Borrowing it
Nothing to install: this file belongs to Sma1lboy/rove. 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/Sma1lboy/rove/main/AGENTS.mdgit clone --depth 1 https://github.com/Sma1lboy/roveWrote 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/sma1lboy/rove/agents-md)<a href="https://agentmods.dev/instructions/sma1lboy/rove/agents-md"><img src="https://agentmods.dev/badge/instructions/sma1lboy/rove/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/sma1lboy/rove/agents-md"><img src="https://agentmods.dev/badge/instructions/sma1lboy/rove/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 | $0.02267 | $0.02267 |
| Opus 5.5 | $0.00907 | $0.00907 |
| Sonnet 5.5 | $0.00453 | $0.00453 |
| Haiku 4.5 | $0.00227 | $0.00227 |
Grade C, and why
rove AGENTS.md scanned grade C 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **NEVER** delete files, branches, worktrees, or run `rm -rf` unless the user explicitly says "delete"/"remove" *in the same turn* — including stale-worktree cleanup. Surface and ask first. How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rove
Rove is a local-first terminal UI for running many AI coding sessions at once — Conductor's multi-task shape made terminal-native with git worktrees and local engine processes. A managed Task = git worktree + branch + terminal tabs; project-main and directory Tasks reuse an existing checkout or directory and own no worktree or branch. The TUI is the product; engine adapters (Claude Code default, Codex behind the same engine-owned contract) are execution backends.
This file is boundaries and orientation only. Read what the task needs:
HANDOFF.md— last local handoff (gitignored, may be absent). Check its date: an old one describes shipped work.docs/DESIGN.mddecisions + stack lock-in ·docs/ARCHITECTURE.mdsource map, ownership,refs/(§7) ·docs/HARNESS.mdself-test contract (load-bearing) ·docs/KEYBINDINGS.mdbefore any chord ·docs/agents/dev-loop.mdtest runners, dev scripts, daemon, engine-data, layout, file-size mechanics.- Version and shipped behavior:
packages/rove/package.json,packages/rove/CHANGELOG.md(over 1 MB: grep it or read the newest entries).
Docs are the source of truth. If docs and implementation disagree, surface the mismatch before widening scope.
Orientation
- Bun-workspace monorepo under
packages/:rove/(TUI/CLI, published@sma1lboy/rove),rove-daemon/,rove-harness/(/harness+ PTY sidecar),branding/(Remotion),rove-docs/(docs site). Unqualifiedsrc/…/test/…paths meanpackages/rove/. - Three test runners; the wrong one looks like a broken environment:
test/render/**→bun test,test/daemon/**→bun run test:socket(plain vitest silently finds no files), everything else → vitest.vi.hoisted is not a function= wrong runner. Details:docs/agents/dev-loop.md. - Develop with
dev:sandbox(throwaway Rove state), neverdev, so you don't touch the real~/.rove/tasks.json. - Tech stack is locked: TypeScript +
@opentui/core+@opentui/react+ React 19 + Bun. Do not re-litigate. React is the only UI; orchestrator/client reactivity is framework-free observable state. - One visual ground truth: fixed-viewport browser
/harness→ xterm.js → PTY sidecar → real OpenTUI. Not Terminal screenshots, render-test output, or mocks. Live-state bugs: drive a REAL engine through the browser's xterm and readrove api inspect. Every PR touching UI source keeps the template's UI evidence section with before/after harness screenshots (bugs and refactors too), orui-evidence: none — <reason>when no frame can change. Seedocs/HARNESS.md. - After editing daemon/orchestrator/engine code,
rove daemon restart— Bun doesn't hot-reload. Debug from<ROVE_HOME>/.rove/daemon.logfirst. refs/is gitignored and read-only; clone list and use indocs/ARCHITECTURE.md§7.- Changing config keys, CLI or
rove apiverbs, engine support, worktree safety, or session/persistence behavior → update the matchingdocs/page in the same PR. A new user-facing page must be added toSECTIONSinpackages/rove-docs/scripts/sync-docs.mjsor it never reaches docs.rove.run. - Respond in the user's language. Don't assume their name.
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 · +43 tokens per session 361ead7cbe71
- 2d ago Changed · +31 tokens per session 7841a1a78c26
- 17d ago Changed · -12 tokens per session 6ab2f83ed6c3
- 20d ago Changed · -38 lines · -1,563 tokens per session 20bb6f9bb47e
- 28d ago Changed · +7 tokens per session 5f8455d8b63f
- 29d ago Changed · +1 lines · +17 tokens per session 3011fd982865
- 1mo ago Changed · +36 tokens per session 72f627074517
- 1mo ago Changed · +29 tokens per session b129e407db08
- 1mo ago Changed · -16 tokens per session 01176fe7bab8
- 1mo ago First seen · 118 lines · 3,695 tokens per session scan C 1599e40029b0
rove AGENTS.md is an instructions file published in the GitHub repository Sma1lboy/rove (178 stars, last pushed today), licensed MIT. It adds 2,267 tokens to every session, about $0.0091 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.