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/msolecki/founder-os/queuenpx skills add msolecki/founder-os --skill queuegit clone --depth 1 https://github.com/msolecki/founder-osWhat 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 | $0.00034 | $0.04323 |
| Opus 5 | $0.00017 | $0.02161 |
| Sonnet 5 | $0.00007 | $0.00865 |
| Haiku 4.5 | $0.00003 | $0.00432 |
Grade A, and why
queue 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 3d 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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Queue
Every cadence in this company produces obligations and not one of them holds one. The daily brief says follow up with Anna and closes. Tomorrow's brief says it again, or forgets — and neither the founder nor any agent can answer whether Anna was followed up with, because the only record is a sentence in a file indexed by date rather than by whether the thing happened.
queue.md is where an obligation lives between the cadence that produced it and
the day it is done, dropped, or proved across three weeks to be neither.
It is not a to-do list. The founder has one of those and it is the problem the
daily brief exists to refuse. A to-do list only grows. This file has a cap of
fifteen, every item carries an expiry it cannot renew, and ## Dropped is a
section rather than a delete key — dropping is a decision, and a decision is worth
reading in November.
When to use
Whenever a session or a cadence produces an obligation that no other owner's file
will hold: a triage keep, the brief's one thing, the next item emitted by closing
the last one.
And every Friday, from weekly-review step 5 — the sweep, which is step 7 below.
The sweep is the only thing standing between this file and the graveyard every
queue eventually becomes.
Inputs
Read first — house rule 1:
queue.md— all five sections, whole. Its state machine does not survive being read in parts: whether an item in## Blockedis still blocked is answered by what sits in## Done.goals.md## Bets— every item names one bet or namesnone.
Two files, and this skill does not sweep for more. context-load caps a
cadence at its own file plus one, and names its exemptions — triage and
daily-brief — and says they do not extend by analogy to other Chief of Staff
cadences. This is one of those cadences, so the intake is not a sweep of every
agent's file looking for work. It is the two doors below, and the cost of that is
written down in ## Guardrails rather than quietly paid.
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.
- 3d ago First seen · 304 lines · 34 tokens per session scan A 8870101d76dd
queue is a skill published in the GitHub repository msolecki/founder-os (4 stars, last pushed 8d ago), licensed MIT. It adds 34 tokens to every session and 4,323 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
lark-im
飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
reflect
Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable agent instructions.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
organize-threads
猫猫辅助整理未分类 thread，分析标题和元数据，建议合适的标签。 Use when: 用户说"帮我整理"、"分类 thread"、点击整理按钮。 Not for: 删除/编辑标签本身。 Output: 按 thread 的标签建议列表。.