Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

bama

skill · daveebbelaar/bamaMIT licenceAudited 30 Oct 2026 · source e0ceb0698707

★ 843pushed today
✓SAFEGrade B · 89/100 · 30 Oct 2026 · e0ceb06
843repo stars · whole daveebbelaar/bama

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit e0ceb0698707 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Build any Mac app. Start here to pick the next skill for a native macOS app.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “bama (daveebbelaar/bama)”. Retrieved 30 Oct 2026. https://modelsatlas.com/skills/daveebbelaar/bama

Trust audit

Audit 0.4.1 · source read 30 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha e0ceb0698707 · 30 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherdaveebbelaar GitHub userOwner of the repository this skill is read from
  • Source folderdaveebbelaar/bama/skills/start/bamaThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdicte0ceb0698707A new audit runs when the source changes
  • Repository statusNot archivedPushed today
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Build any Mac app. Start here to pick the next skill for a native macOS app.

---
name: bama
description: Build any Mac app. Start here to pick the next skill for a native macOS app.
disable-model-invocation: true
---

# Build any Mac app

Find where the user is on the path below, then call the Skill tool with the
skill for that step. One skill per call.

```text
idea -> research -> clone (optional) -> app-brief -> user-stories -> new-mac-app
     -> mac-design + design-system + app-icon -> improve-loop (ux, code, design, verify, commit) -> repeat
```

Pick the app's name first (app-brief, step 1) and create
`<parent>/<AppName>/docs/` before research, so every skill writes into the
same folder. Design comes right after the scaffold: tokens from the first
view, and the real icon in every snapshot.

## Plan

| The user has | Skill |
| --- | --- |
| A vague idea, or asks "what should I build" | `research`, then `app-brief` |
| An app they want to replace or rebuild | `clone` |
| A brief or a screen index, no backlog | `user-stories` |
| A spec from BAMA's `specs/` folder | `app-brief` (it copies the spec) |

## Build

| The user wants to | Skill |
| --- | --- |
| Start a new project | `new-mac-app` |
| Write or fix Swift and SwiftUI code | `swift-swiftui` |
| Hook into macOS: hotkeys, menu bar, windows, screen capture, Shortcuts | `os-integrations` |
| Make it fast: hangs, stutter, GPU, video, memory | `performance` |
| Let Claude Code, Codex, or scripts drive the app: a CLI, an MCP server | `agent-cli` |
| Refactor, clean up, or check the code as it grows | `improve-architecture` |

## Design

| The user wants to | Skill |
| --- | --- |
| Decide how a feature works and what it says: names, flow, modals, accessibility | `ux-design` |
| Make it look and feel like a Mac app | `mac-design` |
| An accent or brand color, a color picker, tokens | `design-system` |
| Their own parts and feel, not Apple's: buttons, rows, sidebar, icons | `design-kit` |
| The look of an app they name, or screenshots of one | `design-from-app` |
| One set of colors, radii, motion, and controls for the whole app | `design-system` |
| Fix spacing and alignment, or check the layout on the grid | `layout-grid` |
| An app icon | `app-icon` |

## Ship

| The user wants to | Skill |
| --- | --- |
| Build it and look at every page | `build-and-verify` |
| Tests, a self-test, or an agent that drives the running app | `test-mac-app` |
| Work through the backlog on its own | `improve-loop` |

## Done when

You named the step, called its skill, and told the user which skill comes
after it.

Excerpt, first 2,516 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit e0ceb06

Download folder ↗
git clone https://github.com/daveebbelaar/bama
git -C bama checkout e0ceb0698707

The author documents no install command, so this uses the repository directly. Our verdict covers commit e0ceb0698707 only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
Claude CodeMentioned in its text, not testedSkills for Claude Code · About Claude Code
CodexMentioned in its text, not testedSkills for Codex · About Codex
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source e0ceb0698707

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/daveebbelaar/bama/badge.svg)](https://modelsatlas.com/skills/daveebbelaar/bama/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

ponytail✓SAFE

dietrichgebert/ponytail

Lazy senior dev mode: the smallest change that fully solves the task, and a reply a busy human understands in one read. Use on any coding task (writing, fixing, refactoring, reviewing, choosing dependencies) and when…

★ 160kGrade B
x402✓SAFE

browser-use/browser-use

Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code…

★ 119kGrade B
remote-browser✓SAFE

browser-use/browser-use

Controls an isolated Browser Use Cloud browser from a sandboxed machine with the current Browser Use CLI.

★ 119kGrade B
qa✓SAFE

browser-use/browser-use

QA-test a website or web app and return a 1-5 quality score (5 = flawless, 1 = broken) with evidence. Use when the user wants to test, QA, evaluate, score, or "check how good" a site, page, flow, or app — including a…

★ 119kGrade B
open-source✓SAFE

browser-use/browser-use

Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from…

★ 119kGrade B
browser-use✓SAFE

browser-use/browser-use

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library…

★ 119kGrade B

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/daveebbelaar/bama/badge.svg)](https://modelsatlas.com/skills/daveebbelaar/bama/)

Questions about bama

What does the bama skill do?
BAMA: Build Any Mac App. Agent skills to research, clone, design, build, optimize, and test native macOS apps with Swift and SwiftUI.
Is bama safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can bama access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does bama work with?
Its documentation mentions claude-code and codex. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (e0ceb0698707), read on 2026-10-30. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.