Guards

See which skills and plugins activated in your Claude Code session, what triggered them, and what they really cost in tokens (with prompt-cache pricing).

A read-only pane that shows the session's live status: doing now, decisions, progress, surprises and the last update.

Band tracking session tokens, tool calls, model working time and cache countdown, with a pane that shows each subagent's transcript

A side pane for the current session: prompt cache hot/cold, tool calls and errors, background commands with restart and stop, the approved plan, task list, subagents and swarm agents, and token usage for the main agent and subagents

Live plan progress bars with stages, steps, step times and soft sounds for decision, error and done. Local fork of zycck/claude-mods plan-progress 0.3.0 (ea2c96b) that sends its rules with the first prompt instead of prompt.compose and sends an unexplained open bar back from turn.complete instead of classic.Stop, redraws the bars from the transcript after a rewind or resume, folds the terminal...

One Mod status pane for Claude Code Desktop with an icon rail: Progress (live plan bars with step times and history, forked from zycck/claude-mods plan-progress), Next steps (up to three suggested next prompts; a click puts one in the composer), Skills & agents (the skills and agents called this session, each tagged personal, project, plugin or built-in, plus the rule and CLAUDE.md files...

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.

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.

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.

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.

On-screen Claude Buddy: an ASCII companion pane mirroring what Claude is doing, with quota gauges, plan position, session vitals, subagents and the prompt cache countdown

Drive the lore CLI: author, retrieve, and maintain OKF documentation bundles, including explicit multi-repository workspaces. Cut from the same lore-cli repository and tag as the CLI itself, so this skill can never describe a version you don't have. Also ships the Lore pane: a pane that browses, reads (rendered and raw), searches, creates and edits the repository's documentation bundle through...

Context window as a stacked bar above the prompt, one colour per /context category; toggle with /context-bar

Cleans up after merged work, once it shipped: removing a branch needs git, the forge or the user to say it merged; removing it or filling in its issue waits for the pipeline holding it to pass; merged, clean work gets a follow-up to remove its worktree and branches.

Gates git work: no commit, push or merge without the user's say-so in the current turn; a push to a branch that already landed is refused; a pushed series must leave the project working at every commit; commit messages (format and the issue it is about, then a Haiku review of the body) and MR descriptions kept tidy.

Comments worth keeping: limit-edits flags comment-heavy edits, limit-turns sends a follow-up when a turn's diff adds too many comments.

Docs worth keeping: docs-review asks Haiku whether new text will be read again, docs-no-repeat-code blocks lines that restate code, limit-docs sends a follow-up when a turn adds too much prose.

Scripts worth keeping: scripts-review asks Haiku whether a new script could just be typed again when needed.

Review design specs and implementation plans in a pane: move by block, pin comments, ask side questions, submit one review.

Holds risky Bash commands, shows what they would change, and waits for Proceed or Cancel.

Records the last turn's Edit and Write calls and steps through them one diff at a time with /replay.

Keeps a glossary of the conversation's terms and a map of where the work stands, in panes opened from a band above the prompt, with a btw input for side questions.

Keeps GitHub Actions spend in sight: the month's minutes and cost for the repo's organisation or account, GitHub budgets, cache and artifacts, risky workflows as they are written, and runs that hang

Shows the context window as a stacked bar above the prompt, one colour per /context category; /context-bar toggles it