Agent skill · Audited from source
bama
skill · daveebbelaar/bamaMIT licenceAudited 30 Oct 2026 · source e0ceb0698707
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.
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
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
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 0 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | NA | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
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
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
| Agent | Status | More |
|---|---|---|
| Claude Code | Mentioned in its text, not tested | Skills for Claude Code · About Claude Code |
| Codex | Mentioned in its text, not tested | Skills for Codex · About Codex |
Audit history
Every audit, every source change
- ✓SAFE B 89 / 100
first audit · source
e0ceb0698707
README badge
For maintainers · shows the latest audit
[](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.
Similar skills
All automation skills →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…
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…
browser-use/browser-use
Controls an isolated Browser Use Cloud browser from a sandboxed machine with the current Browser Use CLI.
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…
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…
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…
Add this badge to your README
[](https://modelsatlas.com/skills/daveebbelaar/bama/)
<a href="https://modelsatlas.com/skills/daveebbelaar/bama/"><img src="https://modelsatlas.com/skills/daveebbelaar/bama/badge.svg" alt="ModelsAtlas: SAFE B"></a>
Questions about bama
What does the bama skill do?
Is bama safe to install?
What can bama access on my machine?
Which assistants does bama work with?
How current is this page?
Sources
- github.com/daveebbelaar/bama/tree/main/skills/start/bama — the audited source at commit e0ceb0698707 and every finding aboveObserved · 30 Oct 2026
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.
- What does the bama skill do?
- Is bama safe to install?
- What can bama access on my machine?