OJ: Instructions file for Codex

AGENTS.md

OJ AGENTS.md is an instructions file for Codex, OpenCode from WajoAI/OJ. It costs 679 tokens per session, scanned A, original, MIT.

A set of instructions for agents working on OJ, a TypeScript repository intended for agent-assisted development. It defines verification requirements, dependency rules, pull-request guidance, and TypeScript coding practices.

In plain words
What is it for?
Use it when changing OJ, especially when adding dependencies, writing TypeScript, or preparing work for review.
Why use it?
It helps agents make small, consistent changes and complete the repository's required checks before handoff.

Instructions file for CodexOpenCode

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

This is WajoAI/OJ's own configuration. It tells Codex and OpenCode how to work on OJ 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 OJ configures →

View source ↗ WajoAI/OJ
Reuse

Borrowing it

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

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 OJ AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/wajoai/oj/agents-md"><img src="https://agentmods.dev/badge/instructions/wajoai/oj/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 679 This file is loaded in full into every session.
When invoked 679 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 $0.00679 $0.00679
Opus 5.5 $0.00272 $0.00272
Sonnet 5.5 $0.00136 $0.00136
Haiku 4.5 $0.00068 $0.00068

Measured 2mo ago against content hash a2f3aaa72a81, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

OJ 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 · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

This repository is built for agentic TypeScript work. Keep changes small, verify them, and leave the repo easier to inspect than you found it.

The goal is idiomatic TypeScript with excellent feedback, not Rust-style TypeScript. Prefer TypeScript platform conventions, clear domain types, and verification that gives agents precise errors.

Required Before Handoff

Run:

npm run verify

If that is too slow while iterating, run the narrowest failing check first, then finish with npm run verify.

Dependency Rules

  • Prefer the platform, TypeScript, and existing dependencies before adding packages.
  • New packages must install through npm with the checked-in .npmrc policy.
  • Do not bypass min-release-age, save-exact, or ignore-scripts without documenting the reason in the PR.
  • Commit package-lock.json after dependency changes.

TypeScript Rules

  • Treat any, unchecked indexing, and broad object shapes as design smells.
  • Prefer discriminated unions for state machines and command results.
  • Use assertNever for unreachable union states and assertPresent instead of non-null assertions.
  • Make union handling exhaustive; do not rely on default switch branches to hide missing cases.
  • Avoid truthy checks for strings, numbers, and nullable values; narrow explicitly.
  • Do not use @ts-ignore, @ts-nocheck, as any, or non-null assertions. If a suppression is unavoidable, explain why and keep it local.
  • Use unknown at boundaries, validate it, then narrow it.
  • Add expect-type assertions when a public API shape matters.
  • Keep runtime validation close to external input boundaries.
  • Keep files concise. The default limit is 500 LOC per file, 30 LOC per function (60 in test files), or 20 KB; split files by purpose instead of raising .repo-health.json.
  • Never loosen .repo-health.json to silence findings — that is flagged as diff.contractLoosened. If a finding is genuinely unfixable right now, add a scoped entry to exceptions with a rule, path, justification (20+ characters), a pr referencing the pull request that de-risks the debt, and an expires date. No PR, no exception: the exception is invalid until the de-risking PR reference is present.
  • Do not copy-paste near-identical functions (same file or across files), duplicate type declarations, repeat magic literals, or dodge size limits with names like index2.ts, order-utils.ts, or doWorkPart2; verification flags all of these.
  • Do not give exported functions positional boolean flags or inline options objects with more than 8 properties; use named domain types or split the function.
  • When verification reports core.module.rewriteRecommended, rewrite the module instead of patching individual findings; follow the repair plan at the top of the output and fix structure first, then types, then effects, then tests.
  • During long repair loops, save a --format json result and pass it back with --baseline so you can see resolved versus newly introduced findings.

Read the full file on GitHub · 49 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 · 49 lines · 679 tokens per session scan A a2f3aaa72a81

Subscribe to this mod's changes

OJ AGENTS.md is an instructions file published in the GitHub repository WajoAI/OJ (12 stars, last pushed 3mo ago), licensed MIT. It adds 679 tokens to every session, about $0.0027 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 2026-08-30.

Related

OJ AGENTS.md compared with instructions from other repositories

OJ AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
OJ AGENTS.mdWajoAI/OJInstructions file123mo agoMITA679Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA1,907GitHub Copilot