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/nweii/agent-stuff/code-to-pantrynpx skills add nweii/agent-stuff --skill code-to-pantrygit clone --depth 1 https://github.com/nweii/agent-stuffWhat 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 | $0.00079 | $0.01521 |
| Opus 5 | $0.00039 | $0.00760 |
| Sonnet 5 | $0.00016 | $0.00304 |
| Haiku 4.5 | $0.00008 | $0.00152 |
Grade A, and why
code-to-pantry 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code to pantry
Nathan's pantry (github.com/nweii/pantry) is a personal collection of modular, self-contained code recipes. The goal is to capture the technique, stripped of its original context, in a form that can be dropped into any future project without modification.
Two directions, and the first is one command:
- Looking something up — he wants to know whether the pantry already has a thing, or wants it pulled into the current project. See Looking something up and stop there.
- Putting something in — he's pointing at code worth keeping. Work through Steps 1–4 below.
Looking something up
The pantry ships its own CLI, so neither direction needs the repo cloned:
bunx github:nweii/pantry list
bunx github:nweii/pantry add <name>
list prints every component with its description. add writes the component's source into the current directory — raw source he owns and edits, not a dependency — and names any packages to install.
Read the list before answering whether something exists, rather than answering from memory: the pantry changes without this skill changing. Where a component matches, name it and offer to add it. Where the match is partial, say what the existing one actually does and let him decide between adapting it and building fresh.
Nothing matching is a normal outcome — say so plainly and build the thing. If what gets built turns out to be worth keeping, that's the other direction, and Step 1 starts below.
What makes a good pantry entry
A pantry entry should be:
- Truly abstracted: no variable names, imports, comments, or usage examples that reference the source project. Someone reading the component cold should have no idea where it came from.
- Self-contained: all logic lives in one file; external dependencies are minimal and explicit
- Opinionated defaults: parameterized just enough for useful variation, with sensible defaults that work out of the box without configuration
- Named for the technique, not the use case (e.g.,
grain, notbackground-texture)
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 · 123 lines · 79 tokens per session scan A b0be0ead6577
code-to-pantry is a skill published in the GitHub repository nweii/agent-stuff (8 stars, last pushed 14d ago), licensed MIT. It adds 79 tokens to every session and 1,521 once invoked, about $0.0004 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。.