What is gatekeeper AGENTS.md?

Repository instructions for Gatekeeper, a system where an AI proposes SQL and a person approves and runs it in Beekeeper Studio, a database desktop application.

Use them when changing the Gatekeeper server, approval interface, shared types, or agent skill, and before running the project’s type and test checks.

They give coding agents the project structure, security guidance, required tools, and checks needed before returning changes.

How Gldywn/gatekeeper configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Gldywn/gatekeeper. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Gldywn/gatekeeper/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Gldywn/gatekeeper

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/gldywn/gatekeeper/agents-md/github.svg)](https://agentmods.dev/instructions/gldywn/gatekeeper/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/gldywn/gatekeeper/agents-md"><img src="https://agentmods.dev/badge/instructions/gldywn/gatekeeper/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/gldywn/gatekeeper/agents-md"><img src="https://agentmods.dev/badge/instructions/gldywn/gatekeeper/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 948 This file is loaded in full into every session.

When invoked 948 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00948	$0.00948
Opus 5.5	$0.00379	$0.00379
Sonnet 5.5	$0.00190	$0.00190
Haiku 4.5	$0.00095	$0.00095

Measured today against content hash a94c9213a943, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gatekeeper 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 today.

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.

AGENTS.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

How any coding agent works in this repository. Build steps, commands and the repo layout are in docs/DEVELOPMENT.md. This file only adds what an agent must know on top of it.

What this is

Gatekeeper lets an AI agent propose SQL that a human approves and runs in Beekeeper Studio. packages/server is the MCP server plus a loopback broker (published to npm). packages/plugin is the Beekeeper Studio plugin: the approval UI and the only component that executes SQL. packages/shared holds the wire types and the design tokens. skills/gatekeeper is the agent skill. landing/ is the marketing site, not the product.

Read before changing:

data flow or behaviour: docs/ARCHITECTURE.md
risk classification, pairing, access modes, data handling: SECURITY.md
any plugin UI: packages/plugin/DESIGN.md. Reuse its tokens and existing components before adding a new treatment.

Toolchain

pnpm only (the version in packageManager), Node >= 22. Never npm, yarn or bun. Dependencies are exact-pinned and quarantined for 7 days (.npmrc, pnpm-workspace.yaml). Ask before adding or bumping one.

Checks before handing work back

pnpm typecheck
pnpm test        # Vitest, no database needed
pnpm lint        # Biome

One package at a time: pnpm --filter @gatekeeper/plugin test or pnpm --filter @gldywn/gatekeeper-mcp-server test (the server keeps its npm name, so @gatekeeper/server matches nothing and exits 0 without running a test).

Seeing a plugin change in Beekeeper Studio

Judge UI work in the real plugin inside Beekeeper Studio, not in a standalone page or a mocked host.

pnpm dev:link builds, then points Beekeeper's plugin slot at this checkout. An installed release is moved aside and pnpm dev:unlink puts it back. pnpm dev:status shows what points where.
pnpm --filter @gatekeeper/plugin dev starts Vite with hot reload inside Beekeeper (pnpm dev also starts the Docker test databases first). Restart Beekeeper once after linking.
Connect Beekeeper to the test databases from pnpm db:up (synthetic data), never to a real database.

Read the full file on GitHub · 81 lines

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.

today Changed · +4 lines · +72 tokens per session a94c9213a943
yesterday Changed · +2 lines · +41 tokens per session 79f55563e09e
23d ago First seen · 75 lines · 835 tokens per session scan A 72b099a18d5e

Subscribe to this mod's changes

gatekeeper AGENTS.md is an instructions file published in the GitHub repository Gldywn/gatekeeper (2 stars, last pushed today), licensed MIT. It adds 948 tokens to every session, about $0.0038 per session on Opus 5.5. 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 2026-09-24.

Databases Guardrails ai-agents beekeeper-studio claude developer-tools

plan-forge caching.instructions.md

Caching patterns for .NET — IDistributedCache, Redis, in-memory, cache-aside, TTL strategies.

srnichols/plan-forge · 733 tokens

plan-forge database.instructions.md

Database patterns for .NET — Dapper/EF Core 10, parameterized queries, migration strategy.

srnichols/plan-forge · 1,890 tokens

plan-forge naming.instructions.md

Azure naming conventions — Microsoft CAF abbreviations, constraints, uniqueness, tagging.

srnichols/plan-forge · 1,453 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,649 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,257 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

gatekeeper: Instructions file for Codex