agent-cms: Instructions file for Codex

AGENTS.md

agent-cms AGENTS.md is an instructions file for Codex, OpenCode from jokull/agent-cms. It costs 717 tokens per session, scanned A, original, MIT.

Project instructions for agent-cms, a content-management system whose code includes an MCP server, GraphQL read access, REST routes, database services, search, and content validation.

In plain words
What is it for?
Orienting work on the CMS's tool server, APIs, database layer, search, schema generation, content fields, and tests.
Why use it?
They give coding agents the repository structure, architecture rules, conventions, and testing guidance needed to change the system safely.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is jokull/agent-cms's own configuration. It tells Codex and OpenCode how to work on agent-cms itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-cms configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jokull/agent-cms. 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/jokull/agent-cms/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/jokull/agent-cms

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.

agentmods badge for agent-cms AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jokull/agent-cms/agents-md/github.svg)](https://agentmods.dev/instructions/jokull/agent-cms/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jokull/agent-cms/agents-md"><img src="https://agentmods.dev/badge/instructions/jokull/agent-cms/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.

agentmods 80×15 button for agent-cms AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jokull/agent-cms/agents-md"><img src="https://agentmods.dev/badge/instructions/jokull/agent-cms/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 717 This file is loaded in full into every session.
When invoked 717 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00717 $0.00717
Opus 5.5 $0.00287 $0.00287
Sonnet 5.5 $0.00143 $0.00143
Haiku 4.5 $0.00072 $0.00072

Measured 2mo ago against content hash af1ac86a51e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-cms 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 2mo 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.

AGENTS.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — agent-cms

For agents working on this codebase (not consuming the CMS).

Project structure

  • src/mcp/ — MCP server: tools, resources, prompts
  • src/graphql/ — GraphQL schema builder and resolvers (read-only content delivery)
  • src/services/ — business logic (model, field, record, publish, asset, webhook, schema-io)
  • src/db/ — row types, validator accessors
  • src/field-types.ts — field type registry with validation schemas
  • src/dast/ — DAST (structured text) validation and traversal
  • src/search/ — FTS5 + Vectorize search
  • src/schema-engine/ — DDL generation for content tables
  • src/http/ — REST API routes
  • src/index.ts — Cloudflare Worker entry point, layer composition

Architecture

Effect services with SqlClient dependency injection. Layers composed at the entry point:

  • D1Client.layer → SqlClient.SqlClient
  • VectorizeContext → optional AI/Vectorize bindings
  • Layer.merge(sqlLayer, vectorizeLayer) → provided once at handler boundary
  • Effect.runPromise only at framework boundaries (MCP, GraphQL Yoga, HTTP handler)

See docs/contributing/effect.md for full patterns.

Conventions

  • No as casts — use Effect Schema or runtime checks
  • No any — use row types from src/db/row-types.ts or unknown
  • Errors are Data.TaggedError in src/errors.ts
  • Field api_keys are snake_case; GraphQL maps to camelCase/PascalCase at the resolver layer

Testing

npx vitest run           # all tests
npx vitest run test/mcp  # scoped to MCP tests

Test helpers in test/app-helpers.ts — creates in-memory D1, runs migrations, provides run() for Effect.

How to add things

New field type: Add to src/field-types.ts registry (column type, default, validation schema). Update src/graphql/schema-builder.ts for GraphQL type mapping.

New MCP tool: Add server.tool(name, description, zodSchema, async (args) => run(Service.method(args))) in src/mcp/server.ts. Keep tools thin — logic goes in services.

Read the full file on GitHub · 68 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.

  1. 2mo ago First seen · 68 lines · 717 tokens per session scan A af1ac86a51e6

Subscribe to this mod's changes

agent-cms AGENTS.md is an instructions file published in the GitHub repository jokull/agent-cms (5 stars, last pushed 2mo ago), licensed MIT. It adds 717 tokens to every session, about $0.0029 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 2026-08-31.

Related

agent-cms AGENTS.md compared with instructions from other repositories

agent-cms AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agent-cms AGENTS.mdjokull/agent-cmsInstructions file52mo agoMITA717Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode