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/martinpuli/createanapp/agents-mdgit clone --depth 1 https://github.com/MartinPuli/createAnAppWhat 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 | $0.00291 | $0.00291 |
| Opus 5 | $0.00146 | $0.00146 |
| Sonnet 5 | $0.00058 | $0.00058 |
| Haiku 4.5 | $0.00029 | $0.00029 |
Grade A, and why
createAnApp 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.
What it actually says
Repository instructions for agents
- Treat every launch claim as unproven until supported by current-state evidence.
- Never copy credentials, tax data, banking data, home addresses, phone numbers, private email addresses, API keys, App Store Connect private keys, signing certificates, or provisioning profiles into the repository.
- Browse current Apple primary sources before completing a submission or advising on a rule that may have changed.
- Preserve unrelated user changes. Use a feature branch and explicit staging.
- Record assumptions, unknowns, owner, evidence, and next action in the launch dossier.
- Do not submit legal, tax, banking, DSA trader, export-control, or regulated-professional attestations for the human.
- Do not claim product-market fit from idea scores, downloads, one purchase, approval, or positive feedback.
- Do not market a feature until the exact release build proves it.
- Use real app UI in screenshots and demos. Label synthetic media and never fabricate testimonials, customers, reviews, or results.
- When a skill references another skill, invoke it if available; otherwise implement the referenced evidence gate directly.
- For release work, follow
docs/executable-release-flow.mdand verify the exact IPA that will be uploaded; never verify one archive and recreate another for delivery. - Treat
.mcp.jsonas a pinned convenience, not a trust decision. Review tool source, permissions, telemetry, and release notes before changing its version.
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 · 15 lines · 291 tokens per session scan A b211d0b8a883
createAnApp AGENTS.md is an instructions file published in the GitHub repository MartinPuli/createAnApp (14 stars, last pushed 12d ago), licensed MIT. It adds 291 tokens to every session, about $0.0015 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 2026-08-30.
Other instructions, from other repositories
ios-swiftui-accessibility-techniques CLAUDE.md
Instructions for cvs-health/ios-swiftui-accessibility-techniques, covering project rules, copyright header (required), rules, swift files and markdown files.
AniShelf AGENTS.md
Instructions for samuelhe52/AniShelf, covering anishelf - developer notes, workflow, code style, testing and commits.
swift-architecture-skill CLAUDE.md
Instructions for efremidze/swift-architecture-skill, covering swift architecture skill, project structure, how the skill works and key conventions.
swift-architecture-skill AGENTS.md
Instructions for efremidze/swift-architecture-skill, covering agents guidelines for swift architecture skill, working with this repository, 1. understanding the skill, 2. modifying architecture playbooks and 3. testing and validation.
swift-ios-skills AGENTS.md
AGENTS.md instructions for dpearson2699/swift-ios-skills, covering claude.md, communication style, what this repo is, core repo shape and required context before any skill change.
swiftui-compose-skill AGENTS.md
Instructions for sorunokoe/swiftui-compose-skill, covering agents.md — swiftui-compose, what this repository is, repository structure, how to apply this skill and reference selection guide.