prb-effect: Instructions file for Codex

AGENTS.md

prb-effect AGENTS.md is an instructions file for Codex, OpenCode from PaulRBerg/prb-effect. It costs 1,519 tokens per session, scanned A, original, MIT.

Development instructions for prb-effect, a TypeScript library built with Effect-TS and managed in a multi-package repository, also called a monorepo.

In plain words
What is it for?
Use them when setting up the repository, changing packages, running Biome or TypeScript checks, and testing affected code.
Why use it?
They define the project’s required tools and checks, reducing inconsistent code and catching type, formatting, lint, or related-test failures.

Instructions file for CodexOpenCode

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

This is PaulRBerg/prb-effect's own configuration. It tells Codex and OpenCode how to work on prb-effect 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 prb-effect configures →

Reuse

Borrowing it

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

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 prb-effect AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/paulrberg/prb-effect/agents-md"><img src="https://agentmods.dev/badge/instructions/paulrberg/prb-effect/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,519 This file is loaded in full into every session.
When invoked 1,519 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 $0.01519 $0.01519
Opus 5.5 $0.00608 $0.00608
Sonnet 5.5 $0.00304 $0.00304
Haiku 4.5 $0.00152 $0.00152

Measured 9d ago against content hash d549f805419e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

prb-effect 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 9d 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 · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

prb-effect Development Guidelines

Bun workspace of Effect 4 libraries published to npm as @prb/effect-*: evm (viem), evm-safe (Safe Apps; depends on evm), next (Next.js), solana, and xstate (xState v5). Declare shared dependency versions in the root package.json workspace catalogs and reference them with catalog: specifiers.

Prerequisites and Setup

Install Node.js v24.15+ or v26+, Bun, Just, and Ni (na, ni, nr), then run bun install at the repository root.

Commands

Root recipes:

just type-check <package>  # tsgo --noEmit in one package directory; no argument checks all packages
just tu [files]            # Unit tests across all packages (excludes *.test.integration.ts)
just ti [files]            # Integration tests, with .env decrypted by dotenvx
just full-check            # Biome, Prettier, and type checks
just full-write            # Biome and Prettier fixes
just build <package>       # Build one package; `just build-all` builds every package

Package recipes come from recipes.just. Run them inside a package directory or as just <module>::<recipe> from the root; the evm-safe module is named evm_safe (for example, just evm_safe::test-unit). In a package, just test runs unit and integration tests; use just test-unit for unit tests only.

Lint Rules

After generating code, run these commands in order. If any command fails, fix errors before continuing.

  1. Biome lint — if JS/TS/JSON files changed: na biome lint <files>
  2. TypeScript check — if TS files changed: just type-check <package> for one package, just type-check-all for changes across packages
  3. Related tests — if test files or test-related files changed: na vitest run <test-files>; do not run the entire suite

The pre-commit hook runs lint-staged, which formats staged files with Biome (JS/TS/JSON) and Prettier (MD/YAML).

Read the full file on GitHub · 110 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. 9d ago Changed · +3 lines · +42 tokens per session d549f805419e
  2. 1mo ago Changed · +12 lines · +232 tokens per session 9b5cd0843733
  3. 1mo ago Changed · +3 tokens per session a4bf4d595af9
  4. 1mo ago Changed · -66 lines · -274 tokens per session aafadf12c8fc
  5. 2mo ago First seen · 161 lines · 1,516 tokens per session scan A 9842c79c5c48

Subscribe to this mod's changes

prb-effect AGENTS.md is an instructions file published in the GitHub repository PaulRBerg/prb-effect (22 stars, last pushed 4d ago), licensed MIT. It adds 1,519 tokens to every session, about $0.0061 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

prb-effect AGENTS.md compared with instructions from other repositories

prb-effect AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
prb-effect AGENTS.mdPaulRBerg/prb-effectInstructions file224d agoMITA1,519Codex, 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