loose-ends
MiguelProz/claude-loose-ends
Proposes the loose ends Claude leaves undone and lets you decide which to keep; keeps them in refs/loose-ends without touching your branches, and Chispa flags what needs your attention. English and Spanish.
1,027 mods
MiguelProz/claude-loose-ends
Proposes the loose ends Claude leaves undone and lets you decide which to keep; keeps them in refs/loose-ends without touching your branches, and Chispa flags what needs your attention. English and Spanish.
aseem-upadhyay/qol-mods
A weekly coach for how you use Claude Code: one habit at a time from your own sessions, tips at your level, CLAUDE.md lines and skills worth making, and your progress over the weeks
yirasso/flows-mod
Saved, repeatable AI flows for Claude Code: agents, Node scripts, approvals and a for-each, written with you in the chat, run with one command and shown step by step in a pane.
gravityXX/aside
A prompt queue for Claude Code. Queue prompts, ideas and comments while Claude works, without interrupting it, and send them once it finishes or whenever you are ready.
Spectree-Tecnologia/spectree-invoker
A runtime that refuses to call work done until a command proves it: evidence bound to a content digest, isolated adversarial QA, a post-merge receipt and only three human gates. An agent squad for Claude Code and Codex, built for spec-driven modular monoliths.
yu1745/claude-code-pi-subagent
让 Claude Code 的原生子代理用 pi 跑第三方模型(DeepSeek、GLM、Qwen、Gemini…),主代理可纠偏、续接、定期监督
ennovative-solutions/gitlab-pipeline-claude-mod
Shows the progress of GitLab CI pipelines in the status line
itsomidho/clawd-tasks
A live task board: Claude's plan, and under each task the steps it took, how long it ran, the files it changed and the agents it started
hymleong/claude-mods
A side pane with Git review, real PowerShell terminals and a live monitor of the servers running on localhost. Nothing else to install.
demartinogiuseppe/idle-mod
Turns Claude Code's wait state into a live briefing on your own project: vulnerabilities, unpushed commits, stale branches, TODO/FIXME debt. Local only, zero tokens, and the fix is one button away.
NeedSomeFoodMr/claude-mods
A pane showing the main loop and every subagent of the session as pixel crabs, each under its role's hat: a short name, role, model, plan progress, context fill, tokens, estimated cost and time, with totals on top and the finished ones kept below; while agents work, one line above the prompt says how the run stands.
NeedSomeFoodMr/claude-mods
A goals list above the prompt that Claude keeps current as it works: what is done, what it is on, and what comes next. Kept per project across sessions.
phantanphatdgteam-gif/snagon-dev-mods
A coding-agent harness for Claude Code as a mod that needs only Claude Code: /snagon-setup writes your project instructions without repeating the harness, a per-project memory (SQLite full-text search over JSONL, kept out of git), a fact-forcing safety gate with git hook-bypass and secret checks, session journal reminders, end-of-session handoff, cost and context notices, a flow that takes...
Orfila-antoine/claude-mods
Buttons above the prompt: rewrite your prompt in one key, verify Claude's weakest claim with a read-only scout, send one of three next prompts in one click, hand off to a fresh session
MDmubarak786/claude-mods
Keep huge shell output out of the context window. A Bash result over a threshold is saved to a file and Claude gets its head and tail plus a slice tool to grep or page the rest on demand.
RikusVanRensburg/agentic-marketplace
/drive and four tools (testing_run, docker_stack, docs_index, drive_check) that keep the drive's testing, docker and docs folders to their manifests; cleanup runs only on /drive clean apply
RikusVanRensburg/agentic-marketplace
Six tools (issue_labels, issue_create, issue_fill, issue_link, label_ensure, issue_consolidate) that do the gh steps for GitHub issues and check each landed; a duplicate closes only on /issues consolidate
RikusVanRensburg/agentic-marketplace
/orchestrate runs a multi-issue plan through subagents: dev and isolated QA per slice on escalating model ladders, a merge agent that merges and verifies each batch, final QA. Needs worktree-lifecycle
RikusVanRensburg/agentic-marketplace
/wt and worktree_* tools for bare-clone repos: start work, ship a draft PR on your yes, hear about the merge, housekeep when you say so, and guard the layout
Verinoda-Labs/verinoda-symbiosis
Verinoda in Claude Code: the Verinoda MCP server's tools listed in front of the model with a one-paragraph call rule, the code index kept fresh while Claude edits, an optional check of each edit for names that do not exist, one-line file cards in place of file contents when the conversation is compacted, an improvement list for you to choose from (/verinoda-improve), and a Turkish pane with an...
kulovema2012/calm-mode
Calm Mode: hides tool calls and shows one friendly checklist above the prompt while Claude works.
rezzminator/effort-live-control
Set each Claude Code sub-agent's reasoning effort per spawn with [effort: low|medium|high|xhigh|max], and let an opted-in agent's effort rise at each failing test run or red sub-task and come home once the trouble resolves.
aosmcleod/next-up-mod
Keeps the follow-ups Claude suggests in one backlog shared by every session, and a checklist Claude keeps for multi-step work in each session, each with a footer button and a pane
schmas/claude-plugins
Calm, non-technical view: hides tool rows and shows one plain-English checklist above the prompt.
No tracking cookies, no third-party scripts. How we handle data