Borrowing it
Nothing to install: this file belongs to the-sid-dani/second-brain-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/the-sid-dani/second-brain-os/main/.agents/skills/inbox-process/SKILL.mdgit clone --depth 1 https://github.com/the-sid-dani/second-brain-osWrote 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.
[](https://agentmods.dev/skills/the-sid-dani/second-brain-os/inbox-process)<a href="https://agentmods.dev/skills/the-sid-dani/second-brain-os/inbox-process"><img src="https://agentmods.dev/badge/skills/the-sid-dani/second-brain-os/inbox-process/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.
<a href="https://agentmods.dev/skills/the-sid-dani/second-brain-os/inbox-process"><img src="https://agentmods.dev/badge/skills/the-sid-dani/second-brain-os/inbox-process.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00118 | $0.04162 |
| Opus 5.5 | $0.00047 | $0.01665 |
| Sonnet 5.5 | $0.00024 | $0.00832 |
| Haiku 4.5 | $0.00012 | $0.00416 |
Grade C, and why
inbox-process scanned grade C 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 7d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
If `yes`: `rm -rf <path>` (folders need `-r`). How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
inbox-process
One intake surface for four related cleanup jobs: Inbox triage, unmigrated Projects triage, workspace-root audit, and a loose-file sweep of Desktop or Downloads. Every mode is propose-and-confirm; deletion receives its own explicit confirmation.
Before you begin: read the Configuration section in root CLAUDE.md. Path tokens like <workspace.inbox> resolve to whatever's defined there.
Why this exists
Two graveyard surfaces share the same triage shape:
-
<workspace.inbox>/— capture zone. Items land fast (drag-drop, Drive download, paste). Without periodic triage, it graveyards. Systems that last either skip an Inbox entirely or have a discipline for clearing it. This workspace keeps one, so the discipline lives in this skill. -
Unmigrated
<workspace.projects>/<slug>/folders (those missingCLAUDE.md) — folders placed in Projects without going through/new-project. Same disease: stuff dropped into the wrong location, never properly scaffolded, slowly accumulating. Per the SOUL.md Operating Principle "Capture before commit," these belong in<workspace.inbox>/until a deliberate decision to promote them; without a triage flow they sit in Projects unscaffolded.
These surfaces share the same triage flow: list candidates, inspect enough to route safely, show the full plan, confirm, then act. /prune-projects handles the next lifecycle stage (scaffolded projects that have gone stale).
/save-resource handles individual save-this-now operations. /inbox-process is the iteration wrapper that goes through everything weekly across both surfaces.
When to use
Trigger phrases (broad — over-trigger rather than miss):
- "process inbox" / "process my inbox"
- "Friday inbox review" / "Friday inbox" / "Friday cleanup"
- "what's in inbox?" / "what's in my inbox?"
- "clear my inbox" / "clean up inbox"
- "triage inbox" / "go through inbox"
- "inbox-process" / "/inbox-process"
- "clean up root" / "tidy the workspace root" / "what shouldn't be in root?"
- "organize my desktop" / "sort my screenshots" / "clean up downloads"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago Changed d4e8795f4097
- 1mo ago First seen · 278 lines · 118 tokens per session scan C a8692581a5ec
inbox-process is a skill published in the GitHub repository the-sid-dani/second-brain-os (3 stars, last pushed 7d ago), licensed MIT. It adds 118 tokens to every session and 4,162 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
apply
A browser-based job application workflow for submitting applications through services such as Ashby, Greenhouse, Lever, and Hacker News. It uses prepared candidate information, answers, job links, and cover letters.
screenpipe-api
Query the user's local and synced-device data via the screenpipe REST API at localhost:3030 — recordings, audio, UI, meetings, connected services, and memory. Use for screen activity, other-device or cross-device history, productivity, media export, connections, durable memory, or discovering and automating saved…
retro-lost
Run a retrospective for an abandoned agent session (untouched for over 24 hours, never closed with a retro): rebuild context cold from the transcript, list what was built, sort Keep/Drop/Try and file the durable parts. Use from a nightly routine or on demand. Triggers: /retro-lost, retro for an abandoned session.
nsr
A routine for starting a new, visible coding-agent session automatically through a scheduled task, so it appears in the recent-session list without someone pressing a start button.
routine-opt
Audit and cut the cost of a machine's scheduled routines: measure tokens per run, pick a lever (cheaper model, split, lower frequency, shorter prefix, retire) and prove the saving with a before-and-after measurement. Use when background routines burn more than interactive work. Triggers: /routine-opt, /ropt, routine…
slot
Registry of reusable agent sessions and slot allocation: claim a free scheduled-task slot instead of creating a new session, set its prompt and fire time, and release it when done. Use when you need to spawn or reuse a visible background session.