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 skills/rizriyz/luvus/luvus-modulenpx skills add RizRiyz/luvus --skill luvus-modulegit clone --depth 1 https://github.com/RizRiyz/luvusWrote 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/skills/rizriyz/luvus/luvus-module)<a href="https://agentmods.dev/skills/rizriyz/luvus/luvus-module"><img src="https://agentmods.dev/badge/skills/rizriyz/luvus/luvus-module.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 | $0.00079 | $0.02164 |
| Opus 5 | $0.00039 | $0.01082 |
| Sonnet 5 | $0.00016 | $0.00433 |
| Haiku 4.5 | $0.00008 | $0.00216 |
Grade A, and why
luvus-module 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 4d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing a luvus module
A luvus module is a plugin for luvus, mission control for your AI coding agents. There is no SDK and no scripting engine: a module is a directory with a luvus-module.toml manifest that declares argv commands (any executable: sh, python, node, a compiled binary). luvus runs those commands as subprocesses with LUVUS_* context in the environment, and the command calls luvus back through the same UHP the luvus CLI uses. So a module in bash/python/node can do what a built-in feature does.
Reference material in this repo (read for depth): MODULE-GUIDE.md, docs/13-modules.md, and the worked modules in examples/modules/ (branch-dock = a sidebar dock, agent-ping = an event hook, scratch-pane = a pane).
The manifest: luvus-module.toml
Top-level keys (all required unless noted):
id = "yourname.my-module" # unique, reverse-dns style
name = "My Module"
version = "0.1.0"
min_luvus_version = "0.8.3" # oldest luvus this needs
description = "One line." # optional
platforms = ["macos", "linux"] # optional; omit = all. Also per-item.
Then any of these tables, each declaring an argv command (a list, run as-is, cwd = the module dir):
[[docks]]id,title,placement(sidebar.left|sidebar.right) — reserve a sidebar dock. luvus renders it; you fill it withui.dock.push(see below).[[bars]]id,title,region(top-right|bottom-right), optionalpriority— reserve a bounded one-row Luvus Bar widget. Publish structured segments withluvus bar push(ui.bar.pushon the UHP); live content is not persisted.[[startup]]command— run once when the session is up and the socket is listening (and on enable). Dock rows and bar content are not persisted, so this is how you repaint them after a restart.[[events]]on,command— run when a luvus event fires. Validonvalues includeworkspace.created/closed,tab.created/closed/moved,pane.created/closed/forked/moved,pane.agent_status_changed,agent.hook, and thetask.*/lease.*events (seeKNOWN_EVENTSinsrc/module/manifest.rsfor the full set — an unknownonis a hard manifest error).[[actions]]id,title,command, optionalcontexts— a runnable action. Withcontexts = ["pane"|"workspace"|"node"|"agent"|"tab"]it also appears in that right-click menu, acting on what was clicked. Withoutcontextsit is CLI-only (luvus module run <id> <action>). Dock rows also invoke an action on click.[[panes]]id,title,command,placement(split|overlay|tab) — a real pane running your command (luvus module pane open <id> <entrypoint>).[[settings]]key,title,type(bool|string|number|enum), plusdefault,options(enum),min/max/step(number),secret(mask + hide the value). Rendered in Settings → Modules; values reach every command as env (below).
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.
- 4d ago First seen · 96 lines · 79 tokens per session scan A ed3bfeafa736
luvus-module is a skill published in the GitHub repository RizRiyz/luvus (683 stars, last pushed yesterday), licensed Apache-2.0. It adds 79 tokens to every session and 2,164 once invoked, about $0.0004 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 skills, from other repositories
herdr-throwaway-repro
Create and control a disposable named Herdr session from inside an existing Herdr session. Use for isolated Herdr runtime, pane, terminal, process, API, persistence, or agent reproductions that should be driven through the CLI/API without touching the default session.
triage
Triage open herdr GitHub issues into a concise decision-first Markdown table. Use when the user says "triage", asks to triage open issues, asks which issues need attention, or wants issue priority/recommendation lights for herdr.
kungfu-agent-onboarding
Discover the exact Kungfu Project, WorkConsole, WorkRef, Skill catalog, and Core Work state admitted to this Amp process.
local-frontend-check
Smoke-test or verify UI behaviour on the local Jarvis Registry frontend running at http://localhost/gateway. Use for manual regression checks, bug-fix verification, and end-to-end confirmation of specific flows without running the automated test suite.
kungfu-agent-onboarding
Use when a user asks to understand, start, inspect, extend, or safely operate installed Kungfu; verify the installed pack, select one intent route, personalize the explanation, and propose one smallest safe next action.
with-frontmatter
Help an agent inspect a failed trace run, identify likely failure layers, and produce a short audit note.