[mod] [skills] Turns a feature request into a spec, one approved step at a time: clarify the request (asking you what is unclear), survey every affected screen and feature with subagents, write the requirements, then propose several feature and UI options with mockups. Saved under docs/specs/; /specs shows the checklist
todo-mod
japan-da-man/claude-code
[mod] TODO pane: check a task to have Claude run it
usage-stats
japan-da-man/claude-code
[mod] Usage stats pane: sessions, messages, tokens, active days, streak, favorite model and a daily heatmap
close-gate
wszaq/claude-mods
Show session close facts and give them to a handoff.
deliverable-dock
wszaq/claude-mods
Record session deliverables and ship one to Downloads
peer-radar
wszaq/claude-mods
Show local and peer Claude Code sessions and sync health.
session-panel
wszaq/claude-mods
Session pane with Progress, Outputs, Used, Subagents and Mods cards
verify-gate
wszaq/claude-mods
Run the repo check after edits and show its result.
waste-alarm
wszaq/claude-mods
Count repeated shell commands and show token-dashboard tips.
round-changes
joaofatoretto/round-changes
Review what each round changed: the files Claude touched, their diffs (shell commands included), and one key to open a change in VS Code.
agent-state
M-i-k-e-l/agent-state
Shows the state of Claude (working, permission, input, idle, background, compacting) in the iTerm2 tab subtitle and in a Sessions pane in the desktop app.
matrix-rain
an80sPWNstar/claude-mods
Matrix digital rain: a /matrix pane, and a few rows above the prompt while Claude works. Pure eye candy.
token-meter
an80sPWNstar/claude-mods
This session's token use: status line shows the context in use (as Claude Code counts it), live spinner count, and a /tokens pane with a Pac-Man context-window maze, Claude vs local LLMs. Plus a Haiku-first subagent guard.
rice-session-accounts
moabualruz/rice-session-accounts
Choose an Anthropic OAuth account by email and tier inside ordinary Claude, with session-local authentication, selected-account reporting and resumable setup on macOS, Linux, WSL and Windows
agent-crew
eric-liebrecht/claude-mods
Live pane showing running sub-agents as animated, individually styled Claude critters with their current tool activity.
vome-automation
Vortitron/home-assistant-mcp
A side pane for the Home Assistant automation Claude is working on: triggers, conditions and actions as HA's editor nests them, what a save changed, which steps the latest run took, and a car-stereo dot-matrix display that acts it out. Works with @vortitron/home-assistant-mcp, hosted on Vome, linked through the Vome relay, or pointed at your own Home Assistant.
vome-dash
Vortitron/home-assistant-mcp
A Home Assistant dashboard in a side pane of Claude Code, working: live states, and controls that toggle, step and run as the dashboard's own do. Shows the dashboard Claude reads or edits, with what a save changed lit up, or one picked with /dash. Needs @vortitron/home-assistant-mcp.
vome-doom
Vortitron/home-assistant-mcp
house.wad in a Claude Code pane: your Home Assistant home as a Doom level, played in the terminal. Shoot a lamp and it turns off for real.
vome-esphome
Vortitron/home-assistant-mcp
A side pane for ESPHome in Claude Code: a map of the device from its YAML (board, network, buses, entities, pins, triggers) with what a save changed lit up, and the build Claude is running as it happens (phase, progress, the latest output, the result), over a dot-matrix chip on the bench. Needs @vortitron/home-assistant-mcp with esphome_activity.
vome-health
Vortitron/home-assistant-mcp
A side pane for your Home Assistant's health: Vome's score out of 100 and what its check found, by severity with what to do, marked as Claude works on each, then a re-check rolls the score to the new one. Needs @vortitron/home-assistant-mcp with vome_health_report and the Vome integration.
cockpit
bharath-gp/ai-harness
Live session dashboard in one side pane (/cockpit). Mods: agents-progress (/agents-info), cache-keeper (/keepwarm, /cache-tax), context-health (/ctx-handoff, /autohandoff), token-meter, usage-limits, filetree (/filetree), next-steps, architect, permission-gate, loops, turn-receipt, session-log, decisions. Skill: cockpit-setup (/cockpit:cockpit-setup).
guardrails
bharath-gp/ai-harness
Safety and review of Claude's output, helped by local decision models. Mods: blast-radius, secret-sentry, reflect (/reflect-queue, /reflect-pause), assumption-tracker (/assumptions), self-critique (/critique), prompt-coach (/sharpen), merge-sweep, decision-gate (/decide-bench), auto-answer, model-picker. Skill: guardrails-setup (/guardrails:guardrails-setup).
guildhall-tavern
GrillerGeek/guildhall
A live pane of the Guildhall during a /quest: who is working, what they are up to in character, and who answers to whom; a recap of phase times and reviewer verdicts when the quest settles, and a band above the prompt while the pane is closed.
code-modernization
mrkhachaturov/ccode-personal-plugins
Guided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, the business rules mined from the code, and a plan you approve, then an upgrade, a rewrite or a rebuild with independent proof that the new code behaves like the old. Includes security hardening, a one-page report, specialist agents, and an optional live progress pane (early access).