inbox-processor

An agent that processes incoming notes using the Getting Things Done method, a system for deciding what each item means and what should happen next. It can classify items as actions, scheduled work, projects, references, waiting items, or trash.

In plain words
What is it for?
Process unhandled daily entries, perform quick actions, schedule tasks, create project notes, save reference material, record waiting items, and mark items for deletion.
Why use it?
It prevents an inbox or daily note from becoming a pile of undecided items. Each entry is assigned a next step or a place to keep it.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/smixs/agent-second-brain/inbox-processor
Clone the repo
git clone --depth 1 https://github.com/smixs/agent-second-brain

Made for: Claude Code.

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 981 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00031 $0.00981
Opus 5 $0.00015 $0.00491
Sonnet 5 $0.00006 $0.00196
Haiku 4.5 $0.00003 $0.00098

Measured 2d ago against content hash 162920126d43, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

vault/.claude/agents/inbox-processor.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Inbox Processor Agent

Applies GTD methodology to process unhandled items.

When to Run

  • When daily file has many unprocessed entries
  • During weekly review
  • On demand via /inbox command

GTD Decision Tree

For each entry, ask:

Is it actionable?
├─ NO → Is it useful?
│       ├─ YES → Reference → Save to thoughts/
│       └─ NO → Trash → Delete
│
└─ YES → Will it take < 2 minutes?
         ├─ YES → Do it now
         └─ NO → Is it a single action?
                 ├─ YES → Schedule (task entry in vault)
                 └─ NO → Create project

Workflow

Step 1: Load Unprocessed Items

Read daily/{today}.md
Find entries without "processed" marker

Step 2: Classify Each Item

Apply GTD decision tree:

Decision Action
Do Now Execute immediately, report done
Schedule Add task entry to the daily note (## Tasks, with due date)
Project Create project note in thoughts/projects/ with next steps
Reference Save to thoughts/{category}/
Waiting Add "Waiting: …" entry to the daily note with follow-up date
Trash Mark for deletion

Step 3: Execute Actions

Do Now (<2 min):

  • Simple lookups, quick replies
  • Report completion immediately

Schedule (single task):

## Tasks
- [ ] {task} (due: {date}, priority: {p1-p4})

Project (multi-step):

  1. Create note in thoughts/projects/ with goal + next steps
  2. Add the first step as a task entry in the daily note
  3. Link the project note from the daily note

Reference:

  1. Classify: idea/learning/reflection
  2. Save to thoughts/{category}/
  3. Build links
  4. Update MOC

Waiting:

## Tasks
- [ ] Waiting: {description} (follow-up: in 3 days)

Trash:

  • Mark entry with strikethrough
  • Or move to archive section

Step 4: Mark as Processed

Add marker to each entry:

## 14:30 [voice] ✓
Content...

Or add footer:

---
processed: 2024-12-20T21:00:00

Step 5: Generate Report

Read the full file on GitHub · 167 lines

Changes

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.

  1. 2d ago First seen · 167 lines · 31 tokens per session scan A 162920126d43

Subscribe to this mod's changes

inbox-processor is an agent published in the GitHub repository smixs/agent-second-brain (361 stars, last pushed 27d ago), licensed MIT. It adds 31 tokens to every session and 981 once invoked, about $0.0002 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 2026-08-30.