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 instructions/planetscale/cli/agents-mdgit clone --depth 1 https://github.com/planetscale/cliWhat 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 | $0.09971 | $0.09971 |
| Opus 5 | $0.04986 | $0.04986 |
| Sonnet 5 | $0.01994 | $0.01994 |
| Haiku 4.5 | $0.00997 | $0.00997 |
Grade A, and why
cli AGENTS.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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 638 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PlanetScale CLI — agent guide
For any automated agent or script using pscale. Always pass --format json. Substitute placeholders from the user's request or from prior command output (org list, database list, branch list).
If you only have the installed pscale binary and this guide is not already in your context, load it and check auth:
pscale --skill
pscale auth check --format json
Use direct CLI automation for shell commands and scripts. Use the hosted PlanetScale MCP server for MCP clients.
This file documents how to invoke pscale. For database assessment, safety review, and operational workflows, install the PlanetScale skills pack (14-pscale-cli-automation covers CLI automation; 00-safe-orchestrator runs the full review). In application repositories, add a separate project AGENTS.md with org, database, branch, and approval rules (see skill 09-mcp-agent-operating-model in that repo).
Public repository safety
This repository is public. Do not include internal or sensitive information in commits, commit messages, pull request titles, or pull request descriptions. Do not name or link private repositories, internal issues or pull requests, Slack conversations, customer details, credentials, or private infrastructure. Include references only when the referenced resource is public.
Concepts
PlanetScale is a serverless database platform for MySQL (via Vitess) and PostgreSQL. Resources are namespaced: an organization (org) owns databases, and each database contains branches — isolated copies of schema (and, for Postgres, data) that work like git branches. The default branch is typically main (production). Most commands target a database + branch and take --org to say which organization they belong to. Throughout this guide, <org>, <database>, and <branch> are placeholders for those names — pick a branch with "ready": true from branch list.
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.
- yesterday First seen · 638 lines · 9,971 tokens per session scan A 846abe445dec
cli AGENTS.md is an instructions file published in the GitHub repository planetscale/cli (664 stars, last pushed 3d ago), licensed Apache-2.0. It adds 9,971 tokens to every session, about $0.0499 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 instructions, from other repositories
ollama CLAUDE.md
Instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
gorest AGENTS.md
Instructions for pilinux/gorest, covering agents.md, project overview, build and run commands, build and tidy dependencies.
chatgpt-cli CLAUDE.md
Instructions for kardolus/chatgpt-cli, covering chatgpt-cli — release runbook, prerequisites, 1. cut the release, 2. publish the github release + binaries and 3. update the homebrew tap.
pvetui AGENTS.md
Instructions for devnullvoid/pvetui, covering agent instructions, initial setup, development workflow, quick reference and code quality standards.
kessoku AGENTS.md
Instructions for mazrean/kessoku, covering repository guidelines — kessoku, project structure, common commands, build and test.