Claude Code Mods

kimura-0314/claude-mod-usage-band

入力欄の上に使用量メーター（ctx・5h・7d・モデル別の週枠）と effort の切り替えを出す

yash-gadodia/claude-mods

A line above the prompt with the five-hour and seven-day limit windows, this session's context fill and cost, plus a nudge to clear when the window gets expensive. The footer shows the cost in Singapore dollars.

yocloud-code/claude-vault

Credential vault for Claude Code: macOS Keychain secrets, per-directory grants, injected env, redacted output, pane with import/export

ibrahimkobeissy/claude-mods

Rings a bell and shows a banner whenever Claude is blocked waiting for you, repeating every 5 minutes until you answer

Plagemes/claude-mods

Lets Claude keep you posted on WhatsApp — progress, problems, reports, questions — and lets you steer every session from your phone, through one self-hosted OpenWA number.

scarrillo/agent-plugins

Timestamps your prompts in the transcript and adds up/down prompt navigation to the footer

legostin/wirepane

The debugging proxy Claude can read, inside Claude Code on macOS: HTTPS, HTTP/2, gRPC, WebSockets and server-sent events from the browser, iOS and Android; one-press device setup; rules and mock servers; a doctor that fixes what is in the way; 16 tools and 3 skills for Claude.

leeovery/portal

Draws the agentic-workflows engine's gates in the band above the prompt — rows a click puts in the prompt and a second click sends — instead of a menu the model has to reproduce; carries a handoff into a fresh conversation; appends the engine's note to a workflow conversation's compaction, so Claude re-reads what it works from; says the phase in the spinner; and refuses a direct edit of a workflow manifest.

leeovery/portal

Draws the transcript rows of what the workflow-gates mod sends — an answer as the question it answered and the answer, a handoff's continuation as where the work went — and a compaction's note as one dim line, instead of Claude Code's framing.

AbhiramDwivedi/claude-ops

Gives every agent that can edit a git worktree of its own, runs a project's setup script with its own port range, kills what an agent left running, removes an agent's worktree and branch once the session merges it, and tidies other merged branches on demand with /tidy

Unayung/cc-mods-youtube

A YouTube player inside Claude Code, backed by cliamp: controls, now playing, thumbnail and playlist

YeonwooSung/my-claude-code-mods

Dependency Lens

lemomo-ai/lemo-mod

说话方式：简短模式（每次回答不超过三句）、记录口吻（首行说明看了什么，末行给出结论） · 默认关闭，在「安全」页开启 / Tone: Brief mode (three sentences or fewer) and Notebook voice (opens with what it looked at, closes with a conclusion) · off by default, switch on in Safety

whyashthakker/awesome-claude-code-mods

Build a saved prompt from goal, constraints, and acceptance criteria.

darkroomengineering/cc-settings

Requests a session compaction when the live context passes a token threshold, so verbatim compaction plugins run near the working ceiling instead of at the model window.

hex/claude-sessions

cs's in-session mod: the rotate band above the prompt, forced rotation past CS_ROTATE_FORCE_CTX, and the wrap key

hamzafer/claude-code-mods

The current prayer and how long is left, the next prayer, and zawal, above the prompt. Computed on your computer from your location; nothing is sent anywhere.

ray-amjad/claude-code-mods

A dreaming pass over Claude's memory folder: merges duplicates, rewrites stale entries, removes dead ones and tidies MEMORY.md, with a backup and undo

escapeboy/claude-code-kit

After a deploy command, runs 5 post-deploy checks from the project's .claude/deploy-verify.json and tells Claude the result.

just-every/12ui-plugin

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.

parodiniccolo/claude-3dgs-view

Preview 3D Gaussian splats (.ply, .spz, .splat, .ksplat, .sog) in a Claude Code pane: orbit with the mouse, rendered by Spark in headless Chrome

NovusEdge/a2a-mod

A2A protocol client for Claude Code: Claude hands tasks to non-Claude worker agents over Agent2Agent and picks up their results.

leinardi/adversarial-review-loop

Implement an agreed plan with an enforced adversarial review loop: every phase commit is gated on an external review.

visualife/ClaudeRouter

Picks the model and effort per request, and shows a live band above the prompt: routing, running agents, skills, MCP, context and plan usage, plus a /ClaudeRouter pane

apolenkov/agent-compact-advisor

Status line score 0-100 for how good a moment it is to /compact now, with reasons; offers a ready /compact that keeps goal, decisions, leftovers and paths, and adds that template to every compaction. Never compacts by itself.

apolenkov/agent-council

A council of independent code reviewers (Codex, Pi, Devin, OpenCodeReview) runs over your working diff in parallel; one summary of agreements, disagreements and unique findings. /council, plus an auto-review that only notifies.

VladLeus/claude-mods

Dashboard of running Claude sessions: context, active/idle, subagents, workflows and who messages whom

charanjit-singh/ClaudeVsCodeMinimal

Mailboxes for Claude sessions: names, cross-profile messages that wake idle sessions, and a band with your account, context, and plan limits.

ririversoza/agent-office

A view-only pixel office pane showing which agents (lead, subagents, Codex, Cursor) are working, with your checklist and this branch's PR

agentic-workbench/agent-quick-menu

A pane and prompt band for plugin commands declared in quick-menu.json, plus plugin and Claude Code settings exposed through /config.

MechC-ODE/agentic-fmi

Early-access live pane for Agentic FMI (/fmi): run progress, values with units, live charts, Pause/Resume/Step/Set/Stop for live runs, built FMUs and system connection diagrams. Reads only the run store; needs the agentic-fmi plugin.

mcpysup-netizen/claude-ai-accounts

Claude·Codex 구독 계정별 남은 한도 띠 + 클릭 한 번 계정 전환(같은 tmux 칸에서 대화 이어가기)

111vandit111/ai-dev-team

Multi-agent build pipeline for any AI coding agent: planner, parallel builders and verifier, per-task models from your own list, knowledge-graph context, live office view

timoncool/angry-switcher

Swear at Claude Code all you like: every prompt is cleaned before Claude reads it. Typos, translit, the wrong keyboard layout, swearing and CAPS go; the meaning, paths and numbers stay; your original rides along so nothing is lost.

DarkSawOktay/claude-mods

Android APK freshness: is the APK up to date with the code, build in progress and its duration, failures and out-of-memory caught at once, size, copy to another folder. For React Native / Expo / Gradle projects. French or English.

alexyslozada/claude-mods

Pide tu aprobación antes de que Claude instale cualquier paquete y muestra el historial en una franja

llkhacquan/claude-mods

Answers permission prompts for you: regex layers allow routine tool calls and always ask on pushes to protected branches, and haiku judges the rest against your plain-text rules. Offers a rule after you approve the same kind of call twice, and logs every decision so /auto-approve learn can suggest more

mako-code/gobworks

Say "this error", "the tests", "this file", "what you just did" or "the plan" and what it points at goes along with your prompt: the failing output, the test failures, the file, the diff, the plan. No model calls, size-capped, never twice, and Remove takes it back.

arthur-fontaine/cc-mod-auto-effort

Picks Claude's effort level for each prompt with a System One decision model

mako-code/gobworks

Every prompt you type gets a quiet second read: without changing your words, a hidden note gives Claude the goal in one line, the likely scope, the project's checks to keep green, and what done means. Haiku only for vague prompts; See, Undo and Off in the band.

VladLeus/claude-mods

Run a session autonomously for a set time with a fixed role; hand off and restart itself at a context threshold

Abdallah-Abdelazim/usage-limits-cc-mod

Draws one dim line above the mod bands to separate them from Claude's output. List it before the other mods.

samfrmr/barmkin-mod

Claude Code mods security layer: secret redaction, untrusted-content taint with a Rule-of-Two egress gate, skill inline-shell mediation guard, MCP tool-poisoning guard, skill-content screen, agent-to-agent firewall, and a Jev System One classifier gateway with an explanation surface.

cpeaustriajc/cj-stack

Cuts a long successful Bash output to its first 2,000 and last 3,000 characters with a count of the cut lines; read-like commands, failures and saved outputs pass whole

Ahorns/BBilingual

Show a translation under every English assistant message in Claude Code. Display-only: the transcript and Claude's context stay English. Bring your own translation backend and target language. Optionally translates what you type into English too.

bostonaholic/claude-mods

Matthew Boston's personal Claude Code mods.

bllshttng/footnote

A Claude Code mod (claude-mod-buddy). Bring back buddy: a terminal companion beside your status line that watches your work and talks back.

Bulls-Work/bullswarm

Bullswarm as a Claude Mod: live subscription meters for every installed coding-agent CLI above the prompt, quota-aware routing of Claude's own subagents to whichever pool has surplus, a verdict note on every bullswarm command the model runs, a /bullswarm command, and $.bullswarm for other plugins.