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/lglucas/ai-dev-operating-system/processizenpx skills add lglucas/ai-dev-operating-system --skill processizegit clone --depth 1 https://github.com/lglucas/ai-dev-operating-systemWhat 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 | $0.00102 | $0.01357 |
| Opus 5 | $0.00051 | $0.00678 |
| Sonnet 5 | $0.00020 | $0.00271 |
| Haiku 4.5 | $0.00010 | $0.00136 |
Grade A, and why
processize 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.
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Processize
Codify a process AFTER you have validated it manually. Never automate a workflow that is still being discovered. Automation locks in whatever you point it at — including the bugs.
Mindset
"If you automate before validating, you scale the wrong thing. If you process-ize after validating 3+ times, you've earned the right to compress." — paraphrased from Sahil Lavingia, The Minimalist Entrepreneur
Three-stage maturity:
- Manual — first 1–3 times. Pure improvisation. Goal: learn what the process actually is.
- Documented — 3rd to ~10th time. Same human, written checklist, no automation. Goal: prove the steps are stable.
- Processized — 10th+ time. Checklist + AI assist + selective automation. Goal: compress the predictable parts, leave judgment with the human.
Skipping straight from 1 to 3 is the most expensive bug in vibe coding.
When to invoke
- User says "tô fazendo isso toda semana" / "isso já cansou" / "deve ter um jeito mais rápido".
- User says "vamos automatizar isso?" — invoke FIRST to check it has been validated 3+ times.
daily-standupskill flags the same manual task across 3+ sessions.- Post-launch operations work that is repeating: weekly user outreach, content publishing, retention checks, billing reconciliation.
- Before introducing any cron, scheduled job, webhook, or AI loop that codifies a workflow.
When NOT to invoke
- The task has been done fewer than 3 times.
- The task changes shape every time it runs (still in discovery).
- The user wants to redesign the process, not codify it — use brainstorming or
prototype-labinstead. - The task is a one-off (e.g. "set up the Stripe account") — write a session log, not a process.
The 5-question gate
Before producing a process document, the skill MUST get answers to these. Ask them one at a time if missing:
- How many times has this been done manually? (< 3 → stop, do it manually a few more times.)
- Did it produce the desired outcome the last 3 times? (no → not yet ready; debug the manual version first.)
- Which steps are identical every time? (these are the automation candidates.)
- Which steps require human judgment? (these stay manual or become AI-assisted.)
- What would happen if the automated version ran wrong for a week without anyone noticing? (defines the safety net.)
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.
- 2d ago First seen · 150 lines · 102 tokens per session scan A 03e776403052
processize is a skill published in the GitHub repository lglucas/ai-dev-operating-system (11 stars, last pushed 24d ago), licensed MIT. It adds 102 tokens to every session and 1,357 once invoked, about $0.0005 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.
Other skills, from other repositories
mailbox
当用户需要任何邮箱/邮件操作时使用此技能——包括查看、阅读、搜索、发送、回复、转发、整理或删除邮件，管理会话线程，绑定个人邮箱或注册新邮箱。此技能是邮件任务的统一且唯一入口，通过 qwenpawmail-mcp 编排操作，当前支持 9 个个人邮箱域名。.
channel_message
Use this skill to proactively send a one-way message to a user/session/channel, usually only when the user explicitly asks to send to a channel/session or when proactive notification is needed. First query sessions with qwenpaw chats list, then push with qwenpaw channels send.
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes, capturing pane output, and managing terminal multiplexer windows. Enables parallel coding-agent orchestration, background process management, and REPL interaction via sockets. Use when the agent needs to launch, monitor, or coordinate…
obsidian-vault
Organize Obsidian vaults with MOCs, wikilinks, frontmatter/properties, dashboards, orphan-note checks, and cleanup workflows. Use ONLY when the user explicitly refers to Obsidian — by naming "Obsidian", an Obsidian "vault", or an Obsidian-specific feature such as wikilinks ("[[ ]]"), the Dataview or Bases plugins, or…
local-tools
Access local system resources including Calendar on macOS and Windows. Use this skill when you need to manage user's schedule directly on their device.
imap-smtp-email
Read and send email via IMAP/SMTP. Check for new/unread messages, fetch content, search mailboxes, mark as read/unread, and send emails with attachments. Works with any IMAP/SMTP server including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.