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 skills/mnott/whazaa/setupnpx skills add mnott/Whazaa --skill setupgit clone --depth 1 https://github.com/mnott/WhazaaWhat 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 | $0.00109 | $0.02773 |
| Opus 5 | $0.00055 | $0.01386 |
| Sonnet 5 | $0.00022 | $0.00555 |
| Haiku 4.5 | $0.00011 | $0.00277 |
Grade B, and why
setup scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Also ensure `~/.claude/settings.json` has `"mcp__aibroker"` in the `permissions.allow` How it starts
The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Whazaa Setup Skill
Complete autonomous setup of Whazaa from a local clone. Ask the user for input only when a QR code scan is required.
Context
Whazaa is the WhatsApp transport adapter for AIBroker — it is not an MCP server itself. Two pieces are involved:
- AIBroker MCP server (
npx -y -p aibroker aibroker-mcp) — started by Claude Code. Provides thewhatsapp_*tools (plustelegram_*,pailot_*,aibroker_*). It reaches Whazaa's watcher over a Unix Domain Socket. - Whazaa watcher daemon (
dist/index.js watch) — a long-running background process that owns the WhatsApp (Baileys) connection and delivers incoming messages to iTerm2 via AppleScript. Managed by macOS launchd ascom.whazaa.watcher.
Running dist/index.js with no subcommand prints usage and exits — it is a CLI, not a
stdio MCP server. Never register whazaa under mcpServers.
The repo path is needed throughout. Determine it before starting:
REPO="$(pwd)" # if already in the repo
# or use the path the user provided
Step 0: Clone (if applicable)
If the user does NOT already have a local clone, clone first:
git clone https://github.com/mnott/Whazaa.git ~/dev/ai/Whazaa
REPO="$HOME/dev/ai/Whazaa"
Use the user's preferred path if specified, otherwise default to ~/dev/ai/Whazaa.
If already in the repo directory, skip this step and set REPO="$(pwd)".
Step 1: Check Prerequisites
Run these checks. Report failures but continue to gather all issues before stopping.
# Node.js version (must be >= 18)
node --version
# macOS check (watcher requires macOS + iTerm2 + AppleScript)
sw_vers -productVersion
# iTerm2 installed
ls /Applications/iTerm.app 2>/dev/null && echo "iTerm2: OK" || echo "iTerm2: NOT FOUND — install from https://iterm2.com"
# ffmpeg (required for TTS voice notes — WAV to OGG conversion)
which ffmpeg && echo "ffmpeg: OK" || echo "ffmpeg: NOT FOUND — install with: brew install ffmpeg"
# whisper (optional — only needed to receive voice notes from phone)
which whisper 2>/dev/null && echo "whisper: OK" || echo "whisper: optional — install with: pip install openai-whisper"
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.
- 2d ago First seen · 333 lines · 109 tokens per session scan B c3528612af71
setup is a skill published in the GitHub repository mnott/Whazaa (5 stars, last pushed 26d ago), licensed MIT. It adds 109 tokens to every session and 2,773 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.