What is launch-store AGENTS.md?

A repository instruction file containing the working rules for AI agents and contributors to Launch Store, including code ownership, branch naming, pull requests, and required checks.

It guides repository navigation, branch and pull-request work, module ownership decisions, and the validation required before a change is accepted.

It reduces mistakes that linters cannot catch, such as editing the wrong module, committing directly to the main branch, or skipping project validation.

launch-store AGENTS.md — Instructions file for Codex and OpenCode by YosefHayim: A repository instruction file containing the working rules

Install

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.

agentmods

npx agentmods add instructions/yosefhayim/launch-store/agents-md

Clone the repo

git clone --depth 1 https://github.com/YosefHayim/launch-store

Made for: Codex, OpenCode.

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/yosefhayim/launch-store/agents-md.svg)](https://agentmods.dev/instructions/yosefhayim/launch-store/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/yosefhayim/launch-store/agents-md"><img src="https://agentmods.dev/badge/instructions/yosefhayim/launch-store/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,863 This file is loaded in full into every session.

When invoked 1,863 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.01863	$0.01863
Opus 5	$0.00932	$0.00932
Sonnet 5	$0.00373	$0.00373
Haiku 4.5	$0.00186	$0.00186

Measured 4d ago against content hash 97ecdca2a3e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

launch-store 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 4d 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.

AGENTS.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Working rules for AI agents and contributors editing Launch. This file holds only what you can't infer from the code and configs: module ownership, conventions a linter can't catch, and the validation gate every change must pass. Usage lives in README.md; style depth lives in CODE-STYLE.md. Branch and PR workflow lives in BRANCHING.md.

Claude Code reads this through CLAUDE.md, which imports this file with @AGENTS.md.

Branching And PRs

Do not commit to main. Branch as feat|fix|refactor|chore|docs/<domain>/<slug>, open a PR, label domain:<domain>, keep the gate green, delete the branch after merge.
Domains: foundation, config, credentials, build, apple, google, store, release, testflight, readiness, agents, cli, docs.
Full rules, CODEOWNERS path map, and the optional experiment/layered-history lab: BRANCHING.md.

Repo Layout - Who Owns What

One TypeScript / Node ESM package. Top-level src/ ownership:

Path	Owns
`src/cli`	Thin Commander wiring: command names, flags, help text, `runCliProgram(...)`. No domain orchestration.
`src/core`	Domain programs, Effect services, config/schema, build/release/store/readiness logic, generated docs, and type homes.
`src/providers`	Swappable backend implementations for build, storage, credentials, submit, and compute providers.
`src/apple`	App Store Connect transport and the generated Apple API mirror.
`src/google`	Google Play transport wrappers around Google's official generated clients.
`src/testkit`	Shared test fakes and Effect test layers.

Current src/core layout:

src/core/
 adopt/          # importing live store state into config
 agents/         # agent skill scaffolding
 build/          # pipeline, build flags, fingerprint, logs, diagnostics, remote/eas handoff
 config/         # config schema/load/scaffold/semantics/project setup
 credentials/    # accounts, secrets, keychain, signing assets
 dashboard/      # terminal dashboard state/rendering
 distribution/   # install manifests, OTA updates, storage-facing distribution helpers
 docs/           # generated command/config docs
 doctor/         # doctor context/inspection
 insights/       # review/vitals aggregation
 listing/        # listing drafts/apply logic and screenshot asset specifications
 mcp/            # MCP server/tools
 migrate/        # EAS/fastlane migration helpers
 plan/           # config-vs-store planning/drift
 privacy/        # privacy parsing/reconciliation/nutrition labels
 readiness/      # store readiness/probes/preflight
 release/        # release, rollout, TestFlight/public release
 releaseTrain/   # release-train records/guards/orchestration
 services/       # Launch-owned Effect service contracts + Live/Test layers
 snapshot/       # live store snapshot/diff/source capture
 store/          # store sync, catalog/product/offers/pricing/reviews/reports across stores
 terminal/       # CLI presentation helpers, glossary, completion, wordmark
 types/          # exported domain shapes imported from owning modules

Read the full file on GitHub · 125 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.

4d ago First seen · 125 lines · 1,863 tokens per session scan A 97ecdca2a3e2

Subscribe to this mod's changes

launch-store AGENTS.md is an instructions file published in the GitHub repository YosefHayim/launch-store (9 stars, last pushed 7d ago), licensed MIT. It adds 1,863 tokens to every session, about $0.0093 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.

android app-store app-store-connect cli code-signing

launch-store AGENTS.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

Branching And PRs

Repo Layout - Who Owns What

What this file has done since we first saw it

Other instructions, from other repositories

appstore-ppp-pricing-agent-skill CLAUDE.md

appstore-precheck AGENTS.md

claude-aso-audit-skill CLAUDE.md

flutter-cn-overseas-app-skills AGENTS.md

aso-mcp CLAUDE.md

indie-app-shipping AGENTS.md