Prompt
353 mods. Bands above the prompt and tools that rewrite what you send.
- jev-skill-suggestion 0.1.0 Keeps the skill listing out of the context window and lets TypeSafe's Jev, a System One decision model, pick at most one skill per prompt from the skills' descriptions, the way TypeSafe's skill-suggestion cookbook does: one request ranks every skill and asks whether the prompt needs a skill at al... 0
- dkod 0.3.0 mod + skill Build and deploy apps through your company's DKOD: policy, templates, Deploy questions and Deliver, with a DKOD band above the prompt and the DKOD rules on every command and file write. 0
- on-me 0.3.0 Band: what waits on you and what Claude is doing now 0
- weather 0.1.2 Current weather (condition and temperature) for a place you set, in the prompt footer, refreshed every 15 minutes. 0
- mize-coworker 0.6.0 Claude as a small coworker in the terminal: an orange pixel-art Claude, two rows tall, in 132 frames. While a turn runs he sits beside the spinner in a scene for every spinner word (a thought bubble, a pen on a notepad, a book, a magnifying glass over text or over a globe, a laptop, a terminal, h... 0
- dojo-fx 0.1.0 Optional visuals for the dojo crew: themed spinners, turn-end flair, a live crew band, deploy/return toasts, and a model guard that keeps dojo agents on their own model. 0
- spiral-stop 0.1.0 Stops fix loops: when the same error returns after 3 fix attempts, tells you and Claude to stop and rethink 0
- output-ladder 0.1.0 Re-explain the last answer as ASD-STE100 text, a diagram, an HTML page or an explainer video, and score answers for STE style. 0
- effort-router 0.4.1 Picks the reasoning effort for each turn of the main conversation with a System One classifier (hosted Jev or a compatible service) and shows the level on the spinner and on the line that closes the turn. In shadow mode it shows and logs its pick and sends the session's effort; in enforce mode it... 0
- charts 0.2.0 Dessine les blocs vega-lite des réponses et des aperçus AskUserQuestion en vraies images (PNG dans Ghostty, SVG sur le desktop). 0
- review-cycle 0.27.0 mod + skill Automated multi-agent code review cycle. Spawns reviewers in parallel (plus Codex when available), applies fixes per CLAUDE.md policy, admits a commit only when a reviewer saw exactly what it records, and asks before a push, pull request, merge or release you did not request, unless you let it go... 0
- bouncer 0.1.0 Paste a link with a short question and Claude's answer opens with a verdict for your projects: use it, later or skip, the effort, the cost and one line why 0
- xcode-status 0.2.0 In Xcode projects only: one line with the last build and test result and the booted simulator; flags 0-test runs; blocks a second xcodebuild while one runs 0
- hud-desktop 0.5.0 HUD above the prompt in the desktop Code tab: dir, running subagents, context, weekly limit, cost and cache, activity; three layouts via /hud 0
- status-bar 0.2.0 Context window as a stacked bar above the prompt, one color per /context category, plus cost, rate limits and recent tool calls 0
- wartezeit 0.1.0 A German vocabulary game above the prompt while Claude works, with words from the session's topic 0
- cache-caffeine 0.12.2 Keeps the prompt cache warm while you step away: a short poke before the cache expires, so the next turn reads the cache instead of writing it again. A row above the prompt turns it on and off and edits the message. Near the usage limit it books Claude a wake right after the reset. 0
- context-handoff 0.1.1 mod + skill Hands a long session off cleanly: at a context threshold Claude updates the docs and writes a handoff, the session compacts with its instructions, then a kickoff prompt carries on. Gives Claude a live context reading and a /wrap-up skill 0
- turn-telemetry 0.1.0 Band above the prompt with per-turn telemetry: duration, TTFT, tok/s sparkline, tokens, requests and stalls 0
- teach-me 0.1.0 Learn while Claude codes. After a turn that changed code, a quick question about that exact change appears above the prompt; answer with /a 1-4, see your weak spots with /teach stats. Needs function hooks (early access). 0
- harness 0.4.12 mod + skill Skills and guard hooks: ai-code-cleanup, interrogate, shape-task, verify-change, setup, a shared-worktree git guard, and a guard against reading API-key config files 0
- model-router 0.1.0 /model subcommands: switch model, provider (via submux) and effort live for each tier and each subagent type; bare /model stays the built-in picker 0
- harness-band 0.1.0 Live band above the prompt following running .harness plans 0
- drift 0.1.0 Are you moving or hiding in the dark? Watches the session for shipped work (commits, pushes, deploys, passing tests) against edits to tooling, config and docs, and says so in one quiet line when you have been in the dark too long. Zero model tokens, no network, nothing leaves your machine. 0
- carousel-ship 0.1.0 After a carousel render: Caption, Queue Threads and Log ledger buttons; blocks Threads posts with a part over 500 characters 0
- status-hud 1.5.1 A bar above the prompt showing current activity, 5-hour limit, weekly limit and context window. 0
- where-are-we 0.1.0 A card above the prompt: Done / In progress / Waiting on your OK, kept by Claude and saved per project across sessions. 0
- tps-report 0.3.0 Bill from management drops by above the prompt while Claude works, and the spinner starts preparing TPS reports. A parody. 0
- mermaid-inline 0.6.0 Mermaid diagrams in Claude Code: every ```mermaid block Claude writes is drawn as a picture right where the fence was in the transcript, with an open-SVG button, and as box art where the terminal cannot show pictures. Fork of galElmalah/claude-mods claude-mermaid. Needs function hooks (early acce... 0
- registro-scritture 0.2.0 A fine turno elenca tutto ciò che è stato scritto fuori dalla repo (Notion, Postpickr, Spreaker, mail, git push) con link e segnalazione degli errori 0