Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/jackspooner/agentcanvas/agents-mdgit clone --depth 1 https://github.com/jackspooner/agentcanvasWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00760 | $0.00760 |
| Opus 5 | $0.00380 | $0.00380 |
| Sonnet 5 | $0.00152 | $0.00152 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
agentcanvas 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentCanvas Agent Guide
Assets-2 usage
agentcanvas.assets2is an optional image-source extension. AgentCanvas stores the durable reference envelope; Assets-2 owns media identity and bytes.- Preserve canonical refs as
{type: "asset", project, assetId}. Do not copy Assets-2 bytes into AgentCanvas or add provider-specific fallbacks to core. - Use the native Assets-2 surface or the shared client for asset operations, and never return local paths, signed URLs, or inline binary data to agents.
Plugin architecture
- The public product term is extension. Keep
plugin,plugins/, andagentcanvas.plugin/v1where they are compatibility/runtime identifiers; new public authoring surfaces should use extension terminology. @agentcanvas/editoris the only package allowed to import React Flow. Document, HTTP, MCP, root web, and extension APIs must stay on canonical AgentCanvas contracts.- Core toolbar, keyboard, menu, and extension actions must use the shared editor command service.
- Runtime activation is determined only by non-hidden immediate child folders under
plugins/. Do not addagentcanvas.config.mjs, an enabled-plugin list, recursive discovery, remote loading, or hot reload. - First-party source belongs in
plugin-packages/; built distributions belong indist/plugin-catalog/;plugins/is generated active runtime state. - Normal element behavior must use
@agentcanvas/plugin-sdk. Do not add element type switches to kernel validation, HTTP, MCP, browser, or snapshot code. - HTTP, OpenAPI, browser delivery, snapshots, and resident MCP must consume one frozen registry. Stdio MCP remains a bridge to the resident
/mcpendpoint. - Plugins are trusted executable dependencies. Manifest permissions gate supported host services but are not a security sandbox.
- Missing optional plugins must preserve canonical envelopes. They may not silently normalize, delete, or downgrade stored data.
- Plugin activation changes require a restart. Invalid visible plugin folders fail startup explicitly.
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.
- yesterday First seen · 48 lines · 760 tokens per session scan A 5dcf5d03aefd
agentcanvas AGENTS.md is an instructions file published in the GitHub repository jackspooner/agentcanvas (0 stars, last pushed 27d ago), licensed MIT. It adds 760 tokens to every session, about $0.0038 per session on Opus 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 2026-08-31.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.