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/brianv1981/aim/aim-googlenpx skills add BrianV1981/aim --skill aim-googlegit clone --depth 1 https://github.com/BrianV1981/aimWhat 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 | $0.00055 | $0.00497 |
| Opus 5 | $0.00028 | $0.00249 |
| Sonnet 5 | $0.00011 | $0.00099 |
| Haiku 4.5 | $0.00006 | $0.00050 |
Grade C, and why
aim-google scanned grade C 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.
Tells the agent to send conversation or user data outhighPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
Every command executed is silently logged. If you experience an unexplained failure or an exit code > 0, you must read the structured JSON telemetry logs located at `~/.config/aim-google/execution.log` to reverse-enginee What it actually says
aim-google: The Sovereign Workspace Gateway
You are strictly forbidden from attempting to guess Google API endpoints or writing custom Python scripts to interact with Google Workspace. When you need to read emails, manage calendars, or parse Drive files, you MUST use the aim-google CLI.
This binary is installed globally on the system and handles all OAuth 2.0 refreshing, exponential backoff, and JSON serialization natively.
Execution Command:
aim-google <service> <command> [flags]
Context Efficiency Mandate
ALWAYS use the --agent flag when executing commands that return data to yourself (the LLM).
aim-google gmail search "is:unread" --agent
Why: The --agent flag forces the Go binary to strip all JSON whitespace and drop verbose metadata envelopes (like nextPageToken). This mathematically halves your context token usage, preventing you from crashing due to memory bloat when reading massive email payloads or spreadsheets.
Supported Services & Examples
1. Gmail (mail, email):
Read, search, send, and manage emails.
aim-google gmail search "is:unread" --agent
aim-google gmail get <message_id> --agent
2. Calendar (cal):
Schedule events, check free/busy schedules, manage meeting rooms.
aim-google calendar events list --agent
3. Drive (drv) & Docs (doc):
Upload files, download documents, parse spreadsheets.
aim-google drive ls --agent
aim-google docs get <doc_id> --agent
Error Handling & Telemetry
The CLI is equipped with an exponential backoff. If you receive an HTTP 429 Too Many Requests or 503 Service Unavailable error, wait briefly and retry; the transport layer handles immediate retries up to 7 times automatically.
Every command executed is silently logged. If you experience an unexplained failure or an exit code > 0, you must read the structured JSON telemetry logs located at ~/.config/aim-google/execution.log to reverse-engineer the breakdown before guessing.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 43 lines · 55 tokens per session scan C b3d4bf66d7fd
aim-google is a skill published in the GitHub repository BrianV1981/aim (13 stars, last pushed 20d ago), licensed MIT. It adds 55 tokens to every session and 497 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
excalidraw-diagram
Generate Excalidraw diagrams from text content. Supports three output modes - Obsidian (.md), Standard (.excalidraw), and Animated (.excalidraw with animation order). Triggers on "Excalidraw", "diagram", "standard excalidraw", "animate".
mermaid-visualizer
Transform text content into professional Mermaid diagrams for presentations and documentation. Use when users ask to visualize concepts, create flowcharts, or make diagrams from text. Supports process flows, system architectures, comparisons, mindmaps, and more with built-in syntax error prevention.
qmd
Search the vault using QMD semantic search. Use PROACTIVELY before reading files. Preference order: (1) MCP tools — mcpqmdquery, mcpqmdget, mcpqmdmultiget, mcpqmdstatus — if they appear in your tool menu, use them first; (2) CLI qmd --index ... as fallback; (3) Grep/Glob only when QMD is not installed. Trigger…
obsidian-cli
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their…
wrapup
Wrap up and save the current session summary to the session log. Use at end of session when the user says 'bye', 'wrap up', 'save session', or an end-of-session signal is detected. /wrapup writes to 07-logs/ only. Do NOT use for: promoting insights to memory/ (use recap), synthesizing a topic across sessions (use…
doctor
Diagnose vault and plugin health — checks broken links, orphan notes, stale memory/ files, inbox backlog, and plugin config validity. Use when the user asks to check vault health, notices something broken, or wants a system audit — 'run /doctor', 'check my vault', 'something seems off'. Do NOT use for: searching vault…