agentmods.dev

repo-canvas: Instructions file for Codex

AGENTS.md

repo-canvas AGENTS.md is an instructions file for Codex, OpenCode from m0ast-git/repo-canvas. It costs 566 tokens per session, scanned A, original, MIT.

A set of repository instructions for Repo Canvas that guides an agent through understanding a change before editing code. It covers documentation, checkpoints, affected parts of the system, unfinished work, and final checks.

In plain words
What is it for?
Use it to trace a change through data production, storage, consumers, and the interface; update the right project documents; preserve unfinished work; and validate the complete affected user scenario.
Why use it?
It helps avoid fixing only the first visible defect while missing related components or causing regressions elsewhere. It also gives one place for current requirements, progress, test results, and limitations.

Instructions file for CodexOpenCode

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

This is m0ast-git/repo-canvas's own configuration. It tells Codex and OpenCode how to work on repo-canvas 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 repo-canvas configures →

not rated 25repo 1mo ago A scan 566 tokens original MIT
View source ↗ m0ast-git/repo-canvas
Reuse

Borrowing it

Nothing to install: this file belongs to m0ast-git/repo-canvas. 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/m0ast-git/repo-canvas/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/m0ast-git/repo-canvas

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 repo-canvas AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/m0ast-git/repo-canvas/agents-md/github.svg)](https://agentmods.dev/instructions/m0ast-git/repo-canvas/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/m0ast-git/repo-canvas/agents-md"><img src="https://agentmods.dev/badge/instructions/m0ast-git/repo-canvas/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 repo-canvas AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/m0ast-git/repo-canvas/agents-md"><img src="https://agentmods.dev/badge/instructions/m0ast-git/repo-canvas/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 566 This file is loaded in full into every session.
When invoked 566 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 $0.00566 $0.00566
Opus 5.5 $0.00226 $0.00226
Sonnet 5.5 $0.00113 $0.00113
Haiku 4.5 $0.00057 $0.00057

Measured 1mo ago against content hash 8753acb26cfb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

repo-canvas 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 · 20 lines

How it starts

The opening of the file, as written. The whole thing — 20 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Работа с Repo Canvas

Вход в задачу и восстановление контекста

  • Перед нетривиальными изменениями и после компакта прочитай карту документации, целиком системную сводку и текущий checkpoint. По задаче дочитай пользовательский сценарий, дизайн или критерии приёмки. Старые логи и снимки не заменяют действующие требования.
  • До правки проследи затронутый путь через производителя данных, хранение, потребителей и обратную связь UI. Используй таблицу области влияния в системной сводке. Проверь соседние компоненты вне исходного списка дефектов.
  • При новом обходе или неожиданной регрессии пересмотри общий механизм до следующей правки. Для библиотечных задач сначала изучи установленную зависимость и её настройки. Финальная приёмка относится ко всему затронутому сценарию.
  • Обновляй канонический документ при изменении контракта; текущий ход долгой задачи держи только в docs/RESUME.md, заменяя устаревшее. Результаты проверок и ограничения — в docs/implementation-status.md и design-qa.md, без конкурирующих версионных инструкций.

Границы работы

  • Пользовательская .repo-canvas/ содержит журнал и историю проекта. Не подменяй её тестовыми данными; для изменяющих данные проверок используй изолированный проект либо обратимое действие с проверенной отменой.
  • Сохраняй незакоммиченные изменения других задач. Не сбрасывай геометрию владельца ради красивой раскладки и не мигрируй записанное прошлое как обычный live-кеш.
  • UI- и документационные задачи не являются основанием запускать полное платное построение. Проверка каталога компонентов не подтверждает работу настоящей карты.
  • Один рабочий сервер; перед запуском проверь слушателя порта. Завершай только свои заменённые/проверочные процессы. Установка и запуск описаны в README.

Проверка

Выбирай проверки по области влияния и критериям приёмки. Изменения кода проверяются релевантными тестами и реальным сценарием; изменения визуала — браузером, включая движение и масштабы. Для документационной уборки проверь сохранение требований, ссылки и отсутствие противоречий; она не требует модельных вызовов или нового прогона приложения.

Read the full file on GitHub · 20 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. 1mo ago First seen · 20 lines · 566 tokens per session scan A 8753acb26cfb

Subscribe to this mod's changes

repo-canvas AGENTS.md is an instructions file published in the GitHub repository m0ast-git/repo-canvas (25 stars, last pushed 1mo ago), licensed MIT. It adds 566 tokens to every session, about $0.0023 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 2026-09-28.

Memory and contextPlanningai-agentscodexdeveloper-toolsrepository-visualization
Related

repo-canvas AGENTS.md compared with instructions from other repositories

repo-canvas AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
repo-canvas AGENTS.mdm0ast-git/repo-canvasInstructions file251mo agoMITA566Codex, 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