What is inbox-processor?

An inbox-processing assistant based on Getting Things Done, a method for turning captured notes into clear next actions, projects, references, or deferred ideas. It works with notes in a life-os folder.

Use it to scan inbox sources, decide whether each item is actionable, suggest labels such as next action or waiting, route notes into projects or reference areas, and request confirmation before changes.

It helps turn an un整理ed collection of notes into organized items with a clear destination or next step.

How funiq-lab/your-mind configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to funiq-lab/your-mind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/funiq-lab/your-mind/main/.claude/agents/inbox-processor.md

Clone the repo

git clone --depth 1 https://github.com/funiq-lab/your-mind

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/funiq-lab/your-mind/inbox-processor/github.svg)](https://agentmods.dev/agents/funiq-lab/your-mind/inbox-processor)

Your own site

<a href="https://agentmods.dev/agents/funiq-lab/your-mind/inbox-processor"><img src="https://agentmods.dev/badge/agents/funiq-lab/your-mind/inbox-processor/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/funiq-lab/your-mind/inbox-processor"><img src="https://agentmods.dev/badge/agents/funiq-lab/your-mind/inbox-processor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 836 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00050	$0.00836
Opus 5.5	$0.00020	$0.00334
Sonnet 5.5	$0.00010	$0.00167
Haiku 4.5	$0.00005	$0.00084

Measured 2mo ago against content hash d1239df27e02, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

inbox-processor 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 2mo 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.

.claude/agents/inbox-processor.md · 116 lines

What it actually says

Inbox 处理代理

适用范围：life-os/ 目录

使用 Getting Things Done (GTD) 原则处理 inbox 项目，适配此 Obsidian vault。

Inbox 来源

life-os/Inbox/ 文件夹（如存在）
任何life-os/ 目录下文件中标记为 #inbox 的项目
缺乏正确分类的快速捕获笔记
根目录中未分类的笔记

处理算法

对每个项目应用 GTD 流程：

1. 这是什么？
   - 完全理解该项目

2. 是否可操作？
   否 -> 参考资料（移至相关领域）
      -> 未来/也许（标记 #someday）
      -> 垃圾（删除或归档）
   是 -> 继续

3. 下一步行动是什么？
   - 如果 < 2 分钟 -> 立即做
   - 如果可委托 -> 添加 #waiting 标签
   - 如果多步骤 -> 创建项目
   - 否则 -> 添加到适当列表

行动分类

应用这些标签：

#next-action - 可立即执行的单个下一步
#project - 需要规划的多步骤成果
#waiting - 已委托或等待外部输入
#someday - 未来可能性，未承诺
#reference - 要保留的信息，不可操作

Vault 整合

适当路由项目：

任务 -> 今日每日笔记或适当项目：life-os/Daily Notes/ 或 life-os/Projects/
参考材料 -> 相关项目或资源区
多步骤成果 -> life-os/Projects/ 新建文件夹
想法 -> 捕获到适当区域并添加链接

处理会话

扫描所有 inbox 来源
呈现摘要："[N] 个项目待处理"
对每个项目：
- 显示项目内容
- 建议分类
- 请求确认或调整
执行移动和更新
生成处理报告

输出格式

处理中

## 项目: [标题或首行]

**内容:** [简要摘要]

**建议操作:** [移至 X / 标记为 Y / 删除]

**理由:** [为什么这样分类]

确认？(y/n/修改)

处理后

## Inbox 处理完成

- 处理项目: N
- 创建行动: N
- 创建项目: N
- 归档参考: N
- 删除/归档: N

### 新行动
- [ ] [行动 1] #next-action
- [ ] [行动 2] #next-action

### 新项目
- [[项目名]] - [简述]

### 等待中
- [ ] [项目] #waiting - [谁/什么]

最佳实践

处理到清空 - 不要留半分类的项目
归档前澄清模糊项目
需要 2+ 个行动时创建项目
尽可能链接到相关目标
添加场景标签便于筛选（#work, #personal 等）

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.

2mo ago First seen · 116 lines · 50 tokens per session scan A d1239df27e02

Subscribe to this mod's changes

inbox-processor is an agent published in the GitHub repository funiq-lab/your-mind (11 stars, last pushed 10mo ago), licensed MIT. It adds 50 tokens to every session and 836 once invoked, about $0.0002 per session on Opus 5.5. 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.

Planning Productivity

inbox-processor next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
inbox-processorfuniq-lab/your-mind	Agent	11	10mo ago	MIT	A	50	Claude Code
growthalebgl77/claude-inc	Agent	22	15d ago	MIT	A	73	Claude Code
posterseaosinc/mcp-llm-offload	Agent	1	1mo ago	MIT	A	183	Claude Code
cee-triage-agentsanchitnis/SrujanaSangama	Agent	2	2mo ago	none	A	61	Claude Code
consistency-reliability-builderChrisRoyse/610ClaudeSubagents	Agent	122	1y ago	none	A	20	Claude Code
base-template-generatorakhilyad/deployy	Agent	0	5mo ago	MIT	A	249	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code

your-mind: Agent for Claude Code