waraxe-claude-mods

Colorful, themeable rendering for Claude Code replies: tables, headings, code, numbers, paths and links.

2 skills

Skins for Claude Code: tool rows that open onto their input and answer, highlighted code, diff, table, math, Mermaid and shell cards, links, folding, a usage band, a calm mode and fifteen themes. /skin swaps them live.

1 skill

Read-only side chat: /aside opens a pane beside the transcript where you ask about the session so far; answers come from a tool-less fork of the session's own transcript and nothing is written back into the main thread.

After a reply, lists the small guesses Claude made. Mark each Right or Wrong, and send the wrong ones back to Claude

Holds risky shell commands (rm -rf, git reset --hard, git clean, force push, migrations) and shows what they would change, with Proceed and Cancel buttons.

A Claude Code mod that keeps the one-hour prompt cache warm during breaks and asks before a cold send whether to continue here or start a new chat. Warming uses model requests and costs tokens. Requires Claude Code 2.1.287+.

Asks before Edit or Write changes a file that another chat edited in the last 30 minutes, with Proceed and Cancel

Turns what you teach Claude into project notes, catches its usual slips, keeps the cache warm while you're away, and picks long sessions back up

One small Claude Code challenge each day in a /challenge pane, with Coach me, Done and Skip buttons and a streak

When Claude ends a reply with a question, explains the choice in a side pane and lets you explore any option, or your own, in a real forked session

Copies the files an rm is about to delete into a backup folder first, so /undo-delete can put the newest deletion back

When Claude asks you to choose a design style, opens a page in your browser that shows each option as a styled card, then shows the normal question

A side pane that pins every diagram Claude draws, keeps a live map of the work, and lets you go into boxes and change them

Tidies long messages that look dictated, then asks whether to send the cleaned version or the text as typed

Picks the reasoning effort for each message you send, for that message only, from its words, and never switches the model

After a long turn, one Haiku call flags up to two things you might miss, in a band above the prompt. Off until /heads-up on

Claude assigns you the tasks only you can do. They wait in a My tasks pane, counted under the prompt, until you answer or reject them, so nothing Claude needs from you gets lost in the chat.

/mission opens a live map of the main agent, its subagents and every tool call, plus a code map of the files they touch.

Mod doctor audits your installed mods with the plugin validator and flags failed checks, shared tool.call hooks and duplicate names

Picks haiku, sonnet or opus for each subagent Claude starts without naming a model, from one small Haiku call, and never changes the main chat's model

/mods: browse, search and install community Claude Code mods from a pane, with what each one can access shown before you install

Reads the last 240 characters of each finished reply aloud with macOS say, off by default and switched with /narrator on and /narrator off

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.

While on, rewrites each long reply in plain language with a short Next steps list, in a side pane, and leaves Claude's reply unchanged

Bounces vague prompts before Claude sees them, and suggests the project's own term

A prompt typed while Claude is working is held in a stack above the prompt instead of landing in the running turn, and sent once the turn ends. Reorder the stack, edit a row in place, send one first, remove one, flush the lot. Needs function hooks (early access) and an interactive terminal.

/rec before you record: masks keys, personal details, and business figures on screen and keeps private files closed (/rec strict, /rec off, /rec config)

claude-reflect as a Claude Code mod: a model check on each short prompt finds reusable corrections (any language); a band above the prompt saves them to CLAUDE.md on one press

Replay Theater: step through the file edits Claude made in the last turn, one diff at a time.

A /heatmap pane that counts this repository's tracked files by top-level folder and kind, from git ls-files, as rows of colored bars

Progress bar above the prompt for /savvy-flow, plus an agents panel (/agents-info): running, finished and planned subagents with model, task progress, context, cost and time.

Claude can use a secret without seeing it: a masked box saves keys to .env and gives Claude a placeholder, every key a tool prints comes back as a placeholder, and committing .env is refused

Band above the prompt: turn number, output speed, turn and session cost, prompt cache countdown and context fill; notifies before the cache expires.

Snake in a pane while Claude works, paused when it's done. Opt-in, so nothing opens until /snake.

Asks Proceed or Cancel, with a short checklist, before a command or MCP tool that costs money or publishes runs

Speaks two alerts with Mac, OpenAI or ElevenLabs voices: when work ends, the project, the thread and what was done; when Claude asks you something, a chime, the question and the recommended option.

One status banner above the prompt: plan usage, the session's turn, speed, cost, cache countdown with a Keep warm button and context fill, a goal and next-step summary, and a heads-up after long turns.

A browser running directly inside claude code. Preview websites, view HTML documents, and let your agent control the built in browser.

A small text pet in the band above the prompt that eats the files Claude reads, with /pet on, /pet off and /pet name

Keeps the failing tests from your last test run in a Failing tests pane, with Fix to send them to Claude and Dismiss to clear them

Time-lapse: records your session's prompts, tool calls and turn times, and replays them as an animated HTML page

Today's Report: totals your Claude Code tasks, the time they would have taken you, and tokens by day, week, month and year, from your session logs

Your plan's 5-hour and 7-day usage as small bars above the prompt, with the reset countdown and the session's cost.

A live recap above the prompt: goal, doing now, waiting on you, next. /where for a longer one.