inbox-processor

inbox-processor is a command for Claude Code from reluctantfuturist/loyal-wingman. It costs 21 tokens per session (678 once invoked), scanned A, original, MIT.

An inbox-triage command for a writing workspace with folders for drafts, research, world-building, and project planning.

In plain words
What is it for?
It scans inbox files, categorises them as scene ideas, research, world-building, planning, parking-lot items, or stale content, and recommends moving or deleting them.
Why use it?
It replaces a large unorganised inbox with recommendations for where each file belongs and flags old material for review.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the loyal-wingman plugin — 12 skills, 7 commands shipped together

Good fit It scans inbox files, categorises them as scene ideas, research, world-building, planning, parking-lot items, or stale content, and recommends moving or deleting them.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/reluctantfuturist/loyal-wingman/inbox-processor
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.

Clone the repo
git clone --depth 1 https://github.com/reluctantfuturist/loyal-wingman

Made for: Claude Code.

Or install loyal-wingman, the plugin that ships this one along with the rest of its 12 skills, 7 commands.

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.

agentmods badge for inbox-processor

README.md
[![agentmods](https://agentmods.dev/badge/commands/reluctantfuturist/loyal-wingman/inbox-processor/github.svg)](https://agentmods.dev/commands/reluctantfuturist/loyal-wingman/inbox-processor)
Your own site
<a href="https://agentmods.dev/commands/reluctantfuturist/loyal-wingman/inbox-processor"><img src="https://agentmods.dev/badge/commands/reluctantfuturist/loyal-wingman/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.

agentmods 80×15 button for inbox-processor

Your own site · 80×15
<a href="https://agentmods.dev/commands/reluctantfuturist/loyal-wingman/inbox-processor"><img src="https://agentmods.dev/badge/commands/reluctantfuturist/loyal-wingman/inbox-processor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 678 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00021 $0.00678
Opus 5 $0.00010 $0.00339
Sonnet 5 $0.00004 $0.00136
Haiku 4.5 $0.00002 $0.00068

Measured 8d ago against content hash 0799431ad33a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

commands/inbox-processor.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/inbox-processor

Systematically triage all files in 00_Inbox/, moving to proper locations or deleting stale content.

Process

Step 1: Scan Inbox

List all files in 00_Inbox/ with:

  • File name
  • Age (days since modified)
  • First 100 characters of content

Flag files >7 days old as STALE.

Step 2: Categorize Each File

For each file, determine category:

Category Destination Action
Scene seed 10_Projects/Scene_Seeds/ Move
Research note 03_Research/[category]/ Move
World bible content 02_World/[category]/ Flag for world-bible
Series planning 10_Projects/Series_Planning/ Move
Parking lot Already in place Process items
Stale/obsolete N/A Delete

Step 3: Present Recommendations

## Inbox Triage: [count] files

### Move to Scene_Seeds
- [file]: [reason] → `10_Projects/Scene_Seeds/[name].md`

### Move to Research
- [file]: [reason] → `03_Research/[category]/[name].md`

### Create World Bible Entry
- [file]: [reason] → Use world-bible skill

### Delete (Stale)
- [file]: [age] days old, [reason for deletion]

### Parking Lot Items
[If Parking_Lot.md exists and has content]
- [item 1]: [recommendation]
- [item 2]: [recommendation]

**Approve these actions?**

Step 4: Execute (After Approval)

For each approved action:

  1. Move files to destinations
  2. Delete approved deletions
  3. For world bible content: invoke world-bible skill
  4. Clear processed parking lot items

Step 5: Report Final State

## Inbox Processed

**Moved:** [count] files
**Deleted:** [count] files
**Created:** [count] world bible entries

**Current inbox state:** [count] files remaining
**Oldest file:** [age] days

Target: <5 files, all <7 days old
Status: [HEALTHY|NEEDS ATTENTION]

Parking Lot Special Handling

If 00_Inbox/Parking_Lot.md exists:

  1. Read all items
  2. For each item, recommend:
    • Develop into scene seed
    • Create world bible entry
    • Research needed
    • Delete (not worth pursuing)
  3. Present for user decision
  4. Process according to decision
  5. Remove processed items from file

Read the full file on GitHub · 109 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. 8d ago First seen · 109 lines · 21 tokens per session scan A 0799431ad33a

Subscribe to this mod's changes

inbox-processor is a command published in the GitHub repository reluctantfuturist/loyal-wingman (7 stars, last pushed 8mo ago), licensed MIT. It adds 21 tokens to every session and 678 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.