agentmods.dev

gpt-image-canvas: Instructions file for Codex

AGENTS.md

gpt-image-canvas AGENTS.md is an instructions file for Codex, OpenCode from mrslimslim/gpt-image-canvas. It costs 710 tokens per session, scanned A, original, MIT.

Repository instructions that explain the project layout, package manager, development commands, and checks required before a change is complete.

In plain words
What is it for?
Use them when installing dependencies, navigating the API, web app, and shared package, running type checks or builds, and verifying user-interface work in a browser.
Why use it?
They give a coding agent the project’s working rules so it knows where code belongs and how to verify its changes.

Instructions file for CodexOpenCode

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

This is mrslimslim/gpt-image-canvas's own configuration. It tells Codex and OpenCode how to work on gpt-image-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 gpt-image-canvas configures →

not rated 739repo 2mo ago A scan 710 tokens original MIT
View source ↗ mrslimslim/gpt-image-canvas
Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mrslimslim/gpt-image-canvas/agents-md"><img src="https://agentmods.dev/badge/instructions/mrslimslim/gpt-image-canvas/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 710 This file is loaded in full into every session.
When invoked 710 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 $0.00710 $0.00710
Opus 5.5 $0.00284 $0.00284
Sonnet 5.5 $0.00142 $0.00142
Haiku 4.5 $0.00071 $0.00071

Measured 2mo ago against content hash c82a7909a6ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gpt-image-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 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.

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 · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Notes

Package Management

  • Use pnpm install; the package manager is pinned to [email protected].
  • Root scripts delegate to workspace packages: pnpm dev, pnpm api:dev, pnpm web:dev, pnpm typecheck, pnpm build, and pnpm start.

Workspace Map

  • API app: apps/api.
  • Web app: apps/web.
  • Shared contracts: packages/shared.

Required Verification

  • Before completing a story, run pnpm typecheck and pnpm build.
  • UI stories require browser verification against the running app. Run pnpm dev and open the Vite web app, usually http://localhost:5173.
  • Post-change verification must be delegated to a subagent running in an independent context whenever the agent environment supports subagents.
  • The verification subagent should run the relevant checks, report exact commands and outcomes, and avoid editing implementation files unless explicitly assigned.
  • Do not mark a story complete until the subagent verification has passed, or until any blocker is clearly documented with the failing command and error summary.
  • If verification fails, fix the issue in the main implementation context, then ask the subagent to rerun the affected checks from a fresh independent context.

Documentation Map

  • Read docs/PRODUCT_SENSE.md before changing product behavior, onboarding, Gallery, provider configuration, or Agent workflows.
  • Read docs/DESIGN.md and docs/FRONTEND.md before UI work in apps/web.
  • Read docs/design-docs/interaction-quality.md for UI polish and micro-interaction work.
  • Read docs/PLANS.md before writing product specs, execution plans, Ralph PRDs, or multi-story task breakdowns.
  • Read docs/RELIABILITY.md and docs/SECURITY.md before API, storage, provider, Docker, SQLite, asset, secret, or local data work.

Native Dependencies

  • After switching Node versions, rebuild native API dependencies if better-sqlite3 reports a NODE_MODULE_VERSION mismatch: pnpm --filter @gpt-image-canvas/api rebuild better-sqlite3 --stream.

Read the full file on GitHub · 51 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 · 51 lines · 710 tokens per session scan A c82a7909a6ce

Subscribe to this mod's changes

gpt-image-canvas AGENTS.md is an instructions file published in the GitHub repository mrslimslim/gpt-image-canvas (739 stars, last pushed 2mo ago), licensed MIT. It adds 710 tokens to every session, about $0.0028 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.

aiai-toolsaiimagegenerator
Related

gpt-image-canvas AGENTS.md compared with instructions from other repositories

gpt-image-canvas AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
gpt-image-canvas AGENTS.mdmrslimslim/gpt-image-canvasInstructions file7392mo agoMITA710Codex, OpenCode
vibetags com-example-config-AsyncTestConfig.instructions.mdPIsberg/vibetagsInstructions file25yesterdayMITA82GitHub Copilot
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