All mods
3,429 mods. Every one passed the check.
- claude-buddy-bridge 0.1.0 把 Claude Code 的额度、上下文、花费和任务进度写成小文件,给桌宠Claude娘读取 1
- better-tool-rows 0.1.14 Shows Read, Edit and Write paths relative to the session directory, Edit/Write results as +/- counts instead of diffs, long Bash commands cut to one line and long Bash output folded 1
- usage-bell 0.1.0 Rings when the session nears a limit: context fill, rate-limit windows, the auto-memory index 1
- loom-pane 0.1.0 A status line naming the session's loom role, plus guards that keep an owner inside its own worktree and ask before a removal loses work. 1
- pixel-office 0.2.0 Every Claude Code session as a pixel character in a shared office you can click and talk to 1
- guards 0.2.0 dotfiles のガード群 (git 操作のスキル強制・ブランチロック・コメント規約・文脈注入)。機能ごとに hooks/ 配下の 1 ファイル 1
- image-view 0.1.0 See the images you paste into Claude Code: thumbnails above the prompt instead of bare [Image #1] tags 1
- catch-me-up 0.1.3 A side pane with a live catch-up summary of your Claude Code session: why it started, what was done, where things stand, and what needs you 1
- jukebox7 0.2.0 Plays music from YouTube when asked in plain words, audio only through a hidden VLC, with a small control pane 1
- nerv 0.1.0 Barra lateral estilo Evangelion: cuota, contexto, qué hace el agente, PRs, subagentes y alertas 1
- lich 0.20.1 mod + skill Claude Code plugin for the lich harness 1
- review-gate 0.1.0 The review gate as a tool.check function hook. Every shell call is decided in process, so the non-commit calls -- almost all of them -- cost no subprocess at all, and a blocked commit can be put to you as a question instead of refused outright. The decision itself is still bin/review-gate, run on... 1
- agent-cast 0.1.0 While subagents and teammates run, shows each one as a character: one row per agent in a band above the prompt (face, type, task, current tool, elapsed time), and their faces at the head of the spinner line. Each agent type has its own face. 1
- inline-headroom 0.7.0 mod + skill Headroom-style levers inside Claude Code as a mod: clamp-only effort routing after successful tool results, a detector-only CacheAligner that flags volatile system-prompt content and cache-hit drops, and a SmartCrusher with lossless compaction, cross-turn dedup, a dense line elider, a config comp... 1
- desk-board 0.0.1 Desk board: one docked pane over every live session and every account's 5-hour and weekly windows. 1
- statusline-band Port of statuslineV4.sh to a mod: draws the same figures in two colored rows (dir, git, model, effort | duration, version, session id / rate limits, context, cost, output style | RAM) in the band above the prompt, so the Desktop Code tab gets a status line. Off in the terminal by default, where t... 1
- compound-fix-probe 0.0.1 Puts pairs of calls to the fix judge, for tests/journeys/measure_fix.py. Not part of the mod. 1
- pull-request-pane 0.3.0 A pane beside the transcript with the GitHub pull requests and issues related to the current session: drag a title or description to leave a comment on it, add as many as you like, then Submit sends them all as one prompt. Watch each pull request's checks, review decision and mergeability update ... 1
- agent-atc 0.1.0 Air-traffic control for subagents: a live pane listing every agent, what each one is doing now, and controls to message or stop one. Open it with /atc. 1
- bouncer 0.1.0 mod + skill Bouncer for Claude Code: enforce condition-based markdown guardrail rules on tool calls — deny or annotate any call whose content matches, instead of file-path-only rules. 1
- fine-print 0.1.0 Opens a card when Claude's final answer omits a recorded file change or a recognized command with side effects, or makes a test or Git claim the recorded results do not fully back. Step through the diffs and prepare an editable question. 1
- clawd-buddy 0.6.0 A small Claude Code mascot above the prompt, with usage, context, cache, directory and git status 1
- eval-kernel 0.1.0 A persistent JavaScript kernel the model drives with one `eval` tool: state survives between cells, and cells call Claude Code tools, models and subagents. 1
- compact-methods 0.1.0 oh-my-pi compaction methods: shake (move old tool output to files, no model call) and handoff (continue from a handoff document). Use `/compact shake` or `/compact handoff [focus]`. 1
- third-eye 0.1.0 A footnote under Claude's reply with one idea you wouldn't have suggested yourself 1
- image-view 0.3.0 See the images you paste into Claude Code: thumbnails above the prompt, drawn with real pixels in kitty and Ghostty (and iTerm2 with CLAUDE_CODE_FORCE_TERMINAL_IMAGES=1), and as half-block thumbnails everywhere else. 1
- cross-review-status 0.1.0 Band above the prompt showing the state of every cross-review review and consult this session has started 1
- spawn-governor 0.1.0 Refuses subagent/teammate spawns the lead's context cannot absorb, caps oversized Agent returns to a file, and enforces spawn depth from exact parentAgentId. 1
- fleet-core-c7 0.0.1 Lead-side teammate lifecycle: tracks teammates, blocks one Stop while idle teammates are resident, exports the roster. 1
- mesh7-pane 0.1.0 Live mesh7 decisions, pending approvals and emergency stops in a pane 1