All mods
2,300 mods. Every one passed the check.
- cli-patch-mods 0.1.0 Function-hook alternative to some claude-code-patches byte patches: undefers Monitor/SendMessage/TaskStop, keeps mode/plan/task nags out of requests, unwraps teammate messages, drops idle pings 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
- house-rules 0.2.0 Enforces git identity, attribution and branch-naming rules on Bash calls 0
- wartezeit 0.1.0 A German vocabulary game above the prompt while Claude works, with words from the session's topic 0
- orch-session 0.1.0 Shows the orch tickets this session holds: status line, band above the prompt, /orch pane and hand-over toasts. 0
- design-lab 0.23.2 mod + skill Build and maintain a verified Figma component library from real code with resumable, schema-validated workflows. 0
- turn-timer 0.1.0 Saves how long every turn took as a row in the chat, logs every prompt's timing, and adds /timings to look back. 0
- lean-comments 0.1.0 Stops Claude adding banner, multi-line, long or narrating code comments 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
- Cache 0.6.0 Countdown of the 1 hour prompt-cache window, counted from the last reply. 0
- turn-telemetry 0.1.0 Band above the prompt with per-turn telemetry: duration, TTFT, tok/s sparkline, tokens, requests and stalls 0
- tool-preload 0.1.0 Keeps context-mode, jcodemunch, claude-mem, WebSearch, Task and Supabase tools loaded so Claude stops calling ToolSearch for them 0
- harness-guard 0.1.0 Shadow or enforce the existing Harness PreToolUse guards as function hooks 0
- blast-radius [mod] Holds risky shell commands (rm -rf, git reset --hard, force push, git clean, migrations, find -delete, xargs rm, also inside bash -c / eval) and shows what they would change in a pane with Proceed / Cancel. Based on Anthropic's claude-code-playground mod 0
- token-weather [mod] A live forecast of the context window above the prompt: weather icon, fill, tokens, a chart of the last turns and how much the last turn added. Based on Anthropic's claude-code-playground mod 0
- dashboard 0.1.0 The context window's fill and the main loop's tokens/s in the status line 0
- revisor-com-prova 1.0.0 Quando volta o resultado de um revisor (Codex, agy, council), lembra o Claude de que achado sem prova não conta e de reproduzir antes de corrigir 0
- sonnet-por-padrao 1.0.0 Subagente e agente de script (Workflow) criados sem modelo escrito rodam no Sonnet em vez de herdar o Opus; Opus só quando pedido de propósito 0
- pre-merge-cross-review 4.0.2 mod + skill merge 前の codex review を必須化する 0
- claude-fnhook-fixture-reserved 1.0.0 Reserved-prefix plugin name: validate must reject it (#1496) 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
- context-meter 0.1.0 A context window meter at the bottom right of the prompt; click it for the full breakdown 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
- shell-mode 0.3.0 用 /shell-mode 切换 Bash 模式,连续执行命令并显示颜色,退出后将输出保留在 CLI 中 0
- context-alert 1.0.0 One closure notice per loop and tier as context nears compaction 0
- gh-pane 0.6.0 A docked pane of the session repo's issues and PRs in run order, with buttons that fill the next command, plus two for this session's ship runs: send the merge reply at the merge gate, then, once the PR is merged there or by ship on its own, clear and run the next command. 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
- usage-stats [mod] Usage stats pane: sessions, messages, tokens, active days, streak, favorite model and a daily heatmap 0
- idle-compact 0.1.0 Runs /compact while the session sits idle waiting on background work, right before the prompt cache expires. 0