Claude Code mod
agent-warehouse
A vector warehouse where the session's agents are little robots: they walk in when spawned, go to the web, files, desk, bench or mail station as they work, cheer and walk out when done (or cry, when they fail). Point at or click a robot for what it is doing.
Install
/plugin marketplace add shaheershoaib/agent-warehouse
/plugin install agent-warehouse@agent-warehouseMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L2Writes or runs: drives Claude, reads mod state, draws
- Sees
- subagent spawns, every tool call
- Draws in
AbovePromptPane- Hooks
session.startcommand.runagent.spawntool.callturn.completesession.sendui.render
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
- shaheershoaib/agent-warehouse
- Folder
.- Marketplace
agent-warehouse- Author
- Shaheer Shoaib
- License
- Apache-2.0
- Last updated
- 10 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is agent-warehouse?
A vector warehouse where the session's agents are little robots: they walk in when spawned, go to the web, files, desk, bench or mail station as they work, cheer and walk out when done (or cry, when they fail). Point at or click a robot for what it is doing. It is a mod for Claude Code, from shaheershoaib/agent-warehouse on GitHub.
What can the agent-warehouse mod access?
Its widest reach is "writes or runs" (drives Claude, reads mod state, draws). It sees subagent spawns, every tool call. It draws in AbovePrompt, Pane. Like any mod, it runs with your permissions.
How do I install agent-warehouse?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add shaheershoaib/agent-warehouse and then /plugin install agent-warehouse@agent-warehouse.
Is agent-warehouse popular?
shaheershoaib/agent-warehouse has 1 GitHub stars and 0 forks, and is included in 1 curated Claude Code list. It was last updated on 10 October 2026.
More pane & dashboard mods
agent-skills-mods
1lucksy/agent-skills-mods
See your agent-skills spec, plan and tasks inside Claude Code: a task board, a progress band above the prompt, an ETA range, sprints and a local dashboard, all read from the markdown you already have.
agent-watch
1TheoGegout/claude-agent-watch
Agent Watch: one pane for every Claude Code session on your machine and its subagents, running, waiting for you, or idle
agent-cats
1anthonyzng/agent-cats
A dashboard of the session's agents as coloured cats: their tasks, skills and run time, their questions answered in place with a meow, and the skills each task uses
agentille
1hasuwini77/agentille
One typed command runs the work: /agt plans, builds and reviews with the right model per step, steps aside on small tasks, and ends on one short card. Also typed-only: /storm picks what to build next, /agt-spawn and "open two sessions" open panes beside you, /agentille-init writes your voice profile, /agentille-project and /agentille-claude-md tend a CLAUDE.md; the /agt-* commands read or tidy. A guard holds every run below its integration ceiling. No profile or config needed; every surface has a switch.
agent-board
1Oualid0/claude-mods
A row above the prompt for the subagents Claude starts: running and done per model, a token bar, and a working pixel crew
agents-info
1pazimor/marketplace
Agents info Mod (Claude Code 2.1.287, Mods API in early access): starting agent, timeline of agents per prompt (new, resumed, forked), resolved model and effort of each, tokens per agent × model × effort, 5 h / 7 day limits with forecast, alerts. Read-only: alters and blocks nothing.
Browse the most popular Claude Code mods, all pane & dashboard mods, or the skills and MCP server directories.