Prompt

Paints the draft you are typing white on orange. Pair it with the Orange Dark theme to color your sent messages.

🔔 Closes the PR loop: watches a PR until CI and agent reviews are green, and weighs review comments before acting on them.

😤 Remembers your corrections: offers to hold a lasting preference, reminds Claude of it every session, and fixes commands it can swap safely.

📺 Catches you up: a recap when you come back to a session, a morning digest of yesterday, and /standup.

🧾 Checks claims and leftovers: notes when Claude says done with nothing run since its last edit, and debug crumbs it added.

📸 Shows you the pictures: a thumbnail the moment you paste one, and /gallery of every image you and Claude passed around this session.

🔫 Shrinks what the model reads: big pastes and long command output, with the full original saved outside the project.

🎾 Tells you when Claude needs you: one line with the question it ended on, and its answers as buttons.

🔔 Closes the PR loop: watches a PR until CI and agent reviews are green, and weighs review comments before acting on them.

😤 Remembers your corrections: offers to hold a lasting preference, reminds Claude of it every session, and fixes commands it can swap safely.

📺 Catches you up: a recap when you come back to a session, a morning digest of yesterday, and /standup.

🧾 Checks claims and leftovers: notes when Claude says done with nothing run since its last edit, and debug crumbs it added.

📸 Shows you the pictures: a thumbnail the moment you paste one, and /gallery of every image you and Claude passed around this session.

🔫 Shrinks what the model reads: big pastes and long command output, with the full original saved outside the project.

🎾 Tells you when Claude needs you: one line with the question it ended on, and its answers as buttons.

A short to-do list pinned above the prompt, ticked off with one click.

A note above the prompt that stays until you clear it.

Plain-language replies when you ask for them. Say "layman", "I'm lost" or "explain again" and the next reply uses everyday words, one idea, one real example. Ask twice and plain mode stays on for the session; /layman on|off switches it by hand.

Paints Markdown onto Claude Code's prompt box as you type: fenced code becomes a syntax-highlighted card (even before you close the fence), and inline code, bold, italic, lists, task lists, quotes, tables, links and headings are styled. Paint only, your text is never changed.

Live plan progress bars above the Claude Code prompt: stages, steps, a pixel fill and soft sounds for decision, error and done

Zsemle, a pixel-art companion above the prompt (golden retriever, cat, slime, paperclip): watches every usage limit (50/75/90% warnings, pace forecast, resets, API errors, automatic model switch and compaction, cost), stops work at 95%, guards file writes and cheers long turns. English and Hungarian, terminal and desktop.

One command — /wf ($wf under Codex), the single SDLC entry point for Claude Code and Codex from one plugin tree — driving a 10-stage lifecycle from intake through retro, with per-slice artifacts, runtime-truth verification, and PO-confirmed stack fingerprinting. 24 keys: the stages, standalone/drivers (design, brainstorm, probe, simplify, auto, yolo, campaign), the task minimal lifecycle...

Routes each turn and subagent to a model tier and reasoning effort using a classifier behind any server that speaks POST /v1/classify (model-router-api on Cloudflare Workers AI today), falling back to the engine's built-in classifier.

Native TaskLedger summary and interactive task board for Claude Code.