claude-code-mods / site
llms.txt485 starsChanged 43 days agoMITView on GitHub
Small plugins for Claude Code built on its function hooks: live lines above the prompt, guards for risky commands, panes, games, and themes for the Claude Code Desktop app. Open source, MIT licensed. Install only the ones you want. Install: npx claude-code-mods@latest (tick the mods you want), or claude plugin marketplace add hamzafer/claude-code-mods then claude plugin install <mod>@claude-code-mods.
In this repositoryOne other file it gives its agents.
- CLAUDE.mdCLAUDE.md
The file
Files
# Claude Code mods and themes > Small plugins for Claude Code built on its function hooks: live lines above the prompt, guards for risky commands, panes, games, and themes for the Claude Code Desktop app. Open source, MIT licensed. Install only the ones you want. Install: `npx claude-code-mods@latest` (tick the mods you want), or `claude plugin marketplace add hamzafer/claude-code-mods` then `claude plugin install <mod>@claude-code-mods`. - [All mods and themes](https://hamzafer.github.io/claude-code-mods/) - [Source on GitHub](https://github.com/hamzafer/claude-code-mods) - [Notes per mod](https://github.com/hamzafer/claude-code-mods/blob/main/docs/mods.md) ## Themes - [gotham-night](https://hamzafer.github.io/claude-code-mods/mods/gotham-night/): A Gotham theme for the Claude Code Desktop app: searchlights sweep while Claude works, and when it needs you the signal lights with a burst of bats. Desktop app only. ## See what's happening - [agent-radar](https://hamzafer.github.io/claude-code-mods/mods/agent-radar/): One live line above the prompt per running subagent or background shell: its model, time, tool count and what it's doing. /radar shows every agent and its messages. - [context-bar](https://hamzafer.github.io/claude-code-mods/mods/context-bar/): Your context window as a stacked bar above the prompt, a color per category, with token counts and the compaction point. /context-bar shows or hides it. - [browser-lanes](https://hamzafer.github.io/claude-code-mods/mods/browser-lanes/): Shows if this session has a Playwright browser and who holds it. /browser clean closes leftover browsers. A subagent that wants the browser waits until the one using it is done. - [md-preview](https://hamzafer.github.io/claude-code-mods/mods/md-preview/): Shows the Markdown files Claude edits, rendered like GitHub, in a pane next to the chat. Before and after side by side. /md opens it. - [heatmap](https://hamzafer.github.io/claude-code-mods/mods/heatmap/): A GitHub-style grid of your Claude Code time in a /heatmap pane, with streaks, peaks and top projects. - [mission-control](https://hamzafer.github.io/claude-code-mods/mods/mission-control/): /mission opens a live map of the main agent, its subagents and every tool call, plus a code map of the files they touch. - [next-steps](https://hamzafer.github.io/claude-code-mods/mods/next-steps/): After each turn, 2 or 3 likely next prompts above the prompt. Press 1, 2 or 3 in an empty prompt to draft one, 0 to dismiss. - [prayer-times](https://hamzafer.github.io/claude-code-mods/mods/prayer-times/): The current prayer and how long is left, the next prayer, and zawal, above the prompt. Computed on your computer from your location; nothing is sent anywhere. - [replay-theater](https://hamzafer.github.io/claude-code-mods/mods/replay-theater/): Step through the last turn's file edits, one diff at a time. - [review-watch](https://hamzafer.github.io/claude-code-mods/mods/review-watch/): A live line above the prompt for each running code review: Codex or a review subagent, its model, what it reviews, time, and Codex's latest output. A toast with the findings when it ends. - [token-weather](https://hamzafer.github.io/claude-code-mods/mods/token-weather/): A live forecast of the context window, with a prompt-cache countdown, drawn above the prompt. - [cache-clock](https://hamzafer.github.io/claude-code-mods/mods/cache-clock/): A prompt-cache line under your status line, from Claude Code's own cache figures: time left while warm, hit rate and misses, and how many tokens the next message re-caches once cold. /cache-clock setup adds it. - [usage-meter](https://hamzafer.github.io/claude-code-mods/mods/usage-meter/): Your plan's 5-hour and 7-day usage as small bars above the prompt, with the reset countdown and the session's cost. - [where-am-i](https://hamzafer.github.io/claude-code-mods/mods/where-am-i/): A live recap above the prompt: goal, doing now, waiting on you, next. /where for a longer one. - [openai-balance](https://hamzafer.github.io/claude-code-mods/mods/openai-balance/): Your OpenAI API credit above the prompt: an estimated balance with a gauge, today's spend, where the money mostly went, and the last call. /openai-balance shows the breakdown. - [openrouter-balance](https://hamzafer.github.io/claude-code-mods/mods/openrouter-balance/): Your OpenRouter credit above the prompt: the balance with a gauge, today's spend and where the money mostly went. /openrouter-balance shows the breakdown. ## Guard your repo - [blast-radius](https://hamzafer.github.io/claude-code-mods/mods/blast-radius/): Holds risky Bash commands and shows what they would change before they run. - [secret-guard](https://hamzafer.github.io/claude-code-mods/mods/secret-guard/): Keeps API keys and tokens out of Claude's context, your files and your commits: hides them in tool output, and asks before a write, commit or push adds one. ## Spend less - [switchboard](https://hamzafer.github.io/claude-code-mods/mods/switchboard/): Picks the model for each subagent that names none, with OpenAI's Decisions API or Jev, from its short label only. One line per spawn above the prompt; /route shows each pick and what each subagent cost. ## My setup (fork and adapt) - [glance](https://hamzafer.github.io/claude-code-mods/mods/glance/): One line above the prompt with what needs you: next meeting, PRs, Linear issues and Slack DMs. /glance lists them all. - [merge-gate](https://hamzafer.github.io/claude-code-mods/mods/merge-gate/): Holds `gh pr merge` until CI passes and one Codex review (OpenAI's luna model) has run. A PR line above the prompt, and /gate shows the PR's status. - [rulebook-guard](https://hamzafer.github.io/claude-code-mods/mods/rulebook-guard/): Writing and git rules: replaces em dashes in prose, and asks before git commit --amend, an unformatted push, or personal info in notes and commits. - [session-saver](https://hamzafer.github.io/claude-code-mods/mods/session-saver/): Names untitled sessions through unpause. /park saves where you left off, and a resumed session shows it. ## For fun - [now-playing](https://hamzafer.github.io/claude-code-mods/mods/now-playing/): What Spotify is playing, one line above the prompt: track, progress and the lyric being sung, with ⏮ ⏸ ⏭ buttons. /music controls it too. macOS. - [reels](https://hamzafer.github.io/claude-code-mods/mods/reels/): YouTube Shorts in a terminal pane: plays while Claude works, pauses when Claude is done. - [snake](https://hamzafer.github.io/claude-code-mods/mods/snake/): Snake in a pane while Claude works, paused when it's done. Opt-in, so nothing opens until /snake.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

