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.
npx agentmods add skills/teejayen/arc/inbox-processornpx skills add teejayen/arc --skill inbox-processorgit clone --depth 1 https://github.com/teejayen/arcWhat 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 | $0.00037 | $0.00495 |
| Opus 5 | $0.00018 | $0.00247 |
| Sonnet 5 | $0.00007 | $0.00099 |
| Haiku 4.5 | $0.00004 | $0.00049 |
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 yesterday.
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
Inbox Processor
Sort items from inbox/ to their proper locations.
When to Use
- Inbox has accumulated items
- During weekly review
- User asks to process/clear inbox
- Session start hook shows stale items
Execution Steps
Step 1: List inbox contents
ls -la inbox/
Note:
- File ages (flag anything > 7 days as stale)
- File types and naming patterns
- Rough categorisation
Step 2: Process each item
For each file, determine destination based on content:
| Content Type | Destination |
|---|---|
| Quick thought/idea | areas/[relevant]/ or projects/[relevant]/ |
| Decision draft | decisions/ (use decision-capture skill) |
| External link/resource | resources/[type]/ (use capture skill) |
| Project-related | projects/[project]/ |
| Area-related | areas/[area]/ |
| Historical/completed | archive/ |
| Session notes | sessions/ |
Step 3: Move or transform
For each item:
- Read the content
- Determine if it needs transformation (adding frontmatter, restructuring)
- Either move as-is or create proper file in destination
- Delete original from inbox/
Step 4: Handle ambiguous items
If destination unclear:
- Ask the user
- Or leave in inbox/ with a note about why
Step 5: Report
Summarise what was processed:
## Inbox Processed
**Items moved:** X
- `thought.md` -> `areas/career/notes.md`
- `link.md` -> `resources/bookmarks/tool.md`
**Items archived:** X
- `old-note.md` -> `archive/2025/`
**Items remaining:** X
- `unclear.md` - needs clarification
**Inbox status:** Clear / X items remaining
Step 6: Update focus if needed
If processing revealed something important, update state/focus.md.
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.
- yesterday First seen · 80 lines · 37 tokens per session scan A 625909e4b9a5
inbox-processor is a skill published in the GitHub repository teejayen/arc (5 stars, last pushed 7mo ago), licensed MIT. It adds 37 tokens to every session and 495 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…