agentleFS
Sign inStart free
ActuallyNodejamActuallyNodejam/openpaperwork/llms.txt

openpaperwork

llms.txt0 starsChanged 11 days agoApache-2.0View on GitHub

A library of 91 standards, laws and style guides for the agent you already have. Each pack holds a guideline with a named source, a starter, and a scripted check, so the agent you already have (Claude, ChatGPT, Cursor, Antigravity and others that read Agent Skills) writes the content and a script decides whether the invoice, agreement, letter, deck or paper meets the rules. Apache 2.0 licence. No account and no agent of its own. Facts an agent should hold…

The file

We split this llms.txt into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never ask a person to paste an API key into a chat, and never write one into this tree.

    line 17

≈ “Common” is an estimate: at least 1 in 5 of the 3,592 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
llms.txt
# OpenPaperwork

> A library of 91 standards, laws and style guides for the agent you already have. Each
> pack holds a guideline with a named source, a starter, and a scripted check, so the agent
> you already have (Claude, ChatGPT, Cursor, Antigravity and others that read Agent Skills) writes the
> content and a script decides whether the invoice, agreement, letter, deck or paper meets
> the rules. Apache 2.0 licence. No account and no agent of its own.

Facts an agent should hold before it acts here:

- A pack is a plain Agent Skill: a `SKILL.md`, the scripts that build the file, and the check.
- A run is finished only when the pack's check prints `pack check clean`. A fail names the
  rule and the evidence; fix what it names and run the check again.
- Scripts copy every number, date and identifier from the person's own file. Never retype them.
- A passing check means the file meets the cited rules. It is not certification and not
  legal, tax or accounting advice.
- Never ask a person to paste an API key into a chat, and never write one into this tree.

## Start here

- One line through the skills CLI: `npx skills add ActuallyNodejam/openpaperwork`; each pack is a plain Agent Skill, no manifest needed
- [README.md](README.md): what it is, install for each agent, what the library covers
- [AGENTS.md](AGENTS.md): setting up and changing this repository as a coding agent
- [Use the packs in your agent](docs/community-preview/PORTABLE_PACK.md): install, what each pack covers, what a run looks like
- [Bring your own agent](docs/community-preview/BRING_YOUR_OWN_AGENT.md): install and sign-in for each supported agent

## The library

- [Pack list](standards/PACKS.md): every pack with its guideline set, checks and starter files
- [Where each pack stands](docs/community-preview/STANDARDS.md): sources, and which settle the page as well as the content
- [Sources and licences](standards/SOURCES.md): where each rule comes from
- [Skills](skills): one folder per pack, each with its `SKILL.md`
- [Plugin marketplace](.claude-plugin/marketplace.json): `openpaperwork`, the whole library as one plugin for the Claude app and Claude Code, and one plugin per department; each workflow is started by its command, such as `/openpaperwork:invoice`

## Contributing

- [CONTRIBUTING.md](CONTRIBUTING.md): how a change is proposed and what evidence it needs
- [Add a standard](docs/community-preview/ADD_A_STANDARD.md): guideline, check, starter, three cases
- [Case protocol](standards/README.md): preparing a case and checking an output, offline

## Optional

- [Philosophy](docs/community-preview/PHILOSOPHY.md)
- [Roadmap](docs/community-preview/ROADMAP.md)
- [Credits](docs/community-preview/CREDITS.md) and [third-party notices](THIRD_PARTY.md)
- [Releasing](docs/community-preview/RELEASING.md)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free