agentleFS
Receiptor-AIReceiptor-AI/bookkeeping-skills/AGENTS.md

bookkeeping-skills

AGENTS.md8 starsChanged 8 months agoMITView on GitHub

This is the independent bookkeeping-skills Git repository. Paths and commands below are relative to this repository's root, whether cloned alone or checked out at skills/bookkeeping in the Receiptor monorepo. This file is the canonical repository guide; CLAUDE.md is only a local entrypoint. Do not require a parent checkout or sibling repository. Read runtime versions, package-manager requirements and commands from this checkout's package metadata and lockfile. For cross-repository work, request the other repository separately and state what could not be verified…

The file

We split this AGENTS.md into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Read the affected skill and its referenced resources before editing.

    line 15
  2. Distinctive:

    Keep references relative to this repository or the individual packaged skill as appropriate.

    line 16
  3. Distinctive:

    Use examples and supporting material already in the repository for focused validation.

    line 17

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
AGENTS.md

bookkeeping-skills agent guide

Repository context

This is the independent bookkeeping-skills Git repository. Paths and commands below are relative to this repository's root, whether cloned alone or checked out at skills/bookkeeping in the Receiptor monorepo. This file is the canonical repository guide; CLAUDE.md is only a local entrypoint. Do not require a parent checkout or sibling repository. Read runtime versions, package-manager requirements and commands from this checkout's package metadata and lockfile. For cross-repository work, request the other repository separately and state what could not be verified locally.

PR authority

Only Kai may create or publish PRs, including drafts. Kai means a task explicitly launched through Gleap Kai Code (Cloud or Bridge); a standalone Codex, Claude or CLI session is not Kai, even when configuring Kai. Other agents hand off changes and validation results without creating a PR through any tool, API or browser. Follow the repository's configured default/base branch; do not invent a staging branch. Preserve unrelated work, never force-push protected branches, and leave merges, releases and production changes to Romeo's explicit instruction.

Scope and validation

This repository owns portable bookkeeping skills. SKILL.md is the user-facing entrypoint, skills/ contains task skills, and jurisdictions/ contains country-specific references. Repository development instructions are separate from those runtime skill instructions.

  • Read the affected skill and its referenced resources before editing. Preserve evidence standards, jurisdiction boundaries, approval requirements and accountant-reviewable output.
  • Keep references relative to this repository or the individual packaged skill as appropriate. Validate that copied/installed skill folders retain the resources they reference.
  • Use examples and supporting material already in the repository for focused validation. There is no package-manager test command to assume from a parent repository.
  • Bookkeeping source changes do not authorize filing taxes, moving money or changing a customer's accounting records.

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.