Claude Code mod
modes
How a session works with you and with its subagents. Two session modes, each [on|off|status], answered with no model call, Claude told once at each switch and reminded by one line on each prompt while on, a label in the prompt footer: /orchestrate hands parts to subagents on another model (haiku · sonnet · opus); /ask answers and changes nothing, refusing Edit, Write and NotebookEdit while on. /modes:interview asks you rounds of AskUserQuestion until the direction is clear. /modes:align stops work in progress: it plays back what was built, names where it drifted from what you asked, and asks before any more changes. A Claude Mod: needs CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1.
Install
/plugin marketplace add proxify-dev/agentic-kit
/plugin install modes@agentic-kitMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L1Reads: reads files, reads mod state, persists state
- Sees
- every prompt, compaction, every tool call
- Draws in
SessionMode- Hooks
session.startcommand.runprompt.submitsession.compactsession.endui.rendertool.call
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
- proxify-dev/agentic-kit
- Folder
plugins/modes- Marketplace
agentic-kit- Author
- teocns
- Type
- Workflow mods
- License
- MIT
- Last updated
- 13 November 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is modes?
How a session works with you and with its subagents. Two session modes, each [on|off|status], answered with no model call, Claude told once at each switch and reminded by one line on each prompt while on, a label in the prompt footer: /orchestrate hands parts to subagents on another model (haiku · sonnet · opus); /ask answers and changes nothing, refusing Edit, Write and NotebookEdit while on. /modes:interview asks you rounds of AskUserQuestion until the direction is clear. /modes:align stops work in progress: it plays back what was built, names where it drifted from what you asked, and asks before any more changes. A Claude Mod: needs CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1. It is a mod for Claude Code, from proxify-dev/agentic-kit on GitHub.
What can the modes mod access?
Its widest reach is "reads" (reads files, reads mod state, persists state). It sees every prompt, compaction, every tool call. It draws in SessionMode. Like any mod, it runs with your permissions.
How do I install modes?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add proxify-dev/agentic-kit and then /plugin install modes@agentic-kit.
Is modes popular?
proxify-dev/agentic-kit has 7 GitHub stars and 0 forks, and is included in 1 curated Claude Code list. It was last updated on 13 November 2026.
More workflow mods
jev-router
7satviksinha/jev-model-router
Routes each turn to a Claude model chosen by TypeSafe's Jev, asked through the Vercel AI Gateway.
office
7charlie947/mod-maker
A pixel-art office in a local web page: every Claude session gets a desk, walks to the filing cabinet when it reads, types when it edits, flies paper planes when it messages, and shows a live Done-by clock
dispatch-gate
7wdsewdser-bit/claude-code-mods
A soft gate on the main session: reminds it, then refuses once per stretch, to hand work to a subagent; and refuses one Claude subagent per hour past three.
plain-cut
7PiPercentHuman/agentjournal
Answers compaction with plain code: the first message and the last few steps, nothing summarised.
aot-evals
7Mahalanobis-Systems/aot-evals
Part of AOT, the Agent Optimization Toolkit, a Mahal Systems offering. Build and iterate the evals for a production agent in three phases: Assess (a discovery report), Build (the agent wired up, cases from real runs, a baseline) and Judge (a local grader application where the people who know what good looks like label runs and the suite is held to them). A stdlib CLI records every attempt, and a fixed report.json schema renders into a local HTML diagnostic.
ponder
7Quinnod345/ponder
Convergent deliberation loop for coding agents - multi-pass, coverage-gated, append-only ledger review and planning.
Browse the most popular Claude Code mods, all workflow mods, or the skills and MCP server directories.