What is pdd GEMINI.md?

Repository instructions for the PDD command-line tool, which helps users develop with Google’s Gemini or Antigravity command-line agents. They document provider selection, authentication options, setup, and project conventions.

They help agents develop, test, and maintain the Python CLI, choose its Google provider, preserve compatibility, and handle private deployment and credential-related code safely.

They clarify which Google command-line tool and credentials to use, reducing setup mistakes when both tools or several authentication methods are available.

pdd GEMINI.md — Instructions file by promptdriven

Install

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.

agentmods

npx agentmods add instructions/promptdriven/pdd/gemini-md

Clone the repo

git clone --depth 1 https://github.com/promptdriven/pdd

Made for: Gemini CLI.

Per session 314 This file is loaded in full into every session.

When invoked 314 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00314	$0.00314
Opus 5	$0.00157	$0.00157
Sonnet 5	$0.00063	$0.00063
Haiku 4.5	$0.00031	$0.00031

Measured 2d ago against content hash c0d4d8ac4887, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pdd GEMINI.md 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 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.

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.

GEMINI.md · 14 lines

What it actually says

Gemini / Antigravity Notes

This repository contains the public PDD CLI.

Migration note (Issue #1152): PDD now supports Google's new Antigravity CLI (agy) alongside the legacy Gemini CLI (gemini). Both map to the google agentic provider. Selection precedence: PDD_AGENTIC_PROVIDER=antigravity (pin Antigravity) > PDD_GOOGLE_CLI=agy|gemini|auto (binary picker; auto prefers agy when installed and credentialed, but uses legacy gemini when both binaries are installed and the only Google auth signal is ~/.gemini/oauth_creds.json) > auto-detect. Antigravity can authenticate through OAuth, keyring-backed Google subscription sign-in, ANTIGRAVITY_API_KEY/GOOGLE_API_KEY, Vertex AI env auth, or PDD's compatibility bridge from GEMINI_API_KEY; legacy gemini remains the explicit rollback path and uses its own OAuth store or GEMINI_API_KEY/GOOGLE_API_KEY. Google announced consumer-tier Gemini CLI cutoff on 2026-06-18.

PDD CLI Development

This is a Python CLI tool.
Use pip install -e ".[dev]" for local development.
The main entry point is pdd/cli.py.
The CLI uses Click for command-line parsing.
Keep private deployment and credential-backed workflow details out of this repository.

Changes

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 · 14 lines · 314 tokens per session scan A c0d4d8ac4887

Subscribe to this mod's changes

pdd GEMINI.md is an instructions file published in the GitHub repository promptdriven/pdd (861 stars, last pushed 8d ago), licensed MIT. It adds 314 tokens to every session, about $0.0016 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.

ai cli code developer-tools development methodology

dev-challenge copilot-instructions.md

Instructions for micheltlutz/dev-challenge, covering github copilot instructions, which job are you doing?, the spec layer is the source of truth, layout and commands.

micheltlutz/dev-challenge · 690 tokens

dev-challenge CLAUDE.md

Instructions for micheltlutz/dev-challenge, covering claude.md, the one rule to internalise, slash commands, subagents and skills.

micheltlutz/dev-challenge · 543 tokens

mint AGENTS.md

Instructions for 3li7alaki/mint, covering mint: atomic completion ledger contract, one unit, one claim, state and worktrees, attempts and provenance and verification and reviews.

3li7alaki/mint · 1,158 tokens

LineCodePro CLAUDE.md

Claude Code instructions for LangLang03/LineCodePro, covering claude.md, project, module layout, commands and architecture.

LangLang03/LineCodePro · 5,378 tokens

ai-interview-kit AGENTS.md

Instructions for CyannSHI/ai-interview-kit, covering ai外呼 prompt 工程化工具包, 可用技能 and 开场引导.

CyannSHI/ai-interview-kit · 324 tokens

unoplat-code-confluence GEMINI.md

Gemini CLI instructions for unoplat/unoplat-code-confluence, a project described as: Always keep your codebases ready for Agents. Improve any coding workflow by atleast 2x by maintaing a live, pluggable context layer per repo that creates and maintains Agents.md.

unoplat/unoplat-code-confluence · 60 tokens