Prompt
330 mods. Bands above the prompt and tools that rewrite what you send.
- image-peek 0.1.0 See the images you paste into Claude Code: a thumbnail above the prompt for each [Image #N], drawn in any truecolor terminal (Warp included) and with real pixels in kitty and Ghostty, and a button that opens it full size in Quick Look. macOS 5
- goblin-chrome 0.1.0 Goblin-mode's face inside Claude Code: a goblin in the band that reacts to the session, hint lines in its voice, a mask over every question, frames by model tier, a day cycle and the project theme's colours. 5
- context-bar 0.1.0 Draws the context window as a stacked bar above the prompt, one color per /context category; toggled with /context-bar 5
- honmoon-redact 0.1.1 Client-side secret/PII redaction hooks: keep API keys and sensitive identifiers out of Claude Code's model context by redacting Read/Bash/Grep tool output, blocking prompts that carry secrets, and denying reads of known credential files. Session-transcript scrubbing verified on Claude Code 2.1.26... 5
- image-peek 0.1.2 Shows the images you paste: thumbnails above the prompt, and larger pictures under each sent message in the chat; needs a kitty-graphics terminal such as Ghostty 5
- cache-timer 0.1.0 Counts down to when the prompt cache expires, so you can send the next message before the whole conversation has to be cached again 5
- pin-board 0.1.1 Pins standing notes with /pin that Claude keeps following after /compact and /clear; shows them in one row above the prompt or as a counter, and keeps them per folder with --keep 5
- typesafe-mod 0.5.1 Routes decisions to TypeSafe's Jev model: ranks installed skills for each prompt, and answers the agent's own this-or-that questions when confident. 4
- ts-band 0.8.0 Tailscale nodes' state in a band above the prompt, with a toast when a node comes up or goes down 4
- receipt 0.1.0 What each turn did, in a band above the prompt once it ends (files changed with lines, commands and failures, reads, subagents), and a toast when the model goes in circles; read from the turn's own tool calls: no tool, no prompt, no tokens 4
- hitokoto 0.6.0 A line from Hitokoto (δΈθ¨) in a band above the prompt, refreshed on a timer, per session, per prompt or once a day 4
- secret-redactor 1.0.0 Keeps secrets, email addresses and IP addresses out of the session transcript: swaps each one for a stable placeholder on the way in, and puts the real value back on the way into a tool call 4
- vercel-deploy-status 1.0.1 Pins the Vercel deploy queue of the linked project under the prompt: every deploy queued, building or just finished, with its phase and elapsed time 4
- whats-agent-doing 0.4.3 A small box above the prompt that always says what the agent is doing right now (reading, thinking, writing, running a tool, waiting for you) and expands to show what it has done. 4
- prompt-coach 0.1.2 Before a vague prompt is sent, suggests a sharper rewrite; you choose: send improved, send yours, or edit the suggestion. Never rewrites silently. 3
- quickbar 0.1.1 A one-line launcher above the prompt: live context %, and one-click buttons for every claude-mods panel you have installed. 3
- pomegr 0.8.3 mod + skill Configure and report bounded, repository-specific coding-agent signals to the local Pomegr observer. 3
- flywheel-mod 0.1.0 Holds risky Bash, PowerShell and file-edit calls with the Flywheel pre-action monitor, writes a hash-chained receipt for every turn, and shows held and passed counts above the prompt. Adds holds only; never approves a call. 3
- context-card 0.1.2 Context window breakdown and plan usage, in the band above the prompt. 3
- claude-queue 0.4.3 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. 3
- context-economy 2.0.0 mod + skill Handoffs that survive a context reset: every compaction becomes a verified handoff written from the live session, a /clear hands the next conversation the handoff the cleared one wrote, and a /handoff skill writes and reads them by hand. 3
- warmline 2.8.0 Claude Code's prompt-cache state, drawn above the prompt where no statusline renders: the Desktop app's Code tab. 3
- adversarial-review-loop 3.0.1 mod + skill Implement an agreed plan with an enforced adversarial review loop: every phase commit is gated on an external review. 2
- proctor 3.0.0 mod + skill Hook-enforced development discipline for Claude Code. Skills teach methodology; hooks enforce compliance mechanically (git gates, planning mode, step budgets, quiet mode, pre-flight checks, self-diagnosis, autonomy metrics); store + tracing survive compaction. 2
- omp-quota 0.1.5 [Experimental] Every omp provider's remaining quota in-session β a /quota band above the prompt, /quota refresh, and a toast when a provider worsens from ok (Claude Mod; needs Claude Code 2.1.287+) 2
- calendar 0.1.3 [Experimental] Upcoming Google Calendar events in-session β /cal toggles a band above the prompt with the next 7 days, /cal N for N days (Claude Mod; needs Claude Code 2.1.287+ and the claude.ai Google Calendar connector) 2
- claude-stats 0.2.1 Usage limits (5h / 7d) and ccusage spend, drawn as a status band above the prompt. 2
- plan-bar 0.1.0 Live progress bars above the prompt for multi-step work: one row per plan, with stages, percent, waiting and failed colors, and sounds 2
- leftovers 0.1.0 Keeps a ledger of what Claude left running or lying around on your machine and servers 2
- next-steps 0.1.0 Tre bottoni sopra il prompt a fine turno: i due prossimi passi naturali della conversazione e Replay 2