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/rizriyz/luvus/agents-mdgit clone --depth 1 https://github.com/RizRiyz/luvusWhat 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 | $0.03991 | $0.03991 |
| Opus 5 | $0.01996 | $0.01996 |
| Sonnet 5 | $0.00798 | $0.00798 |
| Haiku 4.5 | $0.00399 | $0.00399 |
Grade A, and why
luvus 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 yesterday.
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 — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Shared maintainer guidance for coding agents working in the Luvus repository. This file is the repository-level source of truth. Tool-specific instruction files may add guidance, but they must not contradict it.
Start with current evidence
Luvus changes quickly. Before describing behavior or editing a subsystem:
- Check
git status --short --branchand preserve every unrelated change. - Inspect the current implementation and its focused tests.
- Use
cargo run --quiet -- help allorsrc/cli.rsfor the installed command surface. - Use
website/src/content/docs/for public product documentation. - Treat ignored files under
docs/as plans and historical handoffs, not as proof that a feature exists.
When remote state matters, compare the checkout with origin/main. Do not
silently change branches, fetch, rebase, or rewrite the user's work merely to
make the checkout match upstream.
Product model
Luvus is mission control for AI coding agents. It is a single Rust binary with several roles:
- With no command, it starts or attaches a thin TUI client.
- A detached server owns workspaces, tabs, panes, PTYs, terminal grids, agent state, persistence, modules, orchestration, API dispatch, and rendering.
- CLI commands send bounded JSON requests to the selected server and exit.
- Named sessions are independent server namespaces selected with
--session <name>orsession attach <name>. --localis a monolithic development escape hatch.--remote <host>attaches through an SSH byte bridge.
There are two local endpoints per server:
- the newline-delimited JSON control API;
- the binary client transport for input, full frames, frame diffs, clipboard, notifications, sound, detach, and shutdown messages.
Clients are disposable. The server is the single writer of application state. Detaching a client leaves panes alive. Stopping the server ends its live PTYs; the next server restores layout and resumes supported native agent sessions where possible.
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.
- yesterday First seen · 360 lines · 3,991 tokens per session scan A 76b04141a9f2
luvus AGENTS.md is an instructions file published in the GitHub repository RizRiyz/luvus (596 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,991 tokens to every session, about $0.0200 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
herdr AGENTS.md
AGENTS.md instructions for herdrdev/herdr, covering herdr, scope and audience, universal project rules, principles and multiplicative performance paths.
kungfu AGENTS.md
Instructions for kungfu-systems/kungfu, covering agents.md, start from the person's objective, rules that always apply, load bounded context before changing the repository and execute and verify through shifu.
jarvis-registry AGENTS.md
Instructions for ascending-llc/jarvis-registry, covering jarvis registry — agent guide, project overview, ⚠️ plan mode instructions ⚠️, my engineering preferences and 1. architecture review.
kungfu CLAUDE.md
Instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before working in this repository. It routes both product use and contribution work to the repository sources of truth, including the requirement that development and build tasks enter through Shifu.
kungfu copilot-instructions.md
Instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
beevibe CLAUDE.md
Instructions for beevibe-ai/beevibe, covering beevibe — claude code guide, monorepo structure, running locally, critical: @beevibe/core compiles to dist/ and restarting cleanly.