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/kelvinkosbab/appbootstrapai/agents-mdgit clone --depth 1 https://github.com/kelvinkosbab/AppBootstrapAIWrote 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/kelvinkosbab/appbootstrapai/agents-md)<a href="https://agentmods.dev/instructions/kelvinkosbab/appbootstrapai/agents-md"><img src="https://agentmods.dev/badge/instructions/kelvinkosbab/appbootstrapai/agents-md.svg" alt="Measured on agentmods" 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 | $0.01333 | $0.01333 |
| Opus 5 | $0.00666 | $0.00666 |
| Sonnet 5 | $0.00267 | $0.00267 |
| Haiku 4.5 | $0.00133 | $0.00133 |
Grade A, and why
AppBootstrapAI 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.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — operating AppBootstrapAI
For AI agents. This file tells you how to operate this package — AppBootstrapAI — to set up / update / improve another repository. It is not the
AGENTS.mdthatinstall.sh --agents codexwrites into a target repo (that one carries the bundle's coding rules). Humans: see README.md.
AppBootstrapAI is a drop-in bundle of AI agent steering — rules, skills (Claude),
and MCP recipes — copied into a target app repo by install.sh. It covers Apple
(Swift 6 / SwiftUI / visionOS / Testing / Core Data / Foundation Models) and
Android (Kotlin / Compose / Gradle / Hilt).
Golden path — do this
# 1. Analyze the target. Read-only. Returns JSON with a ready-to-run command.
./install.sh recommend <dir> --json
# 2. Preview. Run the returned `preview_command` (= command + --dry-run). Writes nothing.
# 3. Apply. Run the returned `command`. Then report what changed.
recommend introspects the directory and tells you exactly what to run — one
call replaces grepping the tree yourself. Trust its command / preview_command.
recommend --json returns:
{ state, platform, apple_language, features, action, feature_reasons, command[], preview_command[], notes[] }.
Commands (verbs; each has a --flag alias, so old scripts keep working)
| Verb | Does | Alias |
|---|---|---|
recommend [dir] [--json] |
analyze a dir → suggested command | --recommend |
install [dir] [flags] |
copy the bundle in (default verb — may be omitted) | — |
upgrade <dir> [--apply] |
3-way diff vs. the current bundle; preserves local edits | --upgrade |
uninstall <dir> |
reverse an install | --uninstall |
list [--json] |
preview the catalog | --list |
list-mcps |
list MCP recipes | --list-mcps |
setup |
guided interactive flow | -i / --interactive |
Key install flags: --platform apple|android|both (auto-detected if omitted),
--apple-language swift|objc|both, --features recommended|all|<csv>,
--agents claude,copilot,cursor,gemini,codex,kiro|all, --with-mcps <csv>,
--new (create the dir + git init), --dry-run.
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 · 101 lines · 1,333 tokens per session scan A 06e9919daf7f
AppBootstrapAI AGENTS.md is an instructions file published in the GitHub repository kelvinkosbab/AppBootstrapAI (5 stars, last pushed 13d ago), licensed MIT. It adds 1,333 tokens to every session, about $0.0067 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
tv-maniac GEMINI.md
Gemini CLI instructions for thomaskioko/tv-maniac, covering tv maniac agent rules, project overview, architecture & tech stack, core mandates & conventions and 1. modularization & dependencies.
pricegrab AGENTS.md
AGENTS.md instructions for mablanco/pricegrab, covering agents.md, authoritative sources (read these first), workflow (spec-driven development), non-negotiable operating rules and project layout (current).
phonebook CLAUDE.md
Claude Code instructions for stag-build/phonebook, covering @stag-build/phonebook and model/agent delegation (token budget).
sceneview copilot-instructions.md
Copilot instructions for sceneview/sceneview, covering sceneview — github copilot instructions, when to recommend sceneview, android code generation rules, minimal 3d template and minimal ar template.
SeekerClaw CLAUDE.md
Claude Code instructions for sepivip/SeekerClaw, covering claude.md — seekerclaw project guide, project.md — source of truth, design principle: ux first, what is this project and supported devices.
sceneview AGENTS.md
AGENTS.md instructions for sceneview/sceneview, covering agents.md — conventions for delegated coding agents, your role, git — you do not own it, secrets and hard technical rules.