Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/cuongdev/indie-app-shipping/agents-mdgit clone --depth 1 https://github.com/cuongdev/indie-app-shippingWhat 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 | $0.01103 | $0.01103 |
| Opus 5 | $0.00551 | $0.00551 |
| Sonnet 5 | $0.00221 | $0.00221 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
indie-app-shipping AGENTS.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 2d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Indie App Shipping
Cross-tool version of the indie-app-shipping playbook. This file is read by Cursor, Gemini CLI, and Antigravity (and Claude Code) at session start. Claude Code and Antigravity can alternatively load the richer native skill in indie-app-shipping/SKILL.md (same content, on-demand). The detailed checklists live as plain markdown under indie-app-shipping/references/** and templates under indie-app-shipping/assets/** — read the relevant file when you reach its step.
Use this whenever the user is shipping a small mobile app on iOS/macOS (App Store) or Android (Google Play): scaffolding app structure; wiring onboarding/settings/paywall/restore/legal screens; writing or reviewing store metadata; planning screenshots; running a pre-submission compliance check; writing review notes; setting up Play closed testing; handling a rejection; or deciding which shipped apps to invest in further. Trigger even when the user doesn't say "checklist."
Strategic frame
Two ways to ship: (1) one or two deep apps, or (2) many small apps to test fast. This playbook is for path 2 — ship a clean minimal app, measure real users, deepen only what shows signal. The point of a v1 is information, not perfection. If the user is clearly resourced for path 1 on a specific app (real budget, real signal), say so and adjust.
The user works in Vietnamese — respond in Vietnamese unless they switch. Store Console fields and platform terms stay in English where that's the on-platform value.
Platform selection (decide first)
- iOS / macOS →
indie-app-shipping/references/ios/ - Android (Google Play) →
indie-app-shipping/references/android/ - Both → read both; build one skeleton with a store-abstracting billing layer (RevenueCat wraps StoreKit 2 + Play Billing).
Key differences that change how you ship: iOS has a dedicated keyword field, Play has none (weave keywords into title/short/full description); StoreKit 2 vs Play Billing; privacy nutrition labels vs Data safety form; iOS in-app account deletion vs Play in-app plus a public web deletion URL; "Sign in with Apple" required on iOS if you offer social login (no Play equivalent); human App Review vs faster but stricter Play automation; new personal Play accounts must pass a closed test (12 testers, 14 continuous days) before production. Which first? Lead with the platform where your users and monetization live — Play for VN-market reach/volume, App Store for US-market revenue — then port winners.
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.
- 2d ago First seen · 52 lines · 1,103 tokens per session scan A ea94be0058aa
indie-app-shipping AGENTS.md is an instructions file published in the GitHub repository cuongdev/indie-app-shipping (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,103 tokens to every session, about $0.0055 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
claude-code-apple-skills CLAUDE.md
Instructions for rshankras/claude-code-apple-skills, covering claude.md, repository purpose, architecture, skill structure and yaml frontmatter (required).
mobile-ai-agents AGENTS.md
Instructions for salmanashraf/mobile-ai-agents, covering agents.md — mobile ai agents, what this repo is, repo map, how to use an agent and option a — paste into codex chat.
mobile-ai-agents copilot-instructions.md
Instructions for salmanashraf/mobile-ai-agents, covering github copilot instructions — mobile dev skill agents, agent rules, android code review, android crash analysis and swift / ios code review.
mobile-ai-agents CLAUDE.md
Instructions for salmanashraf/mobile-ai-agents, covering claude.md — mobile ai agents, what this repo is, quick start, install everything and install by platform.
appshot AGENTS.md
Instructions for trunghaiy/appshot, covering agents.md, repository overview, architecture, repository structure and agent skills specification.
appshot CLAUDE.md
Instructions for trunghaiy/appshot, covering appshot — claude code project brief, key constraint, where things live, build and git.