Claude Code mod
agent-graph
Define agents with skills and context on a drag-and-drop graph, connect them, and run them locally or as Claude Managed Agents.
Install
git clone https://github.com/CalvoSeko/claude-factory-mod.git
claude --plugin-dir ./claude-factory-mod/agent-graphThe repo has no marketplace file, so load the plugin folder directly with --plugin-dir.
What it can access
- Reach
- L3Network: network, runs processes, writes files, drives Claude, writes the prompt box, reads files, reads env vars, reads mod state, requests an Anthropic credential handle, persists state, draws
- Sees
- every tool call, Agent calls, mcp__agent-graph__read_graph calls, mcp__agent-graph__edit_graph calls, subagent spawns, classic hooks
- Draws in
AbovePromptPane- Hooks
session.startcommand.runui.closeui.renderui.messagetool.callagent.spawnturn.stepclassic.StopFailureturn.complete
From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.
How Claude Code mods work
- A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
- It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
- Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
- Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Details
- Repository
- CalvoSeko/claude-factory-mod
- Folder
agent-graph- License
- MIT
- Last updated
- 12 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is agent-graph?
Define agents with skills and context on a drag-and-drop graph, connect them, and run them locally or as Claude Managed Agents. It is a mod for Claude Code, from CalvoSeko/claude-factory-mod on GitHub.
What can the agent-graph mod access?
Its widest reach is "network" (network, runs processes, writes files, drives Claude, writes the prompt box, reads files, reads env vars, reads mod state, requests an Anthropic credential handle, persists state, draws). It sees every tool call, Agent calls, mcp__agent-graph__read_graph calls, mcp__agent-graph__edit_graph calls, subagent spawns, classic hooks. It draws in AbovePrompt, Pane. Like any mod, it runs with your permissions.
How do I install agent-graph?
Clone CalvoSeko/claude-factory-mod and start Claude Code with --plugin-dir pointing at the mod's folder (agent-graph).
Is agent-graph popular?
CalvoSeko/claude-factory-mod has 4 GitHub stars and 0 forks, and is included in 1 curated Claude Code list. It was last updated on 12 October 2026.
More context & usage mods
wavy-usage
5BatuhanCakmakk/wavy-usage
Liquid-filled rings above the Claude Code prompt for the 5-hour and 7-day limit windows, context fill and prompt-cache lifetime, a fighter jet that shows the model's effort, and a pane of recent turns, their cost, their share of the 5-hour window and what filled it.
am-context-bar
4romnycristopher/claude-am-mods
A context card above the prompt with a collapsed and an expanded view: zone-coloured token count (dumb zone from 50% or 250k tokens, compact or clear from 70% or 400k), context bar with the dumb zone, where to compact or clear and auto-compact marked, breakdown by category, limits, model, thinking, compactions, git, and progress through a plan's phases. Three layouts. /am-context-bar on | off | layout v1|v2|v3 | plan on|off.
vitals
5naicud/cc-vitals
A light, framed live dashboard above the prompt, in the terminal and in the desktop app: model and effort, context and account-wide plan-limit meters (5-hour, weekly, per model, usage credits), cost and burn rate, tokens and cache per turn and session, auto-compaction, live tools, background shells and every subagent with its model and effort, plus weekly and monthly usage and the account's plan limits by product. Two columns on wide terminals, sized to the rows it has, never scrolling. Requires ccusage (npm i -g ccusage) for the usage section. /vitals-low, /vitals-medium and /vitals-high set the detail level; /vitals pane full view, /vitals report usage report.
clawd-hud-spike
4soulrocha/Claude-code-hero-journey
Spike da HUD RPG: sondas no app real para os itens A VALIDAR (sem gastar tokens)
usage-hud
5lucassimzq/claude-usage-mod
A pixel Clawd above your prompt whose mood follows your context, session and weekly usage
cost-ledger
4FynnXland/fynn-mods
Cost ledger across all chats: after every answer it records the chat cost (as /cost), tokens per model and model calls made by other mods. /ledger shows today, 7 and 30 days, total, history by model (days or weeks), projects and the most expensive chats; /ledger limits shows the API value in the current 5-hour and weekly window and in your subscription month, plus an estimate of the usage outside the ledger (claude.ai, phone); /ledger sync <folder> merges your devices through a shared folder (amounts only: no paths, projects or chat titles); /ledger help lists all commands, the current state and your settings. Observer only, no model calls.
Browse the most popular Claude Code mods, all context & usage mods, or the skills and MCP server directories.