All mods
1,869 mods. Every one passed the check.
- breakout-widget 1.0.0 A brick breaker that plays itself; every tool call adds a row of bricks. 1
- aquarium-widget 1.0.0 An aquarium with a fish for every running tool call and agent. 1
- collision-widget 1.0.0 Stops an edit to a file another Claude Code session on this machine changed since this one last read it, and has Claude read it again first 1
- diff-review 0.4.1 git の差分を GitHub の Changes のようにペインで見て (split / unified)、行を選んでコメントし、まとめて Claude に渡す mod 1
- fm 1.0.0 Firstmate Calm for Claude Code: the sailboat working animation and conversation-only transcript presentation, sharing the per-home config/calm preference with the Pi Calm extension. Its hooks module may load through CLAUDE_CODE_ENABLE_FUNCTION_HOOKS or Claude Code's tengu_plugin_hooks_modules rol... 1
- cache-timer 0.1.0 Counts down the prompt cache's lifetime in the prompt footer, so you can tell whether your next message will be a cheap cache read or a full re-send. 1
- blast-radius 0.1.0 See what a risky command would change before it runs. 1
- token-weather 0.1.0 A live forecast of the context window, drawn above the prompt. 1
- replay-theater 0.1.0 Step through the last turn's edits, one diff at a time. 1
- reins-probe 0.1.0 Probe for docs/mods-probe.md: how the mod engine treats a slow, failing or dialog-opening tool.call hook, and where it sits against settings hooks. 1
- codex-subagent 0.1.0 Agent types backed by OpenAI GPT through a per-session codex app-server daemon: the Agent tool spawns codex-subagent:luna or codex-subagent:sol like any subagent, and every model step of that agent is answered by a codex thread instead of a Claude request. 1
- cc-cli-rail 0.1.0 A vertical rail of your session's prompts beside the transcript; click to jump, hide it to a button above the prompt. Fork of prompt-rail by oikon48. 1
- claudelingo 0.1.2 Pick up a foreign language while you work with Claude 1
- wod-band 0.3.1 A pixel-art Ragtag athlete above the prompt who does a rep every turn: the session is an AMRAP of thrusters, burpees and pull-ups. 1
- diff-review 0.1.0 After every Edit, Write, NotebookEdit or sed -i, a docked pane shows that file's uncommitted hunk with [keep] and [revert] buttons; a press dismisses or runs git checkout with no model turn. 1
- atelier-bell 0.1.0 Tells you when an atelier finishes: flux7-studio renders, as toasts and a line under the prompt 1
- orbit 0.1.0 A globe of everything your Claude session talks to: tool calls, sockets and bytes traced to hosts, countries and orgs, with a deny-list that blocks before a call runs. 1
- forge-gate 0.1.0 Enforces the forge phase gate: shows whether the current phase's Verifiable gate is green on exactly the files you have, and sends back a forge stage whose FORGE_RESULT claims "gate":"green" when it isn't. /gate runs it. 1
- __NAME__-widget 1.0.0 __SHOWS__ 1
- claude-roulette 0.1.0 A private text chat with another human while Claude works, with random matching, interests, next, block, report, and automatic task completion handling. 1
- session-band 0.2.0 A status line under the prompt counting belt denials this session, shown from the first deny on. 1
- vn-stockmarket-heatmap 0.2.0 Live Vietnam stock-market heatmap and price board (SSI iBoard) in a Claude Code pane 1
- kiro 0.1.0 Recupera los cortes de Kiro, relanza kiro-gateway y añade /kiro. 1
- turn-budget 0.1.2 Asks before a single turn uses more than +5 session points or 500,000 uncached input tokens, and stops it cleanly if you say so. Checks between requests, never mid-command. 1
- garden-widget 1.0.0 A plant that grows a leaf per tool call, flowers when checks pass and wilts when a call fails. 1
- adversary-draft 0.1.0 Tells the adversary bridge whether the prompt box holds an unsent draft, so it never pastes into one. 1
- aside 0.1.0 A side pane for questions about the session, answered from a fork of the transcript and kept out of it 1
- jev-model-router 0.4.2 Picks the model and the reasoning effort for each task with TypeSafe's Jev, a System One decision model reached either through TypeSafe's own API or the Vercel AI Gateway. Routes subagent models at agent.spawn and the main loop's effort and model at turn.step, in both directions, falling back to ... 1
- jev-model-router 0.4.2 Picks the model and the reasoning effort for each task with TypeSafe's Jev, a System One decision model reached either through TypeSafe's own API or the Vercel AI Gateway. Routes subagent models at agent.spawn and the main loop's effort and model at turn.step, in both directions, falling back to ... 1
- usage-probe 0.1.0 Writes the session's plan rate limits to the file named by THAI_SYLLABUS_USAGE_OUT 1