Borrowing it
Nothing to install: this file belongs to Abdallah-Abdelazim/mobile-pr-review-plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Abdallah-Abdelazim/mobile-pr-review-plugin/main/CLAUDE.mdgit clone --depth 1 https://github.com/Abdallah-Abdelazim/mobile-pr-review-pluginWrote 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.
[](https://agentmods.dev/instructions/abdallah-abdelazim/mobile-pr-review-plugin/claude-md)<a href="https://agentmods.dev/instructions/abdallah-abdelazim/mobile-pr-review-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/abdallah-abdelazim/mobile-pr-review-plugin/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.
<a href="https://agentmods.dev/instructions/abdallah-abdelazim/mobile-pr-review-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/abdallah-abdelazim/mobile-pr-review-plugin/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01036 | $0.01036 |
| Opus 5 | $0.00518 | $0.00518 |
| Sonnet 5 | $0.00207 | $0.00207 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
mobile-pr-review-plugin 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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mobile-pr-review (plugin repo)
A Claude Code plugin: one skill (review-mobile-pr) + 7 bundled subagents for expert Android/iOS/KMP PR review, packaged as its own installable marketplace.
Intent Layer
Before modifying code in a subdirectory, read its CLAUDE.md first to understand local patterns and invariants.
- Review knowledge base & orchestration:
skills/review-mobile-pr/CLAUDE.md- the skill itself (SKILL.md) and the platform review reference docs it and the agents read
No node for agents/ or .claude-plugin/ — both are below the token threshold; covered inline below.
mobile-pr-review-plugin/
├── .claude-plugin/
│ ├── plugin.json # name/version/description — this repo IS the plugin
│ └── marketplace.json # this repo is also its own single-plugin marketplace (source: "./")
├── agents/ # 7 subagent specs — auto-namespaced mobile-pr-review:mobile-pr-* on install
└── skills/review-mobile-pr/ # the skill — see its CLAUDE.md
Key Invariants
plugin.json's"name"field must staymobile-pr-review— it's baked intomarketplace.json's plugin entry, the README's install commands, and everymobile-pr-review:mobile-pr-*agent reference insideskills/review-mobile-pr/SKILL.md. Renaming it breaks all three.- Every file in
agents/here must stay byte-identical to its counterpart at~/.claude/agents/mobile-pr-*.md(the maintainer's personal global copies, used to test changes locally before they're packaged). Editing one without the other silently desyncs local testing from what ships. Same rule forskills/review-mobile-pr/{SKILL.md,references/*.md}vs.~/.claude/skills/review-mobile-pr/{SKILL.md,references/*.md}— except the two SKILL.md copies intentionally diverge on exactly two things: this repo's copy usesmobile-pr-review:mobile-pr-*namespaced agent names and${CLAUDE_PLUGIN_ROOT}-relative reference paths; the personal copy uses baremobile-pr-*names and~/.claude/skills/...-absolute paths. Any other divergence between the two SKILL.md copies is a bug. - This repo's
SKILL.mdimplements a draft-or-live posting mode (defaults to draft/pending review; live posts immediately) resolved via a--draft/--liveinvocation flag or a one-time prompt. It's referenced from 6 places in that file (Posting mode section, Safety contract, step 1 header, step 7's API payload, step 8's summary, the Fallback section) — a change to this feature must be applied consistently at all 6, in both SKILL.md copies. - No agent, and no step in
SKILL.md, may usegh pr review --comment,gh pr comment, or the issues comments API — everything posts through the singlepulls/<number>/reviewscall in step 7, so draft and live comments always land together in one review.
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 · 45 lines · 1,036 tokens per session scan A 12e265455d8f
mobile-pr-review-plugin CLAUDE.md is an instructions file published in the GitHub repository Abdallah-Abdelazim/mobile-pr-review-plugin (1 stars, last pushed 17d ago), licensed MIT. It adds 1,036 tokens to every session, about $0.0052 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.
Other instructions, from other repositories
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.
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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.