badlogic/pi-skills is a collection of reusable skills that extend pi-coding-agent and work with several other coding agents. Developers use it to give agents capabilities such as web search, browser automation, Google service access, transcription, VS Code integration, and YouTube transcript retrieval.
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/badlogic/pi-skills/gmclinpx skills add badlogic/pi-skills --skill gmcligit clone --depth 1 https://github.com/badlogic/pi-skillsWrote 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/skills/badlogic/pi-skills/gmcli)<a href="https://agentmods.dev/skills/badlogic/pi-skills/gmcli"><img src="https://agentmods.dev/badge/skills/badlogic/pi-skills/gmcli.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 5.1 | $0.00025 | $0.00474 |
| Opus 5 | $0.00013 | $0.00237 |
| Sonnet 5 | $0.00005 | $0.00095 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
gmcli 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 6d 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.
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
Gmail CLI
Command-line interface for Gmail operations.
Installation
npm install -g @mariozechner/gmcli
Setup
Google Cloud Console (one-time)
- Create a new project (or select existing)
- Enable the Gmail API
- Set app name in OAuth branding
- Add test users (all Gmail addresses you want to use)
- Create OAuth client:
- Click "Create Client"
- Application type: "Desktop app"
- Download the JSON file
Configure gmcli
First check if already configured:
gmcli accounts list
If no accounts, guide the user through setup:
- Ask if they have a Google Cloud project with Gmail API enabled
- If not, walk them through the Google Cloud Console steps above
- Have them download the OAuth credentials JSON
- Run:
gmcli accounts credentials ~/path/to/credentials.json - Run:
gmcli accounts add <email>(use--manualfor browserless OAuth)
Usage
Run gmcli --help for full command reference.
Common operations:
gmcli <email> search "<query>"- Search emails using Gmail query syntaxgmcli <email> thread <threadId>- Read a thread with all messagesgmcli <email> send --to <emails> --subject <s> --body <b>- Send emailgmcli <email> labels list- List all labelsgmcli <email> drafts list- List drafts
Data Storage
~/.gmcli/credentials.json- OAuth client credentials~/.gmcli/accounts.json- Account tokens~/.gmcli/attachments/- Downloaded attachments
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.
- 6d ago First seen · 59 lines · 25 tokens per session scan A 5985513a2f07
gmcli is a skill published in the GitHub repository badlogic/pi-skills (2,486 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 474 once invoked, about $0.0001 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 skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.