agentmods.dev

Remarc: Instructions file for Codex

AGENTS.md

Remarc AGENTS.md is an instructions file for Codex, OpenCode from metedata/Remarc. It costs 1,160 tokens per session, scanned C, original, MIT.

A development guide for Remarc, a macOS menu-bar app built with SwiftUI and AppKit that lets users comment on selected text.

In plain words
What is it for?
Use it when changing the app, especially its interface, then building, relaunching, debugging, or locating stored comments.
Why use it?
It records the app's build settings, data locations, logging behavior, and relaunch requirements so changes can be built and checked consistently.

Instructions file for CodexOpenCode

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

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

not rated 83repo 1mo ago C scan 1,160 tokens original MIT
View source ↗ metedata/Remarc remarc.app
Reuse

Borrowing it

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

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 Remarc AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/metedata/remarc/agents-md"><img src="https://agentmods.dev/badge/instructions/metedata/remarc/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,160 This file is loaded in full into every session.
When invoked 1,160 The same file — it is already loaded in full.
Security scan C 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 $0.01160 $0.01160
Opus 5.5 $0.00464 $0.00464
Sonnet 5.5 $0.00232 $0.00232
Haiku 4.5 $0.00116 $0.00116

Measured 2mo ago against content hash 99f862718643, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

Remarc AGENTS.md scanned grade C 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 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf app/DerivedData
AGENTS.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Remarc

macOS menu bar app (SwiftUI + AppKit) for contextual commenting on text selections.

  • Bundle ID: com.metepolat.Remarc
  • Min macOS: 14.0 (MACOSX_DEPLOYMENT_TARGET in app/Config/Shared.xcconfig is the source of truth), Swift 6.0+, LSUIElement (no dock icon)
  • Build: cd app && xcodebuild build -workspace Remarc.xcworkspace -scheme Remarc -configuration Debug -derivedDataPath "$(pwd)/DerivedData"
  • Debug log: /tmp/remarc_debug.log (Debug builds only; release builds write no log file unless defaults write com.metepolat.Remarc debugFileLoggingEnabled -bool YES)
  • Data: ~/Library/Application Support/Remarc/comments.json (legacy fallback: data.json)

MANDATORY: After every successful build, you MUST relaunch Remarc. The user cannot verify changes otherwise. Do this every single time, no exceptions:

  1. Build with -derivedDataPath "$(pwd)/DerivedData" (deterministic output path — no grep/find needed)
  2. Relaunch: pkill -x Remarc; sleep 0.5; open app/DerivedData/Build/Products/Debug/Remarc.app

Build

When working on UI changes in SwiftUI, always do a clean build after layout changes to avoid stale build cache issues. Use xcodebuild clean or delete DerivedData when builds behave unexpectedly.

Worktree Builds

When building from worktrees, always verify the correct DerivedData path and binary location before launching. Use absolute paths instead of $PWD in build commands.

UI Work

When the user describes a UI bug, confirm WHICH specific component/view they mean before editing. Ask clarifying questions if the target is ambiguous (e.g., 'comment cards' vs 'session chips').

Development

Contribution Attribution

Use Mete Polat <[email protected]> as the author of repository and automated release commits and as the tagger of annotated tags. Automated commits must use the same identity as committer. Do not add Co-authored-by or equivalent attribution for bots, models, agents, or anyone else. Attribute another contributor only when Mete explicitly requests it.

Read the full file on GitHub · 76 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 · 76 lines · 1,160 tokens per session scan C 99f862718643

Subscribe to this mod's changes

Remarc AGENTS.md is an instructions file published in the GitHub repository metedata/Remarc (83 stars, last pushed 1mo ago), licensed MIT. It adds 1,160 tokens to every session, about $0.0046 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

ai-agentsdeveloper-toolsmacosmodel-context-protocolscreen-annotationswift
Related

Remarc AGENTS.md compared with instructions from other repositories

Remarc AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Remarc AGENTS.mdmetedata/RemarcInstructions file831mo agoMITC1,160Codex, 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