What is compose-doctor CLAUDE.md?

Project instructions for compose-doctor, a Gradle plugin that checks Android Jetpack Compose code and reports a health score and machine-readable results.

Use them when developing or changing the plugin, its agent fix loop, CI workflows, scoring, or Compose playground tests.

They describe how to run the checks, inspect SARIF reports, and use results in automated pull-request checks.

How rotemmiz/compose-doctor configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to rotemmiz/compose-doctor. 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/rotemmiz/compose-doctor/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/rotemmiz/compose-doctor

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/rotemmiz/compose-doctor/claude-md/github.svg)](https://agentmods.dev/instructions/rotemmiz/compose-doctor/claude-md)

Your own site

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

Per session 1,597 This file is loaded in full into every session.

When invoked 1,597 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	$0.01597	$0.01597
Opus 5.5	$0.00639	$0.00639
Sonnet 5.5	$0.00319	$0.00319
Haiku 4.5	$0.00160	$0.00160

Measured 2mo ago against content hash 03fce5d8d5bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

compose-doctor 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 2mo 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 · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

compose-doctor

A deterministic health-check tool for Android Jetpack Compose codebases — the "React Doctor" equivalent for Compose. Ships as a Gradle plugin that produces a 0–100 health score, emits SARIF for an agent fix-loop, and powers a CI/PR gate, wrapped around compose-rules (mrmans0n) + detekt (android-lint planned).

Full design lives in docs/PLAN.md. Read it before making architectural changes.

Status

All three plan phases are implemented and CI is green:

Phase 1 — the plugin applies detekt + compose-rules, emits SARIF, scores it, and writes a machine-readable score.json. Verified against playground/ (a deliberately-broken module).
Phase 2 — agent skill at skills/compose-doctor/SKILL.md (run → read SARIF → fix loop).
Phase 3 — .github/workflows/compose-doctor.yml is a reusable gate (uploads SARIF for code-scanning, posts a sticky PR score comment, fails below a threshold); ci.yml builds + tests + smoke-runs the playground; pr-gate.yml dogfoods the gate (report-only). Verified green end-to-end (the sticky comment posts the current playground score).

Published: the plugin is live on the Gradle Plugin Portal as dev.composedoctor (current version 0.1.0) — apply with plugins { id("dev.composedoctor") version "0.1.0" }. The module applies com.gradle.plugin-publish with full metadata; .github/workflows/release.yml is the manual release (defaults to a credential-free dry run; a real release needs GRADLE_PUBLISH_KEY/ SECRET secrets). To cut a new version: scripts/set-version.sh <x.y.z> (no -SNAPSHOT — the Portal rejects it), then scripts/check-version.sh guards against drift across the manifests.

Remaining follow-ups (non-blocking): android-lint wiring (a11y/security dimensions; needs the Android SDK) and a composeDoctorBaseline task to seed detekt's baseline.xml.

Architecture

Gradle plugin only — no standalone CLI. The plugin orchestrates detekt as a cacheable Gradle task and aggregates its SARIF output (it does not embed detekt-core).

Read the full file on GitHub · 93 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.

2mo ago First seen · 93 lines · 1,597 tokens per session scan A 03fce5d8d5bb

Subscribe to this mod's changes

compose-doctor CLAUDE.md is an instructions file published in the GitHub repository rotemmiz/compose-doctor (5 stars, last pushed 2mo ago), licensed MIT. It adds 1,597 tokens to every session, about $0.0064 per session on Opus 5.5. 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.

Debugging Mobile ai-agent android ci code-health code-quality coding-agent

compose-doctor CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
compose-doctor CLAUDE.mdrotemmiz/compose-doctor	Instructions file	5	2mo ago	MIT	A	1,597	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

compose-doctor: Instructions file for Claude Code