agentmods.dev

agent-frow: Instructions file for Codex

AGENTS.md

agent-frow AGENTS.md is an instructions file for Codex, OpenCode from timeToy34/agent-frow. It costs 271 tokens per session, scanned A, original, MIT.

Repository instructions for building and testing a Windows application from a WSL source checkout. They define which folder is the source, how Windows Cargo builds the app, and where packages and installed copies belong.

In plain words
What is it for?
They are for guiding local build, test, installation, packaging, and release-file handling for the application.
Why use it?
They prevent builds from using the wrong checkout or toolchain and help keep local output separate from source code.

Instructions file for CodexOpenCode

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

This is timeToy34/agent-frow's own configuration. It tells Codex and OpenCode how to work on agent-frow 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 agent-frow configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/jerome/dev/ai-agent-keeb.

not rated 6repo 11d ago A scan 271 tokens original MIT
View source ↗ timeToy34/agent-frow
Reuse

Borrowing it

Nothing to install: this file belongs to timeToy34/agent-frow. 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/timeToy34/agent-frow/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/timeToy34/agent-frow

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 agent-frow AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/timetoy34/agent-frow/agents-md/github.svg)](https://agentmods.dev/instructions/timetoy34/agent-frow/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/timetoy34/agent-frow/agents-md"><img src="https://agentmods.dev/badge/instructions/timetoy34/agent-frow/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 agent-frow AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/timetoy34/agent-frow/agents-md"><img src="https://agentmods.dev/badge/instructions/timetoy34/agent-frow/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 271 This file is loaded in full into every session.
When invoked 271 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 $0.00271 $0.00271
Opus 5.5 $0.00108 $0.00108
Sonnet 5.5 $0.00054 $0.00054
Haiku 4.5 $0.00027 $0.00027

Measured 1mo ago against content hash 030c38b9294f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-frow 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 1mo 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 · 18 lines

What it actually says

Local development workflow

  • Keep the WSL checkout at /home/jerome/dev/ai-agent-keeb as the source of truth. C:\dev\ai-agent-keeb is an output folder, not another source checkout.
  • Build the app with Windows Cargo through build.ps1 -OutputRoot C:\dev\ai-agent-keeb. From WSL, invoke that script with Windows PowerShell. Do not build the app with Linux Cargo or copy the source into the Windows output folder.
  • The default mode tests, builds, installs, restarts, and verifies the copy in %LOCALAPPDATA%\agent-frow. Use that installed copy for testing. -Mode Build and -Mode Test are explicit alternatives; CI never installs.
  • Versioned packages belong in C:\dev\ai-agent-keeb\dist. Use dist.ps1 -OutputRoot C:\dev\ai-agent-keeb to package a new release; preserve existing versioned archives. Do not create loose backup executables.
  • The user handles Git pushes. Leave changes local unless explicitly told to push.

See docs/how-it-works.md for the layout, rollback behavior, and portable commands. Other machines must supply their own separate Windows output root.

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. 1mo ago First seen · 18 lines · 271 tokens per session scan A 030c38b9294f

Subscribe to this mod's changes

agent-frow AGENTS.md is an instructions file published in the GitHub repository timeToy34/agent-frow (6 stars, last pushed 11d ago), licensed MIT. It adds 271 tokens to every session, about $0.0011 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 2026-09-24.

DevOps and cloudclaudecorsaircorsair-icuecorsair-rgbcorsair-rgb-keyboardsrgb-keyboard
Related

agent-frow AGENTS.md compared with instructions from other repositories

agent-frow AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agent-frow AGENTS.mdtimeToy34/agent-frowInstructions file611d agoMITA271Codex, 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