Claude Code Mods

russellpope/claude-mods

Pane of the herdr agents this session spawned, and theirs: status, model, context, cost, ticket. /agent-tree toggles it; a global view lists every herdr agent.

Teodagher/teo-mods

Live board of your subagents: a little Claude critter per agent and one sentence on what it is doing

TheClaessens/thomas-claude-mods

Live graph of this session's agent, its subagents and theirs: model, context, tokens, status and assignment.

Barncore/agent-watch

A progress bar above the prompt and a live agents panel for any subagents Claude starts, with model, context, cost and time. Fork of johnnyvizz's savvy-progress (MIT).

estruyf/claude-agent-watch-mod

Keeps the number of running Claude Code sessions under a limit and shows the ones waiting on you or sitting idle.

hereshecodes/claude-mods

Flags risky Bash commands and writes to sensitive paths in a live sidebar pane, with a status-line tally.

MarkMerk/markmerk-mods

A workshop where Claude and its subagents walk between tool stations: a pixel-art pane in the terminal, and a 3D window with a room for every session, to watch, prompt and answer them. English and German

DiogoHSM/claude-mods

Painel lateral com subagents em pixel art, bolinhas de status das tarefas e barra do plano acima do prompt

jorgik1/claude-agents-pane

/agents-pane opens a sidebar listing available agents in their configured colors, with a Run button each

Blind3y3Design/agents-panel

A pane of every subagent in the session: model, effort, context, tokens, estimated cost and time, with a crab per agent role on desktop. Works with any agent type or workflow.

cedricfarinazzo/agile-skills

Claude Mods for the agile-skills loop: /agile-board opens the agile console pane (board with burnup and a Monte Carlo done-by forecast, ticket and PR flow, aging WIP and PR overlap, what each ticket cost with the median and cost per line, drain passes with cost, cache hit rate and the loop's agents, guards and receipts, links), read live from gh, the Jira MCP and the engine rather than from the model's answers, with a status-line entry (spend per hour and per merged PR, the 85% date) and an alert row above the prompt; guards that check GitHub at merge time (pinned live head, green CI on it, every file read by a reviewer in full or by a diff since a full read), enforce agent tool grants, cap the merge train's fix rounds after review, stop new build work on a ticket at an optional per-ticket cost cap, and refuse pushes to main and force pushes inside the loop, each set to enforce, warn or off, with a one-time bypass a person grants from the console; /receipts checks agent receipts against the contract; retro counts for agile-15. Needs Claude Code 2.1.287 or later.

tsukimiya/agmsg-inbox

Deliver the agmsg inbox to Claude Code through a mod-owned watch.sh instead of the Monitor tool (no 30-minute re-arm)

Creeperprol/claude-mods

Side panes for Claude Code: a usage pane (context, limits, cost, tools) and session link (sessions message each other, host mode)

JohnRiceML/aidiff-gate

Keeps AI-written code honest: flags flaky and bloated tests, trims wall-of-text replies, and makes you write the 'why' before a commit. Uses TypeSafe's Jev as a fast judge.

BillyMRX1/airlock

Routes supported project edits into a Git worktree for review, accept or reject. Worktree routing is not a filesystem sandbox.

yodem/agentic-label-engineering

/ale-board: a live task board for an Agentic Label Engineering (ALE) run above the prompt and in a docked pane. Reads `python3 -m ale status --json` and the run's label files; read-only, LLM-free. An experiment on Claude Code function hooks (Mods).

lua-erissatallan/claude-mods

Allan's workflow mods, built from his own session logs. Every feature has its own on/off row in /config and is switched with /mods on|off <feature>. ALLAN_MODS_OFF=1 disables all of them.

YossiAbutbul/altshift

Fix text typed on the wrong keyboard layout (English <-> Hebrew) and show Hebrew chat right-to-left, from a band above the prompt

Iskandeur/session-board

Alvearium: one ticket board for all your coding-agent sessions (Claude Code in the terminal and on claude.ai/code, and OpenAI Codex CLI) and their agents: what waits on you, what is in progress, what to do next. Live updates, dependencies, priorities, who-talks-to-whom history and a feedback inbox.

barisdemirhan/claude-ambient

A living band above the prompt that Claude's work feeds, with sound: an aquarium, a bonsai, a skyline, constellations, weather that can follow the real sky, a train, Game of Life, a heartbeat, a fireplace, digital rain or a lofi desk. /ambient picks the scene

darshk07/claude-mods

Anchor: pin facts, decisions and rules that are re-sent every turn, so /compact can never lose them. Per-project pinboard with a panel.

kartollikaa/claude-android-emulator

Runs the Android emulator in the Claude desktop app: /emulator opens its live view in the browser pane, one Start button boots it

a252937166/cc-mod

Voiced pixel anime girls who roam the Claude Code transcript: they dance while Claude works and serve tea when it is done, and they do chores too: usage reports, a guard on dangerous commands, secret scans, quick code reviews and task recaps (/waifu help)

hbkse/anki-claude-mod

Review your AnkiWeb decks above the Claude Code prompt while Claude works. Syncs straight with AnkiWeb through Anki's own Rust core; no Anki desktop or AnkiConnect needed.

sagarr/claude-code-annotate-mod

Annotate selected transcript text inline, review in a side pane, send the comments back to Claude

PeteChu/cc-answer

/answer: answer the questions in Claude's last reply in Claude Code's native question dialog

rjohnt/answers-claude-mod

Answers-only view of the main thread: each reply filed under the prompt it answers, latest headline + open ask pinned above the prompt

ph3on1x/agent-plugins-skills

Claude Code subagents on the models you choose: name as many agents as you like, each on a model from your own providers (LM Studio, Unsloth Studio, llama.cpp, vLLM, OpenRouter, any Anthropic-compatible API), and call them like Claude's own subagents while the main session stays on Claude.

tibzejoker/claude-mods

What Claude is building (website, mobile app, desktop client, Unity game…), live in a panel of the client (desktop, mobile in Remote Control, terminal): Claude hooks up the project and the network bridge itself, and drives the same target as you

Thunder-13/apex

Shows the APEX status indicator when APEX (Ask. Perfect. EXecute.) is on. Reads ~/.claude/apex/state.json on session start and each prompt submit. No Pane, no Button.

shezis/claude-api-cost-compare

Live pane showing what this session would cost on the Claude, OpenAI, DeepSeek, GLM and Kimi APIs

dbroadhurst/claude-mod-approvals

A pane on the right listing the decisions Claude needs from you, each with its recommendation and Approve / Chat buttons

adammhal/claude-mods

Retries an auto-mode-blocked call up to three times so Claude Code's own permission prompt (and Moshi) can ask you.

shabier/claude-plugins

Five games in the docked side pane: Rail Runner, Road Hopper, Block Drop, Flap, 2048. Hides below 110 columns.

thefotes/pane-arcade

Play Snake, Minesweeper, 2048, chess (vs Stockfish) and CHIP-8 ROMs in a pane while Claude works.

useloadflow-dev/session-health-claude-code-mod

A side pane that draws the architecture of what you're building, version by version: what changed and why, a request traced through it, a design lesson, design-level security risks, and click-to-explain parts.

aarontan-bot/Claude-mod

Architecture map + plan gate: the AI maps modules, declares a scope, you approve it, and edits outside that scope are blocked and observed.

dot-agi/arrester

After a hook, deny rule, or auto mode blocks a tool call, Arrester stops later calls that reach the same result another way or read or change your guards. After your No, it stops only exact retries.

afterever/claude-mods

A menu for the tool mods in this repo and for your own commands: a button in the footer under the prompt box opens a menu pane, docked on the right, with a Prompt Upgrade switch, a Sound notifications switch with a sound for your own Enter and one for Claude, one-press shortcuts to /prompt-upgrade and /work-report, and USER and PROJECT sections listing your own skills and commands, each of which you can turn off. A remote control for the tools, with one thing of its own: the sound notifications.

amsyeung/artifact-catalog

When Claude publishes a new artifact, asks above the prompt whether to file it in your catalogue (a Notion database and/or an index artifact).

netgfx/claude-artifact-mod

A side pane listing the media files and documents created in this session, with type icons, pagination, and open-with-default-app.

m2ai-portfolio/claude-mods

Enforces the subagent output contract: watches each Agent dispatch's artifact file, flags a 5-minute stall, wakes an idle Claude once per stall, offers a Stop button

kad1r/claude-mods

Windows toast and sound when Claude waits for you: a permission prompt, AskUserQuestion, or an idle prompt

i-noma-ru/claude-ask-choice

When a reply ends with a choice-based question written in plain text, has the model re-ask it with the AskUserQuestion picker so you can select an option instead of typing.

Tvrtk0/claude-code-mods

A read-only mode for questions: Claude answers and investigates but cannot change files, run state-changing commands or send anything; quick, ask and deep levels.

sameeeeeeep/ask-notch

Claude's questions drop from your Mac's notch as a card. Click an option, pick with 1-4, type your own answer, or press esc to answer in Claude Code as usual.

ccdwyer/assertion-guardian

Blocks edits that weaken tests to fake a green run: removed or loosened assertions, added skips, deleted cases, swallowed errors, snapshot rewrites

risen372/claude-mods

Claude logs the assumptions it makes mid-build; a band above the prompt expands into a list where you mark each Right or Wrong.