awesome-claude-mods

One live line per running subagent above the prompt: time, tool count, what it's doing

Pin one goal for the session: it sits above the prompt with a timer, and Claude is told to stay on it and flag unrelated work instead of drifting.

A hidden git snapshot at the start of every turn; /undo-turn rolls back what Claude did

A seatbelt for YOLO mode: blocks catastrophic shell commands (rm -rf ~, mkfs, dd to a disk, fork bombs) and asks before risky ones (force-push, reset --hard, DROP TABLE, curl | sh), even with permissions bypassed.

Holds risky shell commands and shows what they'd change, with Proceed and Cancel buttons

Failing tests spawn a pixel boss; every fix lands a hit, and zero failures is a KO

A tiny ASCII pet that lives above your prompt, reacts to everything Claude does, and levels up as you ship.

A live cost odometer above the prompt, with a burning fuse and threshold alerts

A pixel-art cat walks above the spinner, plays with yarn and sits to think with Claude

Snake, Tetris, 2048, Minesweeper, Pong and more above the prompt, plus a pet that grows

Live context, limits, cost, subagents, tool errors and diffs, plus a risky-command guard

Build any repo on AWS CodeBuild from Claude Code: pick an AWS profile, press Build. Sets itself up, generates the buildspec, streams logs into a pane, and lets Claude fix failures.

Asks before Claude edits a file another open chat changed in the last 30 minutes

Explains a shell command in one plain-English line, with its risk, right where you approve it, so you know what you're saying yes to.

Always know what a session costs: live $ / context / rate-limit status line, the cost of every turn, context warnings, and an optional budget that asks before spending more.

Pleasant sounds when a long turn ends or a permission prompt waits, in four themes

Go make coffee: a desktop notification, a chime, and optionally a phone push when a long Claude turn finishes or Claude is waiting on you.

Keeps Claude's file edits inside the project: refuses writes outside it (symlinks resolved), never lets a tool touch .git internals, and asks before it changes lockfiles, CI workflows, migrations or secrets.

Every file Claude changed this session, at a glance: a one-line band above the prompt, /touched for a +/- table, and a pane that drops @file references into your prompt.

Git status at a glance: branch, ahead/behind and changes on the status line, kept fresh as Claude edits, with a heads-up when the branch changes or a turn makes commits.

Clickable safety rules: block rm -rf, force-push, secret files, sudo; lock to the project

Compacts once after 50 idle minutes, while the 1-hour prompt cache is still warm

Thumbnails of the images you paste, above the prompt, instead of bare [Image #1] tags

Defuses prompt injection in tool output: strips invisible Unicode that hides text from you but not from the model, and flags web pages, files and command output that carry instructions aimed at Claude.

Minesweeper in a pane while Claude works, with a best time and a face that watches Claude

Scores each prompt for blast radius; cheap turns go to GLM/Kimi, risky ones stay on Claude

Stops data exfiltration and surprise network calls: checks every curl, wget, ssh, scp, git push and WebFetch against allow and deny lists, and asks before data goes to a host you haven't approved.

Suggests three next prompts above the input after each turn; press 1, 2 or 3 to draft one

Redacts secrets and PII from every stored row; real values return only inside file writes

Step through the file edits Claude made last turn, one diff at a time, in a pane

Skips Claude's repeat reads of files that haven't changed since it last read them

Click or press a digit to put a reply's `! command` suggestion into your prompt

Keeps secrets out of Claude's context: API keys, tokens, private keys and passwords in tool output are replaced with [REDACTED:kind] before the model or the transcript ever sees them.

Masks API keys and high-entropy tokens in tool results before the model reads them

Stops Claude from installing hallucinated or typosquatted packages: every npm, pip, uv, poetry, cargo and gem install is checked against its registry first. Packages that don't exist are blocked; brand-new, barely used or lookalike packages ask you first.

Snake in a pane while Claude works, paused the moment it's done

Reusable prompts one command away: /snip review drops your saved review prompt into the prompt box, with {{selection}}, {{branch}}, {{date}} and {{args}} filled in.

Themed spinner words: Claude is 'Plundering…' then 'Plundered for 1m 3s'. Ten packs (pirate, Shakespeare, corporate, wizard, chef, space, noir, Gen Z, zen, retro) or your own words.

Your standup, written for you: journals every Claude turn (prompt, files, commits) and turns yesterday and today into Yesterday / Today / Blockers with /standup.

Your test suite's heartbeat: every test run Claude makes shows up in the status line (🧪 ✅ 44/44 passing · 2m ago), with a toast when tests go red or green again, and /tests for history, a pass-rate sparkline and likely flakes.

A one-line TL;DR under every long answer, written by a small fast model, so you can skim a wall of text in two seconds.

A weather forecast for your context window above the prompt, with a chart of recent turns

Mission control for what Claude is doing: a live pane of every tool call with status, arguments, duration and failures, plus /radar summary.

Your plan's 5-hour and 7-day limits as small bars above the prompt, with reset countdowns

A box above the prompt that says what Claude is doing now, and expands to what it did

A live recap above the prompt: the goal, what Claude is doing, what waits on you, next

Spotify Wrapped for your Claude Code life: prompts, tool calls, lines written, streaks, your coding persona, and a share card you can copy.