All mods
2,300 mods. Every one passed the check.
- timeline 0.1.0 Vertical orchestration timeline: talk on the left, work milestones with progress and live subagent cards on the right, per repo across sessions. 0
- kit 0.5.0 The agents kit inside Claude Code: the /flow pane 0
- jev-compact 0.1.1 Context compaction that prunes instead of summarising: rules drop exploration output and hook noise locally, Jev ranks the rest against a budget, a note says what was removed, and removed outputs are archived for the brain. Falls back to the built-in summary when it cannot do better. 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
- turn-usage 1.2.1 A dim line under each Claude reply with how much of your current session's usage limit is used and how much that turn spent, or the cost on pay as you go 0
- claude-who 0.3.3 Friends' Claude Code presence and usage leaderboards via /who. 0
- secret-guard 0.1.0 Masks API keys and tokens in tool results before Claude reads them, and blocks a git push that would leak secrets or home paths to a public repo. 0
- lean-scripts 1.0.1 Scripts worth keeping: scripts-review asks Haiku whether a new script could just be typed again when needed. 0
- usage-bars 0.1.0 Dos barras de píxeles sobre el prompt con el uso de los límites de 5 horas y semanal de Claude 0
- idle-ping 0.1.0 When a turn that did real work ends, ping the user out of band (Telegram if a bot token + TELEGRAM_CHAT_ID are set, else email via CLAUDE_PING_EMAIL + a mailer). 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
- prompt-clock 0.1.1 Shows when you sent each prompt, and when each turn started and ended, in the transcript. 0
- usage-meter 0.1.0 Sleek colored 5-hour and weekly usage bars in the footer; warns at 75%/90% and before agent waves when the window is low. 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
- linear-workflow 0.1.3 mod + skill Linear workflow for Claude Code: issue-next, issue-start, issue-review, issue-ship and issue-plan-cycle skills backed by a deterministic CLI, a linear-manager agent, and a mod that shows the current issue above the prompt with your other sessions and conflict warnings 0
- repo-lock 0.1.0 Blocks dependency changes with the wrong package manager or outside a repo, and shows repo, package manager and branch in the status line. 0
- cc-daniel 0.2.0 Usage limits in the status line and a usage band above the prompt. 0
- git-graph 0.1.2 접었다 펼 수 있는 깃 커밋 그래프 패널 (/git-graph) 0
- smart-compact 0.1.2 Lets Claude compact its own context at a step boundary it picks, with its own instructions, then resume the work. 0
- devhud 0.1.0 cost, context and git hud with an ember theme 0
- compact-handoff 0.1.0 Writes a handoff before each compaction and carries it into the compacted conversation. 0
- 12ui 0.2.84 mod + skill A Design workspace in Claude Code: see design options for a UI as images, select one, ask for more, ask for a change with a note and hand an option off to be built. Your agent runs the 12ui command line once per request, which draws every option at once with your own Codex sign-in. 0
- laya-compaction 0.1.0 Verbatim context compaction for Claude Code, scored by a local Laya model. 0
- fleet 0.17.0 mod + skill A chief of staff for Claude Code: /fleet start makes a session the chief, which plans, keeps a task board and delegates to one agent per repository. 0
- buffer-pane 0.1.0 A pane beside the transcript that holds the next things to tell the agent: write blocks of text while a turn runs, then press [+] to put one block into the prompt box. 0
- sushida 0.1.1 寿司打風の日本語タイピングゲームを /sushida でペインに開く。かな入力のローマ字表記揺れに対応。 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
- clean-view 0.5.0 Calm, non-technical view: hides tool rows and shows one plain-English checklist above the prompt. 0
- token-face 0.1.0 A face above the prompt that gets more uncanny as the context window fills. 0