agentmods.dev

meta-loop-ios CLAUDE.md

meta-loop-ios CLAUDE.md is an instructions file for coding agents from jpavley/meta-loop-ios. It costs 472 tokens per session, scanned A, original, MIT.

Documentation for a Claude Code plugin that guides iOS development through setup, wireframes, specifications, implementation, and recorded learnings. It describes the project structure, standards, and installation process.

In plain words
What is it for?
Use it to understand, install, or maintain the Meta-Loop iOS workflow. It covers commands for setting up a project, reviewing wireframes, writing specifications, implementing them, and capturing lessons.
Why use it?
It gives developers a shared process and explains where each command and reference document belongs. The project itself contains no Swift code or Xcode build.

Instructions file

not rated 3 6mo ago A scan 472 tokens original MIT
View the source file jpavley/meta-loop-ios
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/jpavley/meta-loop-ios/claude-md
Clone the repo
git clone --depth 1 https://github.com/jpavley/meta-loop-ios

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.

agentmods badge for meta-loop-ios CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jpavley/meta-loop-ios/claude-md.svg)](https://agentmods.dev/instructions/jpavley/meta-loop-ios/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jpavley/meta-loop-ios/claude-md"><img src="https://agentmods.dev/badge/instructions/jpavley/meta-loop-ios/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 472 This file is loaded in full into every session.
When invoked 472 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.

ModelPer sessionOnce invoked
Fable 5 $0.00472 $0.00472
Opus 5 $0.00236 $0.00236
Sonnet 5 $0.00094 $0.00094
Haiku 4.5 $0.00047 $0.00047

Measured 3d ago against content hash 6584524cad63, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

meta-loop-ios 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 3d 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.

CLAUDE.md · 45 lines

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.

Meta-Loop iOS Plugin

A Claude Code plugin providing a structured AI-assisted iOS development methodology. This is a documentation-only project — no Swift code, no Xcode project, no build step.

Project Structure

.claude-plugin/plugin.json   # Minimal manifest (Anthropic standard)
commands/                    # Slash commands (installed to .claude/commands/)
  ml-setup.md               # Step 0: Scaffold project for meta-loop workflow
  ml-wireframe.md            # Step 1: Review wireframe
  ml-spec.md                 # Step 2: Create spec from wireframe
  ml-impl.md                 # Step 3: Implement from spec
  ml-retain.md               # Step 4: Capture learnings
skills/                      # Reference docs (installed to .claude/skills/)
  meta-loop-methodology/     # Process theory + user guide
  wireframe-design/          # Wireframe creation tips
  view-specifications/       # Spec writing guide + template
  project-structure/         # Directory layout + file responsibilities
install.sh                   # Copies commands + skills into a target project

Standards

  • Follows Anthropic knowledge-work-plugins format
  • Commands use argument-hint: (not arguments:) in YAML frontmatter
  • Skills use YAML frontmatter with name: and description:
  • All doc references in commands point to skills/.../SKILL.md

Conventions

  • Command files are markdown with YAML frontmatter
  • Skill files are named SKILL.md inside a named directory
  • The plugin manifest at .claude-plugin/plugin.json is minimal (name, version, description, author)
  • install.sh copies commands to .claude/commands/ and the skills tree to .claude/skills/
  • Keep examples generic (not tied to a specific app)
  • Keep content platform-agnostic in requirement sections; platform-specific code goes only in Implementation Reference sections

Repo Info

  • Remote: github.com:jpavley/meta-loop-ios.git
  • Branch: main
  • License: MIT
  • Author: John Pavley

Read the full file on GitHub · 45 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.

  1. 3d ago First seen · 45 lines · 472 tokens per session scan A 6584524cad63

Subscribe to this mod's changes

meta-loop-ios CLAUDE.md is an instructions file published in the GitHub repository jpavley/meta-loop-ios (3 stars, last pushed 6mo ago), licensed MIT. It adds 472 tokens to every session, about $0.0024 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.

Mobileai-assisted-developmentclaude-codeclaude-code-pluginiosmeta-loopswiftui
Related

Other instructions, from other repositories

ios-swiftui-accessibility-techniques CLAUDE.md

Claude Code instructions for cvs-health/ios-swiftui-accessibility-techniques, covering project rules, copyright header (required), rules, swift files and markdown files.

cvs-health/ios-swiftui-accessibility-techniques · 455 tokens

AniShelf AGENTS.md

Instructions for samuelhe52/AniShelf, covering anishelf - developer notes, workflow, code style, testing and commits.

samuelhe52/AniShelf · 1,083 tokens

swift-architecture-skill CLAUDE.md

Instructions for efremidze/swift-architecture-skill, covering swift architecture skill, project structure, how the skill works and key conventions.

efremidze/swift-architecture-skill · 422 tokens

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.

efremidze/swift-architecture-skill · 987 tokens

createAnApp AGENTS.md

Instructions for MartinPuli/createAnApp, a project described as: Evidence-gated AI agent skills for shipping Apple apps from idea validation to App Store launch.

MartinPuli/createAnApp · 291 tokens

cloudx-sdk-agents AGENTS.md

Instructions for cloudx-io/cloudx-sdk-agents, covering agents.md, the one rule, repository map and for agent tooling maintainers.

cloudx-io/cloudx-sdk-agents · 513 tokens