What is codex-toolloop AGENTS.md?

Project instructions for codex-toolloop, a Node.js and TypeScript workspace containing coding-agent runtimes, backends, workflows, and tool-policy components.

Use them when modifying this monorepo, a repository containing multiple related packages, especially when changing Codex app-server or SDK integration code.

They tell an agent how the repository is organized, how to set it up, and which build, type-check, test, and schema-update commands are required.

How BjornMelin/codex-toolloop configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to BjornMelin/codex-toolloop. 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/BjornMelin/codex-toolloop/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/BjornMelin/codex-toolloop

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/bjornmelin/codex-toolloop/agents-md/github.svg)](https://agentmods.dev/instructions/bjornmelin/codex-toolloop/agents-md)

Your own site

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

Per session 1,422 This file is loaded in full into every session.

When invoked 1,422 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	$0.01422	$0.01422
Opus 5.5	$0.00569	$0.00569
Sonnet 5.5	$0.00284	$0.00284
Haiku 4.5	$0.00142	$0.00142

Measured 2mo ago against content hash 25d56d43fde8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codex-toolloop 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 · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Setup

Node.js 24+ (.nvmrc), pnpm (Corepack: corepack enable).
Copy .env.example to .env; never commit real keys.

Project Layout

apps/cli/: CLI entrypoint (apps/cli/src/index.ts).
packages/: workspace packages
- packages/codex-toolloop/: core runtime scaffold
- packages/codex/: Codex backends (app-server / exec / sdk)
- packages/mcp/: MCP tool substrate + policy
- packages/workflows/: workflow + routing utilities
- packages/testkit/: fixtures/mocks/temp dirs
src/: root exports + prototype workflows
tests/unit/: Vitest runtime tests; tests/type/: *.test-d.ts
docs/: PRD, ADRs (docs/adr/), specs (docs/specs/)
examples/: runnable scripts (pnpm examples:*)

Commands

pnpm install
pnpm dev:cli -- doctor
pnpm build
pnpm fix:typecheck  # required before finishing work
pnpm test
pnpm test:watch
pnpm examples:basic

Codex app-server schema upgrades

If pinned @openai/codex version changes, run pnpm codex:gen and update integration code for protocol deltas.
Guide: docs/codex-app-server-protocol.md (ADR 0013/0014, SPEC 023/024-029).
When Codex SDK is involved, use the $codex-sdk skill guide.

Turborepo (Vercel)

Use turbo run build on Vercel (filters inferred by root).
In turbo.json, define tasks.build.outputs for each framework output dir.
- Next.js: [".next/**", "!.next/cache/**"]
Never include .next/cache/** in outputs.
Declare task env + globalEnv to avoid stale cache hits.
Validate remote caching locally: turbo run build, then inspect node_modules/.cache/turbo.

Style

TypeScript ESM (NodeNext), strict, noUncheckedIndexedAccess, exactOptionalPropertyTypes.
Biome (biome.json): 2-space indent, 80-col.
Exported schemas use ...Schema; keep exports small and explicit.

Development Standards

Required before you finish:

pnpm -s fix:typecheck (runs pnpm -s fix, pnpm -s typecheck, pnpm -s test). Keep its changes.

Read the full file on GitHub · 114 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.

2mo ago First seen · 114 lines · 1,422 tokens per session scan A 25d56d43fde8

Subscribe to this mod's changes

codex-toolloop AGENTS.md is an instructions file published in the GitHub repository BjornMelin/codex-toolloop (1 stars, last pushed 8mo ago), licensed MIT. It adds 1,422 tokens to every session, about $0.0057 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.

ai-agents automation biome codex codex-cli codex-sdk

codex-toolloop AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
codex-toolloop AGENTS.mdBjornMelin/codex-toolloop	Instructions file	1	8mo ago	MIT	A	1,422	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

codex-toolloop: Instructions file for Codex