critique: Instructions file for Codex

AGENTS.md

critique AGENTS.md is an instructions file for Codex, OpenCode from remorses/critique. It costs 2,057 tokens per session, scanned A, original, MIT.

Instructions for developing an interactive terminal interface, or TUI, built with the OpenTUI framework and React. They cover unreleased package versions, Bun commands, and safe ways to run the project.

In plain words
What is it for?
Use them when updating OpenTUI preview dependencies, reading its current documentation, building the terminal interface, or running non-interactive commands.
Why use it?
They prevent version references from pointing to the wrong code and warn against commands that would start an interactive process and hang the session.

Instructions file for CodexOpenCode

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

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

About the project

Critique is a tool for viewing and reviewing Git changes in a terminal, web preview, or coding-agent workflow. It is for developers and agents that need to inspect diffs, commits, branches, and related call-stack information.

remorses/critique · 1,285 stars · on GitHub · critique.work

Reuse

Borrowing it

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

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 critique AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/remorses/critique/agents-md"><img src="https://agentmods.dev/badge/instructions/remorses/critique/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,057 This file is loaded in full into every session.
When invoked 2,057 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.02057 $0.02057
Opus 5.5 $0.00823 $0.00823
Sonnet 5.5 $0.00411 $0.00411
Haiku 4.5 $0.00206 $0.00206

Measured 3d ago against content hash 3d7e3a1b661f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

critique AGENTS.md scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

IMPORTANT! before starting every task ALWAYS read opentui docs with `curl -s https://raw.githubusercontent.com/sst/opentui/refs/heads/main/packages/react/README.md`
AGENTS.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

opentui

opentui is the framework used to render the tui, using react.

IMPORTANT! before starting every task ALWAYS read opentui docs with curl -s https://raw.githubusercontent.com/sst/opentui/refs/heads/main/packages/react/README.md

ALWAYS!

using unreleased opentui versions

to use a pkg.pr.new preview URL for opentui, get the last commit hash (40 chars always) from PR https://github.com/anomalyco/opentui/pull/536:

gh pr view 536 -R anomalyco/opentui --json commits --jq '.commits[-1].oid[:40]'

then use it in package.json:

https://pkg.pr.new/anomalyco/opentui/@opentuah/core@<hash>
https://pkg.pr.new/anomalyco/opentui/@opentuah/react@<hash>

YOU MUST ALWAYS use the commit hash 40 characters long when changing the pkg.pr.new url! not the pr number!

if the commit hash url does not work it means it is still building. ignore the pkg.pr.new comment with the pr number in the install script. you MUST use the url with the commit hash.

bun

NEVER run the interactive TUI (e.g. bun run src/cli.tsx without arguments). It will hang. Instead ask the user to run it.

The web command is safe to run - it generates HTML and exits:

bun run src/cli.tsx web

NEVER use tsc --noEmit in this repo. Always run emitting builds so cli/dist stays updated.

after every code change, run bun run build from cli/ to make sure it compiles. fix any type errors before moving on.

NEVER use require. just import at the top of the file with esm

use bun add to install packages instead of npm

React

NEVER pass function or callbacks as dependencies of useEffect, this will very easily cause infinite loops if you forget to use useCallback

NEVER use useCallback. it is useless if we never pass functions in useEffect dependencies

Try to never use useEffect if possible. usually you can move logic directly in event handlers instead

Rules

  • if you need Node.js apis import the namesapce and not the named exports: import fs from 'fs' and not import { writeFileSync } from 'fs'
  • DO NOT use as any. instead try to understand how to fix the types in other ways
  • to implement compound components like List.Item first define the type of List, using a interface, then use : to implement it and add compound components later using . and omitting the props types given they are already typed by the interface, here is an example
  • DO NOT use console.log. only use logger.log instead
  • uses onInput not onChange. it is passed a simple string value and not an event object
  • to render examples components use renderWithProviders not render
  • ALWAYS bind all class methods to this in the constructor. This ensures methods work correctly when called in any context (callbacks, event handlers, etc). Example:

Read the full file on GitHub · 166 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. 3d ago Changed · +8 lines · +229 tokens per session 3d7e3a1b661f
  2. 1mo ago Changed · -14 lines · -146 tokens per session 012cc510beb7
  3. 2mo ago First seen · 172 lines · 1,974 tokens per session scan A 3f691c9fe37e

Subscribe to this mod's changes

critique AGENTS.md is an instructions file published in the GitHub repository remorses/critique (1,285 stars, last pushed 4d ago), licensed MIT. It adds 2,057 tokens to every session, about $0.0082 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

critique AGENTS.md compared with instructions from other repositories

critique AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
critique AGENTS.mdremorses/critiqueInstructions file1.3k4d agoMITA2,057Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, 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