ctxd AGENTS.md

Project instructions that record user preferences and workspace facts for an AI coding agent. They describe how the ctxd project provides curated Metabase database context to AI tools.

In plain words
What is it for?
Guiding work on ctxd, including Metabase setup, database-context refreshes, authentication, query permissions, and deployment details.
Why use it?
They give the agent consistent project knowledge, so it does not repeatedly ask the same questions or make decisions that conflict with the team's setup.

Instructions file for CodexOpenCode

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/thisis-gp/ctxd/agents-md
Clone the repo
git clone --depth 1 https://github.com/thisis-gp/ctxd

Made for: Codex, OpenCode.

Per session 239 This file is loaded in full into every session.
When invoked 239 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.

ModelPer sessionOnce invoked
Fable 5 $0.00239 $0.00239
Opus 5 $0.00120 $0.00120
Sonnet 5 $0.00048 $0.00048
Haiku 4.5 $0.00024 $0.00024

Measured yesterday against content hash de466a84c2ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ctxd 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.

AGENTS.md · 15 lines

What it actually says

Learned User Preferences

  • Prefer simple plug-and-play org rollout: end users should not configure Metabase credentials; tech configures Metabase once on the server.
  • Default product mode is context-only: LLM builds/validates SQL via ctxd; users run queries in Metabase. Query execution is opt-in via CTXD_ALLOW_QUERY.
  • Hosted auth uses per-user connector tokens issued from an admin dashboard (not one shared org token).

Learned Workspace Facts

  • The project is being named ctxd (context daemon).
  • Ctxd reduces token use and schema-query hallucinations by serving curated, versioned Metabase context to AI agents through MCP.
  • The intended operational model is that a technical team ingests schema context while other users connect through MCP; SQL is drafted for Metabase rather than executed by default.
  • Preferred hosted ingest is ctxd refresh on a nightly cron on the same host/volume as the MCP server (GitHub Action artifacts alone do not update live Docker data).
  • HTTPS is terminated by Caddy in front of ctxd serve --http.
  • BRD.md is internal planning and is gitignored for the public repo.
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.

  1. yesterday First seen · 15 lines · 239 tokens per session scan A de466a84c2ba

Subscribe to this mod's changes

ctxd AGENTS.md is an instructions file published in the GitHub repository thisis-gp/ctxd (1 stars, last pushed 29d ago), licensed MIT. It adds 239 tokens to every session, about $0.0012 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 2026-08-31.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 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 · 6,785 tokens

next.js 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 · 7,296 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens