agentmods.dev

local-lmcanvas: Instructions file for Codex

AGENTS.md

local-lmcanvas AGENTS.md is an instructions file for Codex, OpenCode from max-lee-dev/local-lmcanvas. It costs 470 tokens per session, scanned A, original, MIT.

Project instructions for local-lmcanvas, a fully local desktop app for branching AI conversations, built with Electron, React, and TypeScript.

In plain words
What is it for?
Developing the Electron app, changing its canvas or conversation data model, connecting AI command-line providers, and running its required type check and build.
Why use it?
They identify the correct build checks and show where the app handles providers, saved conversations, communication between processes, and the user interface.

Instructions file for CodexOpenCode

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

This is max-lee-dev/local-lmcanvas's own configuration. It tells Codex and OpenCode how to work on local-lmcanvas 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 local-lmcanvas configures →

not rated 12repo 3mo ago A scan 470 tokens original MIT
View source ↗ max-lee-dev/local-lmcanvas
Reuse

Borrowing it

Nothing to install: this file belongs to max-lee-dev/local-lmcanvas. 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/max-lee-dev/local-lmcanvas/agent-sdk-rewrite/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/max-lee-dev/local-lmcanvas

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 local-lmcanvas AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/max-lee-dev/local-lmcanvas/agents-md"><img src="https://agentmods.dev/badge/instructions/max-lee-dev/local-lmcanvas/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 470 This file is loaded in full into every session.
When invoked 470 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 $0.00470 $0.00470
Opus 5.5 $0.00188 $0.00188
Sonnet 5.5 $0.00094 $0.00094
Haiku 4.5 $0.00047 $0.00047

Measured 2mo ago against content hash 299877a1744a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

local-lmcanvas 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 · 47 lines

What it actually says

AGENTS.md

Guide for AI coding agents (Claude Code, Cursor, Codex, etc.) working in this repo.

Project

local-lmcanvas is a fully-local, canvas-based branching AI conversation tool. Electron 33 + React 19 + TypeScript 5.6 (strict). Supports multiple CLI-backed providers (Claude, Codex, Cursor) with per-provider model selection; collects no telemetry.

Build & verify

bun install
bun run dev         # launches the Electron app
bun run typecheck   # REQUIRED before claiming work complete
bun run build       # production build

There are no tests and no lint script. Don't try to run them.

Project layout

  • src/main/ — Electron main process (Node), IPC handlers, file I/O. Touch for: spawning the LLM CLI, persisting canvases, settings.
  • src/preload/ — contextBridge. Touch for: adding new IPC channels exposed to the renderer.
  • src/renderer/ — React UI, xyflow canvas. Touch for: UI changes.
  • src/shared/ — types and graph helpers used by both sides. Touch for: changing the data model or message-history reconstruction.

Hot files

  • src/main/index.ts — IPC handler registration and BrowserWindow setup.
  • src/shared/history.ts — graph traversal / message-history reconstruction.
  • src/renderer/src/hooks/useCanvasStore.ts — Zustand store, ~530 lines.
  • src/renderer/src/components/Canvas/CustomNode.tsx — node UI, ~550 lines.

Conventions

  • TypeScript strict. No any unless a third-party type forces it.
  • No @ts-ignore / @ts-expect-error.
  • Minimal comments — names should carry the meaning.
  • No backwards-compat shims for code you delete.
  • IPC channels: typed in src/shared/ipc.ts, registered in src/main/index.ts, exposed in src/preload/index.ts. Keep all three in sync.

Before you finish

  1. Run bun run typecheck.
  2. Run bun run dev and click through what you changed.
  3. Summarize what you did.
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 · 47 lines · 470 tokens per session scan A 299877a1744a

Subscribe to this mod's changes

local-lmcanvas AGENTS.md is an instructions file published in the GitHub repository max-lee-dev/local-lmcanvas (12 stars, last pushed 3mo ago), licensed MIT. It adds 470 tokens to every session, about $0.0019 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.

Building agentsFrontendReact
Related

local-lmcanvas AGENTS.md compared with instructions from other repositories

local-lmcanvas AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
local-lmcanvas AGENTS.mdmax-lee-dev/local-lmcanvasInstructions file123mo agoMITA470Codex, 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