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/semantic-craft/ios-vibebuddy/agents-mdgit clone --depth 1 https://github.com/semantic-craft/iOS-vibebuddyWrote 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/semantic-craft/ios-vibebuddy/agents-md)<a href="https://agentmods.dev/instructions/semantic-craft/ios-vibebuddy/agents-md"><img src="https://agentmods.dev/badge/instructions/semantic-craft/ios-vibebuddy/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 | $0.00392 | $0.00392 |
| Opus 5 | $0.00196 | $0.00196 |
| Sonnet 5 | $0.00078 | $0.00078 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
iOS-vibebuddy 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 today.
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
AGENTS.md
Agent-facing configuration for the iOS-vibebuddy repo.
Verification strategy
This is a personal-use project. Default to real end-to-end acceptance: build and run the actual Mac app/daemon, exercise it with real Claude Code or Codex Desktop/CLI data, and verify the resulting snapshot, UI, notification, recovery, and installation behavior as applicable.
Keep only a small number of fast automated tests for critical pure logic or a previously reproduced regression. Test-first development, coverage targets, and one-test-per-edge-case matrices are not required. Preserve existing useful tests, but do not let low-value test expansion displace end-to-end validation.
Agent skills
Skills come from dev-link (Matt Pocock groups + design-ui), never from
anything tracked in this repo. .agents/skills/<name> are absolute symlinks
into the xw-skills warehouse, and .claude/skills/<name> are relative
symlinks pointing at those. Both directories are gitignored/excluded and
machine-local. Re-run dev-link after pulling warehouse changes; this repo
owns no skills of its own.
Issue tracker
Issues and PRDs live as local markdown under .scratch/<feature>/ in this repo
(not GitHub Issues). See docs/agents/issue-tracker.md.
Triage labels
Five canonical triage roles use their default strings (needs-triage,
needs-info, ready-for-agent, ready-for-human, wontfix), recorded as a
Status: line in each issue file. See docs/agents/triage-labels.md.
Domain docs
Single-context layout — one CONTEXT.md + docs/adr/ at the repo root.
See docs/agents/domain.md.
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.
- today Changed · +16 lines · +182 tokens per session f01f83c57c8e
- 5d ago First seen · 25 lines · 210 tokens per session scan A 1c7b6cf0df78
iOS-vibebuddy AGENTS.md is an instructions file published in the GitHub repository semantic-craft/iOS-vibebuddy (85 stars, last pushed today), licensed MIT. It adds 392 tokens to every session, about $0.0020 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
FluidAudio CLAUDE.md
Claude Code instructions for FluidInference/FluidAudio, covering claude.md, project overview, critical development rules, never use @unchecked sendable and never create dummy models or synthetic data.
apple-browsers pixels.instructions.md
Instructions for duckduckgo/apple-browsers, a project described as: DuckDuckGo iOS & macOS browsers.
apple-platform-build-tools-claude-code-plugin CLAUDE.md
Claude Code instructions for rhyean88/apple-platform-build-tools-claude-code-plugin, covering claude.md, what this repository contains, repository structure, key design principles and file organization.
apple-platform-build-tools-claude-code-plugin CLAUDE.md
Claude Code instructions for kylehughes/apple-platform-build-tools-claude-code-plugin, covering claude.md, what this repository contains, repository structure, key design principles and file organization.
apple-dev-skills AGENTS.md
Instructions for gaelic-ghost/apple-dev-skills, covering agents.md, scope, apple rules, install guidance and validation.
FluidAudio copilot-instructions.md
Copilot instructions for FluidInference/FluidAudio, covering fluidaudio - agent development guide, build & test commands, architecture, critical rules and code style (swift-format config).