What is nubecita CLAUDE.md?

Project instructions for Nubecita, a native Android client for Bluesky and the AT Protocol, built with Kotlin and Jetpack Compose. They cover the architecture, performance checks, tests, screenshots, and issue tracking.

Use them when developing or testing Nubecita, checking Compose performance, validating screenshots, running Gradle checks, or managing work in its beads issue tracker.

They give a coding agent the project's required tools, quality checks, and workflow for changing a multi-module Android app.

How kikin81/nubecita configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kikin81/nubecita. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/kikin81/nubecita/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/kikin81/nubecita

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/kikin81/nubecita/claude-md/github.svg)](https://agentmods.dev/instructions/kikin81/nubecita/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/kikin81/nubecita/claude-md"><img src="https://agentmods.dev/badge/instructions/kikin81/nubecita/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/kikin81/nubecita/claude-md"><img src="https://agentmods.dev/badge/instructions/kikin81/nubecita/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 10,191 This file is loaded in full into every session.

When invoked 10,191 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What 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 5.1	$0.10191	$0.10191
Opus 5	$0.05096	$0.05096
Sonnet 5	$0.02038	$0.02038
Haiku 4.5	$0.01019	$0.01019

Measured 10d ago against content hash 5de9cefdb8ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

nubecita CLAUDE.md 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 10d 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.

CLAUDE.md · 422 lines

How it starts

The opening of the file, as written. The whole thing — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project overview

Nubecita — a fast, lightweight, native Android client for Bluesky and the AT Protocol. Kotlin 2.3 + Jetpack Compose with Material 3 Expressive, MVI on ViewModel + StateFlow, Hilt for DI. 100% native; 120hz scrolling is a hard requirement.

Stack: Coil 3 (images), Media3 (video), atproto-kotlin SDK (networking), DataStore + Tink (encrypted OAuth sessions), Room (offline caches — :core:database is wired), Navigation 3. Firebase Analytics + Crashlytics + App Check are integrated.

Key commands

./gradlew :app:assembleDebug
./gradlew testDebugUnitTest
./gradlew spotlessCheck lint :app:checkSortDependencies
./gradlew jacocoTestReportAggregated
./gradlew :designsystem:validateDebugScreenshotTest     # validate against committed screenshot baselines
./gradlew :benchmark:connectedBenchmarkReleaseAndroidTest  # Macrobenchmark, needs connected device/emulator

# Compose Compiler stability + recomposition reports (perf audits)
./gradlew :app:assembleRelease -PcomposeReports=true -PdebugSignedRelease=true
# reports land at <module>/build/compose_compiler/

pre-commit run --all-files

Workflow

All work is tracked in beads (bd). Every change starts from a bd issue. There are two landing paths, and the bd issue's shape picks which one:

Standalone issue (bug, chore, task, one-off feature) → one short-lived branch + one PR to main. This is the Loop below and it is unchanged.
Epic (a parent with children) → a gh stack PR stack, one PR per child, landed with a single atomic merge so the whole feature reaches main in one push and cuts one semantic release. See Epics: stacked PRs.

When using Claude Code, the bd-workflow skill automates both paths; without it, the steps below are the convention.

Working from a second machine? Read docs/beads-multi-machine.md first. The bd database syncs across machines via the DoltHub remote (bd dolt push/pull), and a stale/shadowed dolt binary will silently fork it (the symptom is table has unknown fields). That runbook covers the required per-machine dolt setup, the pull-first/push-last session loop, and fork recovery — the canonical source of truth is the Dolt remote, never .beads/issues.jsonl.

Read the full file on GitHub · 422 lines

Changes

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.

10d ago First seen · 422 lines · 10,191 tokens per session scan A 5de9cefdb8ec

Subscribe to this mod's changes

nubecita CLAUDE.md is an instructions file published in the GitHub repository kikin81/nubecita (5 stars, last pushed today), licensed MIT. It adds 10,191 tokens to every session, about $0.0510 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.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

nubecita: Instructions file for Claude Code