
- models/Xenova/all-MiniLM-L6-v2/onnx/model_quantized.onnx 22434 KB
- models/Xenova/all-MiniLM-L6-v2/special_tokens_map.json 125 B
- models/Xenova/all-MiniLM-L6-v2/tokenizer_config.json 366 B
- models/Xenova/all-MiniLM-L6-v2/tokenizer.json 695 KB
- package-lock.json 407 KB
- package.json 1.1 KB
- README.md 4.7 KB
- scripts/download-model.js 1.7 KB runs code
- scripts/migrate-embeddings.ts 3.4 KB runs code
- src/core/embedding-service.ts 4.3 KB runs code
- src/core/thread-manager.ts 14 KB runs code
- src/core/vector-search-engine.ts 1.2 KB runs code
- src/core/vector-utils.ts 1.0 KB runs code
- src/database/db.ts 4.5 KB runs code
- src/database/file-changes-dao.ts 2.8 KB runs code
- src/database/index.ts 121 B runs code
- src/database/messages-dao.ts 5.1 KB runs code
- src/database/threads-dao.ts 6.4 KB runs code
- src/git/git-integration.ts 5.6 KB runs code
- src/index.ts 257 B runs code
- src/server.ts 6.1 KB runs code
- src/tools/add-message.ts 1.5 KB runs code
- src/tools/create-thread.ts 1.3 KB runs code
- src/tools/delete-thread.ts 925 B runs code
- src/tools/get-current-thread.ts 2.6 KB runs code
- src/tools/get-thread.ts 1.2 KB runs code
- src/tools/list-threads.ts 1.2 KB runs code
- src/tools/search-messages.ts 4.4 KB runs code
- src/tools/switch-thread.ts 1.4 KB runs code
- src/tools/track-file-change.ts 1.7 KB runs code
- src/tools/update-thread.ts 1.2 KB runs code
- src/types/index.ts 2.6 KB runs code
- test-add-message.js 2.3 KB runs code
- test-output-format.js 546 B runs code
- tests/integration/file-tracker.test.ts 3.3 KB runs code
- tests/integration/mcp-tools.test.ts 5.4 KB runs code
- tests/integration/search-messages.test.ts 5.8 KB runs code
- tests/unit/__mocks__/embedding-service.ts 1.3 KB runs code
- tests/unit/database.test.ts 1.6 KB runs code
- tests/unit/file-changes-dao.test.ts 3.6 KB runs code
- tests/unit/git-integration.test.ts 4.9 KB runs code
- tests/unit/messages-dao.test.ts 3.9 KB runs code
- tests/unit/thread-manager.test.ts 9.2 KB runs code
- tests/unit/threads-dao.test.ts 6.0 KB runs code
- tests/unit/vector-search.test.ts 3.7 KB runs code
- tsconfig.json 464 B
- USAGE_GUIDE.md 6.7 KB
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.
- 1mo ago First seen · 47 lines · 0 tokens per session scan A b0f881d1c9cc
thread-manager is a skill published in the GitHub repository peterfei/ai-agent-team (448 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 458 tokens. 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
claude-code-bash-patterns
Claude Code Bash tool patterns with hooks, automation, git workflows. Use for PreToolUse hooks, command chaining, CLI orchestration, custom commands, or encountering bash permissions, command failures, security guards, hook configurations.
agentic-delegation
Plan who does each step of a task in this repo, on which model, at which effort: Haiku or Sonnet subagents for search, recon, and log-reading; code edits on Opus 5.5; start at medium effort and escalate on evidence (high, then xhigh, then Fable 5.1 for one stuck task); the orchestrator keeps design, security-sensitive…
jiaojie
A human-first method for handing ongoing work from one chat, AI model, device, or language to another. It creates or reads a small handoff document, or a package with files when the receiver needs them.
aws-non-destructive-task-automation-advisor
Design AWS non-destructive task automation using EventBridge, Step Functions, Lambda, Systems Manager Automation, SNS, SQS, approvals, notifications, reporting, and evidence gathering. Use only for read-only or coordination-safe automation; do not use for destructive remediation or mutation-heavy runbooks.
promote
Turn a scratch script into a permanent tool this repo keeps. Use when a check, report, or analysis has proved worth running more than once.
sitrep-panel
Keep a live local HTML report updated as you work on a task — a status board, a running "what's happening now" narrative, screenshots, and a newest-first log — served on localhost so the user can watch progress in a browser tab instead of reading the transcript. Use when the user invokes /sitrep-panel, asks for a…