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/niall-young/canvasight/agents-mdgit clone --depth 1 https://github.com/Niall-Young/CanvasightWrote 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/niall-young/canvasight/agents-md)<a href="https://agentmods.dev/instructions/niall-young/canvasight/agents-md"><img src="https://agentmods.dev/badge/instructions/niall-young/canvasight/agents-md.svg" alt="Measured on agentmods" 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 | $0.06043 | $0.06043 |
| Opus 5 | $0.03021 | $0.03021 |
| Sonnet 5 | $0.01209 | $0.01209 |
| Haiku 4.5 | $0.00604 | $0.00604 |
Grade A, and why
Canvasight 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Context
Canvasight is an early-stage repo-local Codex plugin. The active product lives under plugins/canvasight as a Vite, React, TypeScript, XYFlow, Zustand, and Radix UI application. Preserve room for the final stack, but do not treat the repository as an empty baseline anymore.
The plugin opens a canvas workspace whose v2 domain model is Page -> Group -> Task Node | Asset Node. Task Nodes own Markdown instructions and Codex mode; Asset Nodes each reference one Canvasight-managed project file and may start a downstream Run; Groups are non-nested semantic containers whose Run includes only direct members, internal Edges, and member assets. Task Nodes do not accept new inline attachments: file selection, drop, and file/image paste create Asset Nodes. Legacy Task attachments remain readable, runnable, exportable, removable, and explicitly promotable without silent data loss. Edges express dependency/evidence/decision/flow rather than Group containment. The web app is served by a project-level local daemon that outlives thread-local MCP shim processes. Normal plugin use renders Canvasight inside a Codex native widget through open_canvasight; callers must read the active task's CODEX_THREAD_ID and pass it as threadId because MCP child processes may not inherit it and Chat / Plan / Goal preflight requires an explicit target. The widget directly hosts the built app instead of iframe-loading localhost. Native widget JSON APIs route through the app-only canvasight_widget_api MCP tool, which proxies a strict allowlist to the daemon; the sandboxed widget must not depend on direct localhost fetches for startup or editing. Widget CSP must still include the daemon's exact origin before resource delivery for daemon-backed attachment assets. Native open tool results must not publicly expose daemon 127.0.0.1 URLs or tokens. Running a Task/Asset sends Markdown for that node plus downstream children; running a Group sends only its contained scope to the current Codex thread through the widget host bridge after native Chat / Plan / Goal preflight. The widget bridge may use standard MCP Apps ui/message or the Codex/OpenAI compatibility window.openai.sendFollowUpMessage; both count as native widget host bridge transports, not browser fallback. A successful MCP App handshake makes sendMessage callable even if the host omits the advisory hostCapabilities.message declaration; only the send Promise result determines sent/failed. Browser URLs and bare dev pages are fallback/development surfaces: after a current-thread claim they only queue payloads for await_canvasight_run; they must not report app-server turn/start as a successful Run path.
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.
- 5d ago First seen · 134 lines · 6,043 tokens per session scan A 32192bb5503b
Canvasight AGENTS.md is an instructions file published in the GitHub repository Niall-Young/Canvasight (209 stars, last pushed 9d ago), licensed MIT. It adds 6,043 tokens to every session, about $0.0302 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 2026-08-30.
Other instructions, from other repositories
semiotic CLAUDE.md
Claude Code instructions for nteract/semiotic, covering semiotic claude code instructions and claude code notes.
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
pip-web CLAUDE.md
Claude Code instructions for playpip/pip-web, covering claude.md — agent guide for pip, read first (by task), the three layers (respect the boundaries), non-negotiables and commands / definition of done.
rush AGENTS.md
Instructions for onurhan1337/rush, covering project rules for ikas app starter app (next.js), core principles, stack overview, mcp usage and graphql and api workflow.
tanstack-start-template AGENTS.md
AGENTS.md instructions for dyeoman2/tanstack-start-template, covering tanstack start agent guide, core philosophy, architecture, golden rules and key patterns.
next-sanity CLAUDE.md
Claude Code instructions for sanity-io/next-sanity, a project described as: Sanity toolkit for Next.js.