Borrowing it
Nothing to install: this file belongs to XMihura/Kanvas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/XMihura/Kanvas/main/AGENTS.mdgit clone --depth 1 https://github.com/XMihura/KanvasWrote 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.
[](https://agentmods.dev/instructions/xmihura/kanvas/agents-md)<a href="https://agentmods.dev/instructions/xmihura/kanvas/agents-md"><img src="https://agentmods.dev/badge/instructions/xmihura/kanvas/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.
<a href="https://agentmods.dev/instructions/xmihura/kanvas/agents-md"><img src="https://agentmods.dev/badge/instructions/xmihura/kanvas/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01339 | $0.01339 |
| Opus 5.5 | $0.00536 | $0.00536 |
| Sonnet 5.5 | $0.00268 | $0.00268 |
| Haiku 4.5 | $0.00134 | $0.00134 |
Grade A, and why
Kanvas 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 today.
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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on Kanvas
Kanvas is a task board shared by humans and AI agents. This file is for agents and contributors changing Kanvas itself. The instructions Kanvas gives to agents in other projects live in skill/SKILL.md.
Layout
| Path | What it is |
|---|---|
kanvas.py |
CLI, board model, local server, init / import / export. Python 3.8+, standard library only |
kanvas.html |
The whole browser board in one file: CSS, markup and JavaScript, no build step |
skill/SKILL.md |
Agent skill that init installs into projects |
examples/sample.json |
Demo board, also used by the tests |
examples/drone.json |
The board in the README, its screenshots and the skill's examples |
tests/test_kanvas.py |
Test suite (unittest) |
tests/layout_stats.py, tests/fixtures/ |
Graph clutter measurements and the boards they run on |
pyproject.toml |
The kanvas-board package, which installs the kanvas command. Its version comes from VERSION in kanvas.py, and the VERSION file must match. hatchling and hatch-fancy-pypi-readme, which points the README's relative links at GitHub for PyPI, are needed only to build it |
tests/check_installed.py |
Runs an installed kanvas command through init, subfolders, export, serve (with a second project joining it) and the project copy |
Rules
- Zero dependencies.
kanvas.pyuses only the standard library and must run on Python 3.8 on Linux, macOS and Windows.kanvas.htmlloads nothing from the network. - One format, two writers.
kanvas.py(canonical,dumps) andkanvas.html(canonical,serialize) must produce byte-identical files. Change both together;test_html_serializer_matches_pythonchecks it. - The CLI enforces the agent workflow. Agents can propose, start, finish (with a summary), pause, note and add dependencies, and they can edit, withdraw and rewire proposals until a human approves them. Approving, changing approved tasks and marking done stay human-only, in the browser. Turning YOLO on approves the chain's proposals; a proposal an agent links into the chain later stays a proposal.
- Writes are safe. Every CLI write goes through
mutate(): lock, load, change, atomic replace. Failed commands leave the file untouched. Browser saves are compare-and-swap through the server (If-Match, 409 with the current board, the change is replayed). - Never edit a user's existing files.
initonly creates files that do not exist yet, apart from the skill copies it owns.
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.
- today Changed · -62 lines · +330 tokens per session 46149a01aa68
- 1mo ago First seen · 132 lines · 1,009 tokens per session scan A b0b5e0467296
Kanvas AGENTS.md is an instructions file published in the GitHub repository XMihura/Kanvas (297 stars, last pushed today), licensed MIT. It adds 1,339 tokens to every session, about $0.0054 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.
Other instructions, from other repositories
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.