Rules

Open **one** index below. Do not load multiple. Specialized rows (e.g. dataset prep, what's next) are **alternatives** to the general research/skills index — not extra docs to load together. | If the task is… | Index |

CatatZ adalah aplikasi pencatatan keuangan berbasis Next.js 16 App Router, Supabase, Server Actions, dan PWA Serwist. File ini adalah instruksi repository-level untuk agent saat bekerja dari root repository CatatZ.

Machine-readable operating guidance for AI coding agents in **hotosm/ui**. Project: **hotosm/ui** Accountability: human maintainers are responsible for all merged changes.

Guidance for AI agents (and humans) working in this repository. This is the source of truth; `CLAUDE.md` is a symlink to it. `liatrio-otel-collector` is a custom OpenTelemetry Collector distribution. It bundles upstream

Compact ramp-up guide for AI agents. Each item exists because an agent would likely miss it.

This repository uses `.okf/` as compact operational memory for AI agents. OKF v0.1: non-reserved `.md` files need YAML frontmatter with non-empty `type`, `title`, and `description`; `index.md` is a directory listing; only bundle-root `index.md` may have frontmatter (`okf_version`).

Guidance for any AI agent working in this repository.

This file gives contributor agents enough project context to make focused changes without rediscovering the repo shape.

This is the first-page guide for agents working in the Hands repository. Hands manages APK uploads, release channels, public update checks, share pages, and Raft-based access control on Cloudflare Workers, Containers, D1, and

Skill files (SKILL.md, references/, etc.) are loaded as context for AI agents. Follow these rules when editing them, per the [Agent Skills specification](https://agentskills.io/specification):

Always create a feature branch before making any code changes: git checkout -b <descriptive-branch-name> Name the branch after the feature or fix, for example: Never commit directly to `main`.

Agent-focused notes for safe, fast contributions. Format reference: [agents.md](https://agents.md/).

AI coding agent instructions for project conventions and guidelines.

> How an AI coding/operations agent (Hermes, Claude Code, Codex, etc.) should > work with this skill in any environment. This file exists so that an agent dropped into the project cold -- with no prior context -- can use the skill correctly on first contact. Read this

These instructions apply to this repository and all child directories.

> Instructions for AI coding agents working on the Prolific CLI.

This file defines repository-wide instructions for coding agents working in this project.

For an agent consuming `wpd`. wpd finds and investigates; it does not grade, rank, or recommend. It hands you typed, measurement-tagged numbers and a clean exit code; the judgment stays with you.

> **Before you invoke megaplan, run the `megaplan-prep` skill.** It's the front door for every run: it sizes the work (one plan vs. an epic), shapes the brief, and picks the profile (intelligence tier), robustness level, and thinking depth. Do not run `<launcher> init` without it.

Frontend UI for creating and managing prisoner contacts within the Digital Prison Service (DPS). See [README.md](README.md) for setup and running instructions.

<!-- Keep this file under 120 lines. Every line loads into every session. --> <!-- Passive context > active retrieval. Put critical knowledge HERE, not in separate files. -->

This project uses **bd** (beads) for issue tracking. Run `bd onboard` to get started.