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/lout33/termcanvas/agents-mdgit clone --depth 1 https://github.com/lout33/termcanvasWhat 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 | $0.01749 | $0.01749 |
| Opus 5 | $0.00874 | $0.00874 |
| Sonnet 5 | $0.00350 | $0.00350 |
| Haiku 4.5 | $0.00175 | $0.00175 |
Grade A, and why
termcanvas 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 2d 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file explains the local architecture of the TermCanvas app so future agents can extend it safely.
Product intent
This is a minimal infinite-canvas Electron app for spatial terminal workflows.
Each node is a real interactive terminal, not a text note. The product should stay simple and terminal-first.
Architecture overview
Main process — main.js
Responsibilities:
- create the Electron window
- own the terminal session registry
- spawn PTY clients through
node-pty - attach PTY clients to long-lived
tmuxsessions whentmuxis available - fall back to plain shell PTYs when
tmuxis unavailable - validate that a renderer only talks to its own terminal sessions
- detach live tmux-backed sessions when a window closes
- permanently destroy a terminal session when the user closes a node
- own workspace folder import, refresh, watch, and preview access
- own app-session file persistence in Electron
userData - own file dialog and local file read/write for canvas JSON and app-data JSON import/export
Important rule:
Real shell processes belong in main, never in the renderer.
Terminal identity model
The current session store is:
Map<terminalId, session>
Important distinction:
terminalIdis the current renderer-to-main attachment idsessionKeyis the stable terminal identity saved in app-session snapshots- tmux session names are derived from
sessionKey
Each session currently tracks:
ownerWebContentsIdptyshellNamecwdbackend("tmux"or"pty")sessionKeytmuxSessionNameisDisposing
Detach semantics matter:
- closing the app/window should detach from tmux-backed sessions in normal runs
- clicking a node close button should kill the underlying session permanently
- smoke-test mode disables persistent relaunch behavior so tests do not leak sessions
App-session persistence
The app now persists a normalized JSON snapshot under Electron userData.
That snapshot includes:
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.
- 2d ago First seen · 270 lines · 1,749 tokens per session scan A 269d4b20c840
termcanvas AGENTS.md is an instructions file published in the GitHub repository lout33/termcanvas (24 stars, last pushed 1mo ago), licensed MIT. It adds 1,749 tokens to every session, about $0.0087 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
plano CLAUDE.md
Instructions for zqkra/plano, covering claude.md, what plano is, commands, environment gotchas (windows — hit these during setup) and environment gotchas (linux / fedora kde — port-specific).
open-codesign CLAUDE.md
Instructions for OpenCoworkAI/open-codesign, covering claude.md — open codesign, what this project is, hard constraints (do not violate), stack & conventions and frontend stack (locked).
opencove AGENTS.md
AGENTS.md instructions for DeadWaveWave/opencove, covering system prompt: opencove project ai developer agent, 1. core directives & golden rules, 2. decision framework (small vs large), a. small change (fast feedback / 小步快反馈) and b. large change (deep thinking / 慎重对齐).
wesight AGENTS.md
Instructions for freestylefly/wesight, covering claude.md, build and development commands, build production bundle (typescript + vite), lint with eslint and run memory extractor tests (node.js built-in test runner).
limboo CLAUDE.md
Instructions for limboo-ai/limboo, covering claude.md, 1. what is limboo?, 2. tech stack (current), 3. project structure and the three electron contexts (critical mental model).
getvect AGENTS.md
Instructions for craigjmidwinter/getvect, covering agents.md, commands (green on a clean checkout), invariants a pr must not break and process.