Agent skill

Luvus Module

by RizRiyz in RizRiyz/luvus

Write a luvus module (an extension for luvus, mission control for your AI coding agents).

Apache-2.0Auto-check passedDevelopment

Install Luvus Module

skills CLI
$ npx skills add RizRiyz/luvus --skill luvus-module -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install RizRiyz/luvus luvus-module --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/RizRiyz/luvus.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/luvus-module .claude/skills/luvus-module && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
luvus-module
GitHub stars
957
Token cost
~2.5k tokens
SKILL.md length
1,208 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
Apache-2.0

At a glance

Write a luvus module (an extension for luvus, mission control for your AI coding agents).

  • The user is building
  • SKILL.md covers The manifest: luvus-module.toml, What your command receives (no…, What your command can do: call… and Recipes, plus 2 more sections
  • Needs LUVUS_MODULE_TOKEN
  • Debugging a luvus module: authoring luvus-module.toml

What it does

Luvus Module is an agent skill from RizRiyz/luvus. Write a luvus module (an extension for luvus, mission control for your AI coding agents). Use when the user is building or debugging a luvus module: authoring luvus-module.toml, adding a sidebar dock, Luvus Bar widget, right-click action, event hook, module pane, module settings, or calling luvus back over its UHP.

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development. It works with Kimi, tmux and Rust. The repository describes itself as: Mission control for your AI agents. The licence is Apache-2.0.

When your agent uses it

  • The user is building
  • Debugging a luvus module: authoring luvus-module.toml
  • Adding a sidebar dock
  • Luvus Bar widget

Example prompts

  • “/luvus-module”

Requirements

  • A credential in LUVUS_MODULE_TOKEN

What it can do on your machine

Read from SKILL.md and the folder at commit 5a2ebeb. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are toml).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • LUVUS_MODULE_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Luvus Module loads about 2.5k tokens when it runs. Until then it costs about 82 tokens; SKILL.md has 1,208 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~82
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from RizRiyz/luvus at commit 5a2ebeb, republished under its Apache-2.0 licence (© RizRiyz). 1,208 words, ~2,518 tokens.

Download SKILL.mdSave it as .claude/skills/luvus-module/SKILL.md (or your agent's skills folder).
name
luvus-module
description
Write a luvus module (an extension for luvus, mission control for your AI coding agents). Use when the user is building or debugging a luvus module: authoring luvus-module.toml, adding a sidebar dock, Luvus Bar widget, right-click action, event hook, module pane, module settings, or calling luvus back over its UHP.

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):

toml
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 with ui.dock.push (see below).
  • [[bars]] id, title, region (top-right | bottom-right), optional priority — reserve a bounded one-row Luvus Bar widget. Publish structured segments with luvus bar push (ui.bar.push on 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. Valid on values include workspace.created/closed, tab.created/closed/moved, pane.created/closed/forked/moved, pane.agent_status_changed, agent.hook, and the task.*/lease.* events (see KNOWN_EVENTS in src/module/manifest.rs for the full set — an unknown on is a hard manifest error).
  • [[actions]] id, title, command, optional contexts — a runnable action. With contexts = ["pane"|"workspace"|"node"|"agent"|"tab"] it also appears in that right-click menu, acting on what was clicked. Without contexts it 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), plus default, options (enum), min/max/step (number), secret (mask + hide the value). Rendered in Settings → Modules; values reach every command as env (below).
  • [worktree_provider] one optional fixed creation command, optional fixed remove_command, and optional platforms. The user selects the module id in config.json at worktree.provider; config cannot replace either command.

A worktree provider reads one versioned JSON request from stdin. Creation gets version, operation, repository, branch, and branch_exists, and must print only {"path":"/absolute/worktree/path"} on stdout. Removal gets version, operation, repository, path, branch, and force; it must print nothing, exit successfully, and unregister and remove the target. If a provider violates its exit or stdout contract after deletion already completed, Luvus reconciles the proven Git/filesystem state instead of retaining a stale workspace; stdout remains unsupported. Human logs go to stderr. This command is synchronous and must not call back into the Luvus CLI/API while the server waits. Luvus verifies the returned path is a registered worktree of the source repository on the exact requested branch before opening a workspace; explicit removal is verified before and after the command. Internal rollback and task merge remain Git-backed.

What your command receives (no JSON parsing needed)

luvus puts context in the environment, flat, so a bash module never parses JSON:

  • LUVUS_MODULE_ID, LUVUS_MODULE_ROOT (the module dir), LUVUS_MODULE_VERSION
  • LUVUS_MODULE_TOKEN — UI-publisher credential for this server; the Luvus CLI forwards it automatically, so do not persist or override it
  • LUVUS_MODULE_CONFIG_DIR, LUVUS_MODULE_STATE_DIR — writable per-module dirs
  • LUVUS_WORKSPACE_ID, LUVUS_WORKSPACE_CWD, LUVUS_TAB_INDEX
  • LUVUS_PANE_ID, LUVUS_PANE_CWD, LUVUS_PANE_AGENT, LUVUS_PANE_STATUS (the clicked/target pane)
  • LUVUS_SETTING_<KEY> for each declared setting (uppercased key), plus the whole set as JSON
  • [worktree_provider] commands read their versioned operation request as JSON from stdin
  • Dock-row clicks add LUVUS_MODULE_DOCK_ID, LUVUS_MODULE_ROW_ACTION, LUVUS_MODULE_ROW_VALUE, LUVUS_MODULE_ROW_TEXT, LUVUS_MODULE_ROW_INDEX
  • Bar-segment clicks add LUVUS_MODULE_BAR_ID, LUVUS_MODULE_BAR_SEGMENT, and optional LUVUS_MODULE_BAR_VALUE
  • LUVUS_MODULE_CONTEXT_JSON — the full snapshot, if you want structured data
  • LUVUS_SOCKET_PATH, LUVUS_BIN_PATH — to call luvus back (below)
Show full SKILL.md (573 more words)Show less

What your command can do: call luvus back

Run the luvus CLI from inside the command; it talks to the running server over $LUVUS_SOCKET_PATH. Use "$LUVUS_BIN_PATH" to guarantee the same binary as the session. Module-facing methods:

  • luvus ui dock push --id <dock> --rows <json> (or pipe the JSON on stdin) — fill your dock. Rows are {text, dot?, tone?, spans?, action?, value?, menu?}; a row's action invokes one of your [[actions]] on click, with the row's value in LUVUS_MODULE_ROW_VALUE. tone is a Luvus Bar tone name (normal, muted, accent, success, warning, error) for the text, and spans is [{text, tone?}] to color segments of one row with the same tone names (a span without a tone takes the row's). Both are optional and theme-bound, raw colors and ANSI are not accepted. Omitting tone gives the default row color, which is not the same as normal.
  • luvus bar push --id <widget> --content <json> — atomically publish structured text, symbol, state, badge, progress, spacer, and separator segments. Add --compact-content; an action must name one of your [[actions]].
  • luvus ui notification push --text <text> --level info|success|warning|error — publish bounded transient status; use --dedupe-key for replacement.
  • luvus ui toast "<text>" — flash a one-line confirmation.
  • luvus ui agent-title push --titles <json> — publish AGENTS sidebar titles for live panes (pane) and resumable sessions (built-in agent + session_id). OSC still wins; never send a Luvus =alias as the title. luvus ui agent-title clear drops one key or every title owned by your module. The CLI authenticates ownership automatically.
  • luvus ui sidebar / ui dock list / ui dock move — sidebar/dock control.
  • luvus tab rename <name> / tab list — tabs.
  • luvus module settings <id> / module settings <id> <key> — read your settings exactly (values are masked in settings list when secret, but exact in settings get).
  • Plus the whole CLI: luvus pane split/run/send, luvus agent ..., luvus git ..., etc.

Recipes

A sidebar dock (like examples/modules/branch-dock): declare [[docks]], a [[startup]] that runs a script which builds a JSON rows array and calls ui dock push, and [[events]] so it refreshes on workspace.created/tab.created. Give rows an action matching a [[actions]] id to make them clickable.

A Luvus Bar widget (like examples/modules/ci-bar): declare [[bars]], publish full and compact structured content from a one-shot startup/event action, and keep expensive work outside the render path. Use a pane for arbitrary terminal UI and a dock for multi-row content.

An event hook (like agent-ping): a [[events]] with on = "pane.agent_status_changed" and a command that reads LUVUS_PANE_* and reacts (notify, log, ui toast).

A right-click action: an [[actions]] with contexts = ["pane"] (or workspace/node/agent/tab). It appears in that menu and runs against the clicked target's LUVUS_* env.

A pane: a [[panes]] entry; open it with luvus module pane open <module-id> <entrypoint>.

Test loop

luvus module link <path-to-module-dir>     # register a local module (dev)
luvus module list                          # confirm it's runnable
luvus module log [<id>]                     # tail command output/errors while iterating
luvus module run <id> <action>              # invoke an action directly
luvus module enable <id> | disable <id>

Iterate: edit the script, re-run the action or trigger the event, watch module log. The manifest is validated on link; a broken manifest keeps the entry visible but not runnable, with the reason in module info <id>.

Conventions

  • One module, one job. Keep commands fast and quiet — luvus caps a command's output (64 KiB) and runs at most 32 at a time.
  • Identity env (LUVUS_MODULE_ID, LUVUS_MODULE_TOKEN, socket path) is injected and cannot be overridden. Never log or persist the token.
  • Use platforms on the manifest or any item to skip a build step / hook / pane / action where it does not apply.
  • To share it: luvus module install <owner>/<repo> clones + builds + registers from GitHub; tag the repo with the luvus-module topic so luvus module search finds it.

© RizRiyz, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/luvus-module of RizRiyz/luvus.

Open the folder on GitHubat commit 5a2ebeb

Compare with similar skills

Luvus Module next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Luvus Module compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Luvus Module this skillRizRiyz/luvus957—~2.5kAutomated safety check: PassApache-2.0
Tuicragavra/tuicr3.3k—~3.2kAutomated safety check: PassMIT
TUI Change Verification for Warpwarpdotdev/warp65k1 repos~5.5kAutomated safety check: NotesAGPL-3.0
Agenttrace Session Auditluoyuctl/agenttrace1401 repos~656Automated safety check: PassMIT
Run Shuntpleaseai/shunt264—~2.6kAutomated safety check: PassApache-2.0
Migrate Core Code to Submodulestinyhumansai/openhuman42k—~2.6kAutomated safety check: PassGPL-3.0

Similar skills

  • Tuicr

    agavra/tuicr

    Use tuicr's review CLI to read and add comments in active TUI review sessions, and launch tuicr in cmux, tmux, Zellij, or Herdr when a user needs an interactive review pane.

    3.3k GitHub stars~3.2k tokensUpdated today
    DevelopmentAuto-check passed
  • Runs Warp's terminal UI for real, drives it with keystrokes and reads the rendered screen back to confirm that a change looks and behaves as intended.

    65k GitHub starsUsed in 1 repo~5.5k tokens
    Testing & QAAuto-check: notes
  • Agenttrace Session Audit

    luoyuctl/agenttrace

    Audit local AI coding-agent sessions with agenttrace. An agent skill from luoyuctl/agenttrace.

    140 GitHub starsUsed in 1 repo~656 tokens
    AI & LLM EngineeringAuto-check passed
  • Run Shunt

    pleaseai/shunt

    Build, launch, and drive shunt — the Claude Code LLM gateway (a Rust/axum Anthropic-Messages proxy).

    264 GitHub stars~2.6k tokensUpdated today
    Testing & QAAuto-check passed
  • Migrate Core Code to Submodules

    tinyhumansai/openhuman

    Plans and carries out moving non-host-specific code and its tests from the OpenHuman core into vendored tiny submodule libraries, then releases the submodule and re-pins the host.

    42k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed
  • Guide for writing idiomatic Rust code based on Apollo GraphQL's best practices handbook.

    5.6k GitHub starsUsed in 3 repos~1.1k tokens
    DevelopmentAuto-check passed

Works with

Categories

Questions about Luvus Module

What does Luvus Module do?

Write a luvus module (an extension for luvus, mission control for your AI coding agents). Luvus Module is an agent skill from RizRiyz/luvus. Write a luvus module (an extension for luvus, mission control for your AI coding agents).

When should I use Luvus Module?

Luvus Module fits situations like: the user is building; debugging a luvus module: authoring luvus-module.toml; adding a sidebar dock; luvus Bar widget.

How do I install Luvus Module in Claude Code?

Run `npx skills add RizRiyz/luvus --skill luvus-module -a claude-code`. Or copy the skill folder (skills/luvus-module in RizRiyz/luvus) into .claude/skills/luvus-module in your project. Claude Code loads it when a task matches its description.

How do I install Luvus Module in Codex?

Run `npx skills add RizRiyz/luvus --skill luvus-module -a codex`. Or copy the skill folder (skills/luvus-module in RizRiyz/luvus) into .agents/skills/luvus-module in your project. Codex loads it when a task matches its description.

Can I use Luvus Module in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add RizRiyz/luvus --skill luvus-module -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/luvus-module, .gemini/skills/luvus-module, .github/skills/luvus-module and .opencode/skills/luvus-module in your project.

What does Luvus Module need to run?

Going by SKILL.md and its folder, Luvus Module needs credentials named LUVUS_MODULE_TOKEN. Our summary lists: A credential in LUVUS_MODULE_TOKEN.

Does Luvus Module access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Luvus Module safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Luvus Module use?

Luvus Module is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Luvus Module use?

About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Luvus Module?

Skills that share tags, products or a category with Luvus Module: Tuicr (agavra/tuicr, 3.3k stars), TUI Change Verification for Warp (warpdotdev/warp, 65k stars), Agenttrace Session Audit (luoyuctl/agenttrace, 140 stars) and Run Shunt (pleaseai/shunt, 264 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Luvus Module?

RizRiyz (a GitHub user) maintains it in RizRiyz/luvus, which has 957 GitHub stars. The repository was last updated on October 7, 2026.

Source: RizRiyz/luvus on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.