inbox-watcher

inbox-watcher is a skill for Claude Code from DavidROliverBA/ArchitectKB. It costs 17 tokens per session (784 once invoked), scanned B, original, MIT.

A file-inbox monitor that checks for items waiting to be processed and classifies them for suitable handling. It can also process items using the suggested skills.

In plain words
What is it for?
Use it to check incoming voice notes, PDFs, presentations, images, and notes that lack a type label. It can suggest or start the next processing step.
Why use it?
It removes the need to manually inspect folders and decide what to do with every new file or untyped note.

Skill for Claude Code

Written for Claude Code: context: fork in frontmatter. Also seen: model in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node .claude/scripts/graph-query.js --where="type=" --json 2>/dev/null.

Good fit Use it to check incoming voice notes, PDFs, presentations, images, and notes that lack a type label. It can suggest or start the next processing step.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/DavidROliverBA/ArchitectKB
agentmods
npx agentmods add skills/davidroliverba/architectkb/inbox-watcher

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.

agentmods badge for inbox-watcher

README.md
[![agentmods](https://agentmods.dev/badge/skills/davidroliverba/architectkb/inbox-watcher.svg)](https://agentmods.dev/skills/davidroliverba/architectkb/inbox-watcher)
Your own site
<a href="https://agentmods.dev/skills/davidroliverba/architectkb/inbox-watcher"><img src="https://agentmods.dev/badge/skills/davidroliverba/architectkb/inbox-watcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 784 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00017 $0.00784
Opus 5 $0.00009 $0.00392
Sonnet 5 $0.00003 $0.00157
Haiku 4.5 $0.00002 $0.00078

Measured 8d ago against content hash c9fee2922fdf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

inbox-watcher scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

find . -name "*.md" -not -path "./.claude/*" -not -path "./.obsidian/*" -not -path "./node_modules/*" -not -path "./Templates/*" -not -path "./Archive/*" | while read f; do
.claude/skills/inbox-watcher/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/inbox-watcher

Monitor for unprocessed files in the vault and suggest the appropriate skill to handle each.

Usage

/inbox-watcher              # Check and classify all unprocessed files
/inbox-watcher --process    # Check and auto-process with suggested skills

Instructions

1. Check for Unprocessed Inbox Items

npm run inbox:check 2>/dev/null

If no inbox script output, fall back to scanning common drop locations:

# Check for files that may need processing
ls -t voicenotes/*.md 2>/dev/null | head -10
ls -t Attachments/*.pdf Attachments/*.pptx 2>/dev/null | head -10

2. Check for Untyped Notes

Find markdown files that lack a type field in frontmatter (potential unprocessed content):

node .claude/scripts/graph-query.js --where="type=" --json 2>/dev/null

If graph-query.js does not support querying for empty/null type, use a Grep fallback:

# Find notes without a type field in frontmatter
find . -name "*.md" -not -path "./.claude/*" -not -path "./.obsidian/*" -not -path "./node_modules/*" -not -path "./Templates/*" -not -path "./Archive/*" | while read f; do
  if \! head -20 "$f" | grep -q "^type:"; then echo "$f"; fi
done

3. Classify and Recommend

For each unprocessed file, suggest the appropriate skill:

File Pattern Suggested Skill Rationale
voicenotes/*.md /meeting or /daily Voice transcriptions → meeting notes or daily entries
Attachments/*.pdf /pdf-to-page PDFs → structured page notes
Attachments/*.pptx /pptx-to-page PowerPoints → page notes with slide images
*.csv in root /csv-to-page or /csv-to-sql Data files → markdown tables or SQLite
Untyped .md at root /incubator or manual triage Loose notes need classification
Email - *.md without type /email Email drafts needing frontmatter

4. Present Report

## Inbox Report — YYYY-MM-DD

### Unprocessed Files (N found)

| # | File | Type | Suggested Action |
|---|------|------|-----------------|
| 1 | voicenotes/2026-02-13... | Voice note | `/meeting` — transcribe to meeting note |
| 2 | Attachments/report.pdf | PDF | `/pdf-to-page` — extract to page |

### Quick Actions
- Process all: `/inbox-watcher --process`
- Process one: Run the suggested skill command

Read the full file on GitHub · 91 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 · 91 lines · 17 tokens per session scan B c9fee2922fdf

Subscribe to this mod's changes

inbox-watcher is a skill published in the GitHub repository DavidROliverBA/ArchitectKB (52 stars, last pushed 6mo ago), licensed MIT. It adds 17 tokens to every session and 784 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens