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/yusufkaraaslan/tote/agents-mdgit clone --depth 1 https://github.com/yusufkaraaslan/toteWrote 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/yusufkaraaslan/tote/agents-md)<a href="https://agentmods.dev/instructions/yusufkaraaslan/tote/agents-md"><img src="https://agentmods.dev/badge/instructions/yusufkaraaslan/tote/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 | $0.01642 | $0.01642 |
| Opus 5 | $0.00821 | $0.00821 |
| Sonnet 5 | $0.00328 | $0.00328 |
| Haiku 4.5 | $0.00164 | $0.00164 |
Grade A, and why
tote AGENTS.md scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Terminals must stay real PTYs (node-pty) — piping through child_process breaks TUI agents. node-pty's prebuilt `spawn-helper` must be executable (postinstall chmods it; asarUnpack for packaged builds) or spawns fail wi How it starts
The opening of the file, as written. The whole thing — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tote — agent notes
Electron hub app: web LLM tabs + shared workspace folder + docked CLI-agent terminals.
- Run:
npm install && npm start(postinstall copies xterm assets to src/renderer/vendor). - Main process:
src/main/(sessions per provider partition, downloads → ACTIVE workspace's inbox/, Downloads-folder bridge for native apps (macOS only; copies, and only files the quarantine xattr attributes to a known LLM app), app launcher, IPC, node-pty). Setup wizard logic lives insrc/main/installer.js(system checks, Claude Desktop MCP binding, MCP snippet) + the#wizard-*section ofsrc/renderer/app.js. - CLI profiles carry an
installcommand (npm -g) used by the wizard; keep package names accurate when adding profiles. Wizard installs self-heal: the run's output is buffered andsrc/renderer/npmfix.js(pure,npm testcovers it) detects npm's blocked-install-scripts warning (retry with--allow-scripts=…) and EACCES on a root-owned global prefix (setup:fixNpmPrefixpoints npm at~/.localonly whenprefixPlansays that's safe); each mend runs at most once. - Workspaces are two-level: one
global+ project spaces inconfig/workspaces.json. All file ops resolve the ACTIVE space at call time viaWorkspaceManager.getRoot()— never cache the root. Spaces are managed from the top strip's right-click menu and the Workspaces section of Settings (add / rename / change folder / remove →workspaces:*IPC); ids are stable across rename/re-point. - Renderer:
src/renderer/vanilla JS, no bundler. Bridge surface =window.tote(seesrc/preload/preload.js). - Providers, CLI profiles, workspaces and apps are data, not code: defaults in
config/*.json, runtime copies in userData. Prefer adding entries there over hardcoding. - Never give the renderer
nodeIntegration. New capabilities go through ipcMain handlers inmain.js+ preload wrappers. - Keep all workspace file access inside
WorkspaceManager.resolveSafe(path-escape guard). - Terminals must stay real PTYs (node-pty) — piping through child_process breaks TUI agents. node-pty's prebuilt
spawn-helpermust be executable (postinstall chmods it; asarUnpack for packaged builds) or spawns fail withposix_spawnp failed. - A GUI launch (Finder/Dock/
.desktop) gives the app a minimal PATH, socodex/claude/npmare missing even though they work in a terminal.ptyManager.jsruns every CLI profile through$SHELL -l -i -c 'exec …', andadoptLoginShellPath()inmain.jsadopts the login shell's PATH at startup for the wizard checks and local services. Don't exec profile commands directly on POSIX. - Webview popups (OAuth) must open in-app so they share the provider partition; only non-http schemes go to the system browser. UA = Electron's real UA minus Electron/Tote tokens — never a hardcoded foreign UA.
- Views are per-workspace: web tabs are instances stored in
views.json(+menu opens providers, duplicates allowed), terminals tagged withwsId;showWorkspaceViews()restores a space's setup on switch. - Layout: a tiling tree of panes, not docks. Web views, terminals and the files tree are equal leaves in one binary tree; the pure engine is
src/renderer/layout.js(window.TileTree, covered bynpm test) andapplyTiles()in app.js turns the tree into rects.#tilesis flat: a pane element is created once per content instance and never reparented — reparenting a<webview>reloads the guest and loses page state. - Strip order is the registry list order; a tab drag calls
workspaces:reorder→WorkspaceManager.reorder(ids), which only rewrites the order inworkspaces.json(active space, entry fields and watchers untouched) and re-appends any id the renderer omitted. - Temp spaces carry
temp: true+lastUsedand live undersettings.scratchRoot(default~/tote/scratch).discardTemp()is the only function in Tote that deletes user files — temp-only, inside-the-root-only, never the last space — andremove()still never touches the disk.promote()moves the folder and keeps the id soviews.jsonsurvives; the sweep runs at launch only. Pure parts are insrc/main/scratch.js, tested byscripts/test-scratch.js(run bynpm test). - Each space holds groups — virtual desktops with their own tree (
views.json:groups[]+activeGroup), switched from#group-baror Cmd/Ctrl+Alt+1…9. Other groups' webviews and PTYs stay alive and hidden. Walk persisted trees withgroupsOf(V), neverV.tiling. - The files tree is a dock:
insertRootpins it to the whole left edge at the width it had when closed (filesRatio, per space);splitTarget()andopenPanekeep content panes out of it. - Files dropped on a terminal pane are typed in as shell-escaped paths (
acceptFileDrop), never sent — and every other drop is swallowed, because Chromium's default is to navigate the window to the file. Paths come fromwebUtils.getPathForFile(File.pathis gone since Electron 32), withwill-navigatein main.js as the backstop. - Files are panes: clicking one opens leaf kind
doc, whose ref is an instance (views.json:docs: [{id, path, mode}]), not a path — a click retargets the pane you have, Cmd/Ctrl-click opens a second. Only those three fields persist; unsaved buffers never reach disk. Text and code are editable with Cmd/Ctrl+S, markdown and SVG render with asrc|viewtoggle (MOD+E), images and PDFs are read-only, and anything else still goes to the system app.readDocinworkspace.jsis the single classify-and-read channel;docKindalso stamps every tree node. - Rendered markdown comes from
src/renderer/markdown.js(pure,npm testcovers it) and is built withcreateElement— neverinnerHTML. The parser keeps raw HTML literal and filters hrefs to http(s)/mailto/relative, which is what makes that safe; keep both rules if you ever swap the parser out. - A doc pane re-reads its own file on
workspace:changed(the ping has no path): clean panes reload silently, dirty ones show thechanged on diskbar, and "keep mine" lets the next save overwrite. - Any splitter or pane drag must toggle
body.draggingso webviews don't eat mouse events. Fit xterm beforeptySpawnandptyResizeafter, or TUIs render at 80×24. Shift+Enter needs theattachCustomKeyEventHandlerinspawnTermthat sends LF (\n, the Ctrl+J byte) — xterm's default CR is indistinguishable from Enter, so agents submit instead of adding a line. That handler also maps Shift+arrows/Home/End to xterm's scrollback (bare arrows belong to the agent's history), passing them through on the alternate screen.
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 · +1 lines · +156 tokens per session 40a601205d9a
- 4d ago First seen · 26 lines · 1,486 tokens per session scan A 2e79b1b39a51
tote AGENTS.md is an instructions file published in the GitHub repository yusufkaraaslan/tote (5 stars, last pushed yesterday), licensed MIT. It adds 1,642 tokens to every session, about $0.0082 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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).
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.
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.