Extends Claude Code with plugins for work tracking, token usage monitoring, local LLM delegation, and UI enhancements.
Also known as v1nvn/agentic, @v1nvn/omlx, @v1nvn/readability
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 14, 2026
- License
- MIT
What is agentic MCP?
agentic extends Claude Code with plugins for work tracking, token usage monitoring, local LLM delegation, and UI enhancements.
Summary generated from the project's README
About agentic MCP server
Developers using Claude Code can expand their terminal environment with a suite of specialized plugins designed for work tracking, monitoring, and local delegation. This collection allows you to manage tasks via a todo system, monitor live token usage and GLM Coding Plan quotas, and even delegate bulk tasks like summarization or image description to a local omlx inference server.
Setup requires Claude Code and Node.js, with specific plugins like omlx needing a running server on 127.0.0.1:6659. You can install individual tools from the v1nvn/agentic marketplace, such as readability for cleaning Markdown from URLs or statusline for customizing your agent panel themes. Some tools, including rm for sending replies to a reMarkable device and md for Markdown-Viewer sharing, function as zero-token hooks that do not increase your model usage.
Beyond standard automation, the suite offers unique UI enhancements like rulings, which generates a local HTML page for decision-making, and native macOS banners via the notify module for permission prompts.
What you can do with it
- 1Delegate tasks to local modelsYou can offload bulk work like writing commit messages or docstrings to a local inference server.
- 2Track project progressManage your development workflow by tracking tasks through a dedicated todo system within your repository.
- 3Monitor token consumptionKeep an eye on your live session context and account limits through dedicated usage panes.
- 4Streamline decision makingPresent complex choices to yourself or others on a self-contained local webpage with visual options.
Written from the project's README. Every use case is checked against a quote from it.
How to install agentic MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall agentic MCP in Claude Code
$ claude mcp add agentic -- npx -y @v1nvn/omlxInstall agentic MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"agentic": {
"command": "npx",
"args": [
"-y",
"@v1nvn/omlx"
]
}
}
}Install agentic MCP in VS Code
.vscode/mcp.json
{
"servers": {
"agentic": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@v1nvn/omlx"
]
}
}
}Install agentic MCP in VS Code CLI
$ code --add-mcp '{"name":"agentic","type":"stdio","command":"npx","args":["-y","@v1nvn/omlx"]}'Install agentic MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"agentic": {
"command": "npx",
"args": [
"-y",
"@v1nvn/omlx"
]
}
}
}Install agentic MCP in Codex
$ codex mcp add agentic -- npx -y @v1nvn/omlxInstall agentic MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.agentic] command = "npx" args = ["-y", "@v1nvn/omlx"]
Install agentic MCP in Gemini CLI
$ gemini mcp add -s user agentic npx -- -y @v1nvn/omlxInstall agentic MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"agentic": {
"command": "npx",
"args": [
"-y",
"@v1nvn/omlx"
]
}
}
}Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablev1nvn/agentic is public and reachablegithub.com/v1nvn/agentic ↗Pass
- Package names this repository as its source@v1nvn/omlx, @v1nvn/readability name v1nvn/agentic as sourcenpmjs.com/package/@v1nvn/omlx ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for @v1nvn/omlx, @v1nvn/readabilitynpmjs.com/package/@v1nvn/omlx/v/0.57.0#provenance ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-14github.com/v1nvn/agentic ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from @v1nvn/omlx, @v1nvn/readabilityPass
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubagentic
Eleven Claude Code plugins, installed independently from one marketplace. The code lives
in nine npm packages (@v1nvn/*); each plugin directory is a thin manifest — most run
their package through version-pinned npx; enhansome is an HTTP MCP config pointing
at the hosted registry server, and todo and notify carry no package — todo
manifest + skills, notify a hooks module.
| Plugin | What it does | Invoke |
|---|---|---|
| readability | Read a URL to clean Markdown via the readability MCP server. The host shell fetches with curl; the server never touches the network. |
paste a URL, or "read this" |
| omlx | Delegate bulk work — commit messages, docstrings, summarization, extraction, image description — to a local omlx inference server. | the agent routes on its own, or "ask the local model" |
| enhansome | Search the enhansome registry forest — curated registries and the repos they carry — via the hosted MCP server. | the agent routes on its own, or "search the registry" |
| rm | Beam the last reply to a reMarkable as EPUB. | /rm-send |
| md | Send the last reply to a Markdown-Viewer as a #share= URL — editable or read-only. |
/md-edit, /md-view |
| zai | GLM Coding Plan quota and usage — the report as a pane. | /zai-usage |
| tokens | Live token usage — the account report as a pane, and the live session (context, flow, limits, agents) as a pane. | /tokens-usage, /tokens-top |
| statusline | Pick a theme for the status line + agent panel, or revert the setup. | /statusline:lab |
| todo | Work tracking — the rules plus eight verbs over TODO.md, progress/, references/, archive/. Every repo carries data only. |
/todo:run <plan>, or a what's-next ask |
| rulings | Put decisions the owner must make on one local HTML page — each ruling self-contained, its options pictured and lettered. | /rulings:consult, or "consult me" |
| notify | Native macOS banners on permission prompts and true-done turns — the repo, the session's own title, the message itself. | automatic — fires on its own |
rm, md, zai, tokens and notify are zero-token the mod way — a function-hook module serves a surface the model never reads.
Prerequisites
- Claude Code
- Node.js — the package-backed plugins run through
npx - A running omlx server on
127.0.0.1:6659, foromlx(omlx serve) - macOS, for
notify—osascriptposts the banners
Install
Add the marketplace, then install any subset. Each plugin stands alone.
claude plugin marketplace add v1nvn/agentic
claude plugin install rm@agentic # or: readability, omlx, enhansome, md, zai, tokens, statusline, todo, rulings, notify
Start Claude Code and run the command shown above for the plugin you installed.
In a plain shell
The four tool CLIs run outside Claude Code too:
npx -y @v1nvn/zai@0.56.0 usage # GLM Coding Plan usage report (bare prints the commands)
npx -y @v1nvn/tokens@0.56.0 usage # token usage + cache hit rate from local transcripts
npx -y @v1nvn/rm@0.56.0 # last reply → reMarkable (or a file: npx -y @v1nvn/rm@0.56.0 reply.md)
npx -y @v1nvn/md@0.56.0 # last reply → Markdown-Viewer (--view for read-only; or a file: npx -y @v1nvn/md@0.56.0 reply.md)
rm needs pandoc plus ssh/scp access to the device (REMARKABLE_HOST, default
remarkable, device dir REMARKABLE_DIR, default /home/root/books); md honors
MD_VIEWER_URL (default https://md.v1n.space) and a set MD_NO_OPEN to skip opening
the browser.
statusline
Five commands drive both surfaces. In Claude Code, /statusline:lab sketches the themes
as plain renders and offers the picker in chat — the agent writes the pick.
In a terminal outside Claude Code, the wizard is the guide:
npx -y @v1nvn/statusline@0.56.0 configure # the wizard — bare, on a TTY
npx -y @v1nvn/statusline@0.56.0 configure --theme lean # a theme write
npx -y @v1nvn/statusline@0.56.0 configure --theme lean --bar gauge # a theme plus one swap
npx -y @v1nvn/statusline@0.56.0 preview --theme rich --plain # chat-safe sketch, nothing written
npx -y @v1nvn/statusline@0.56.0 catalog # themes block, then one line per item
npx -y @v1nvn/statusline@0.56.0 restore # both keys back to their pre-lab values
npx -y @v1nvn/statusline@0.56.0 status # rows + verdict — exit 0 healthy, 1 needs action
configure is the sole writer: one run touches exactly the statusLine and
subagentStatusLine keys of ~/.claude/settings.json and deploys a launcher
(render.mjs) into the plugin data dir — the whole write footprint.
Each value is one inline shell command: node on that data-dir launcher, the
decisions as flags — --theme first, then one --<item>=<alt> per pick that
differs from the theme's own, --layout only when passed; the subagent key
adds --subagent, the one valueless flag. Both keys paint the same theme: the
subagent row renders the theme's layout filtered to the six per-task items
(state, model, effort, bar, tokens, duration), the task's label and
description leading. The launcher reads Claude Code's install record
(installed_plugins.json) and imports the newest installed plugin's
src/render/entry.ts, so a plugin update repaints with no rerun. Raw:
node "$HOME/.claude/plugins/data/statusline-agentic/render.mjs" --theme=lean --bar=gauge || true
node "$HOME/.claude/plugins/data/statusline-agentic/render.mjs" --subagent --theme=lean || true
The layout — brace clusters of item ids — rides as --layout only when
passed; the theme's layout holds otherwise. With flags, configure is
strict — --theme <name> (quiet, classic, lean, rich, custom) is the base
design and item flags override it; classic names the shipped defaults.
The theme resolves at paint,
and preview renders a candidate through the same resolution without
writing — --plain strips the color escapes so the sketch survives chat. A
foreign settings key is refused unless --force. The first takeover saves
the pre-lab key values to backup.json; restore splices them back
byte-exact — keys absent before the lab are removed — then deletes the lab
data. The theme name rides the key — status and catalog read it from
there, and swaps keep the name. status checks the install: node, the
renderer the install record resolves, both keys, config drift, the theme,
backup, captures — one row per fact plus a verdict, every action row naming
its fix. /statusline:lab inside a session runs the same commands.
Repo and machine:
repo
packages/statusline/ the CLI and the renderer — pure TS, zero bash
src/ test/ src/ holds the CLI and src/render/ the renderer entries
assets/payloads/ p1–p4.json preview fixtures, main surface
assets/ticks/ multi.json preview fixtures, agent panel
SKILL.md the /statusline:lab skill — model-taught entry point
machine, after `claude plugin install statusline@agentic`
~/.claude/plugins/cache/agentic/statusline/<version>/ the installed plugin — node_modules/ installed
from its package-lock.json; src/render/entry.ts paints
~/.claude/plugins/data/statusline-agentic/
render.mjs the launcher — deployed by configure, spawned by both keys
backup.json pre-lab key values — first takeover wins
captures/main.json captures/tick.json every paint's stdin, teed by the renderer; feeds previews
~/.claude/settings.json statusLine + subagentStatusLine → the inline commands
Install: claude plugin marketplace add v1nvn/agentic, then
claude plugin install statusline@agentic, then /statusline:lab in a session — or
npx -y @v1nvn/statusline@0.56.0 configure in a terminal, where the wizard
previews both surfaces at 80/120/200 columns and saves.
Uninstall runs npx -y @v1nvn/statusline@0.56.0 restore first, then uninstalls
the plugin: a plain uninstall deletes the data dir — backup.json and the
resolver go with it — and the keys left behind point node at a file that is
gone: a blank line at the next paint.
Layout
A plugin's root is its package home; there is no plugins/ directory — all
ten plugins root at packages/<name>/ itself. Eight homes publish
npm code.
.claude-plugin/marketplace.json Claude marketplace manifest; sources point into the package homes
packages/ one yarn workspace — every plugin's home
readability/ omlx/ the two MCP servers (@v1nvn/readability, @v1nvn/omlx) — the plugin root itself:
.claude-plugin/ + .mcp.json (pinned npx) + dev.mcp.json (dev wiring) (+ skills/)
core/ @v1nvn/agentic-core — last-reply + CLI plumbing + the drawing kit,
imported by every process-side surface; the island never imports it
rm/ md/ zai/ the tool CLIs (rm-send, md-send, zai-usage) + their mods — the plugin root itself:
.claude-plugin/ + hooks/register.ts(x) + hooks/support.ts (the island glue)
+ tests/ + package-lock.json (core pin Claude Code installs)
zai also types/ (state contract)
tokens/ tokens-report CLI + the tokens mod — the plugin root itself:
.claude-plugin/ + hooks/register.tsx + hooks/support.ts + tests/ + types/
(state contract); src/ holds the CLI (index, cli, scan)
and the island's aggregate/format/top/text.ts
(the island's own formatting slice — the engine's loader
keeps the island off npm, so it cannot import core's kit)
statusline/ the configure CLI + renderer, pure TS (@v1nvn/statusline) — the plugin root itself:
.claude-plugin/ + SKILL.md (see statusline above)
+ src/render/launcher.mjs (the data-dir deploy, zero deps)
rulings/ the decisions-page builder, pure TS (@v1nvn/rulings) — the plugin root itself:
.claude-plugin/ + SKILL.md (see rulings above) + README.md
enhansome/ todo/ package-less homes — the plugin root itself:
.claude-plugin/ + .mcp.json, todo: .claude-plugin/ + skills/ + README.md
types/claude-code.d.ts vendored mod API declarations, engine-written per version
tsconfig.mods.json type-checks every mod package against the vendored types
Versions ride one lockstep train: .claude-plugin/marketplace.json is the source, and
set-version.mjs mirrors it into every package, plugin manifest, core dependency pin,
lockfile, and npx pin. Nothing is built: node ≥23.6 runs the .ts sources, and every
published package ships src.
agentic MCP questions
How do I add agentic MCP to Claude Code?
Run claude mcp add agentic -- npx -y @v1nvn/omlx in your terminal. Add --scope user to make it available in every project.
How do I add agentic MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Can I use the ommlx plugin with a local model?
Yes, the omlx plugin delegates tasks like commit messages and summarization to a local omlx inference server.
Does the readability plugin access the internet?
No, the host shell fetches the URL using curl, so the server itself never touches the network.
What are the requirements for the notify plugin?
The notify plugin requires macOS to use osascript for posting native banners.