Guards

A Servers pane for this project's dev servers: what is listening, on which port, since when, with Start, Stop, Restart and Log buttons; names the process holding a port when a command fails with EADDRINUSE; a read-only dev_servers tool for Claude. Scans with netstat (never lsof), one session for all; no model calls.

Live pane of long-running jobs (training, downloads, extractions): progress, ETA, stalls and finishes, read from their logs with no model calls; jobs_list / jobs_watch / jobs_unwatch tools so Claude follows jobs instead of polling them.

Watches how your other mods really behave: hook failures and slow hooks (read off the chain's own trace), what each one did (toasts, status lines, commands, processes, model calls, writes), with /mods for a live pane and /mods report for the last day, week or month. Changes nothing they do; no model calls.

Watches your Modal apps from the CLI, in projects that use Modal: running apps and containers on the status line, a toast when one has been up too long, today's spend where the CLI reports it, and a pane to stop an app (after you confirm). One session polls for all the open ones. No model calls.

Watches your open pull requests: CI pass/fail toasts for the PRs you open here, failing-check logs attached when you mention them, a prs_status tool so Claude reads them without gh, and the post-merge ritual (fetch --prune, switch, ff-only pull, delete the branch) done for you with no model calls; in a linked worktree it only fetches and leaves the worktree to you. Tells you once when gh's...

Makes past sessions recallable: indexes Claude Code and Codex transcripts, subagent runs, memory files, standing orders and second-opinion reviews into a local SQLite index (kept after Claude Code deletes old transcripts), gives Claude search, expand, recap and list tools, and adds /recall (search, last session, timeline, decisions, commands, files, PRs, ask), /remember, a...

Raises the alarm when a long-running session stalls while you are away: a permission dialog or a question that has waited for you past a threshold (toast, Mac notification, optional phone push, repeated while it stays open), and a turn that stopped on a login, usage-limit or billing error, with the fix. Leaves scheduled routines to routine-watch. No model calls.

A machine-wide meter of the plan's rolling 5-hour usage: every session's turns summed as effective tokens, the cap learned from each session-limit hit, the burn on the status line, a toast before the wall, /usage and a usage_status tool so Claude can pace itself. No process runs, no model calls.

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).

A pane summarising the remaining todos, each with Do, Chat, Defer and Delete

Write a handover when a Claude Code session gets long, type /clear, and the next session picks up where you left off with nothing to paste.

Live mesh7 decisions, pending approvals and emergency stops in a pane

An idle pixel-art city in a side pane that grows as you prompt, edit and run commands. Open it with /city.

Dependency-ordered DAG workflows of Claude Code subagents, with a live DAG pane

Flags pasted code that carries someone else's license or copyright header.

Flags weak cryptography: MD5 or SHA1 for passwords, Math.random for tokens, ECB mode, hard-coded IVs.

Flags typosquatted or brand-new packages before npm, pip or cargo installs them.

A live pane listing changed files with +/- line counts, updated after every edit.

Collects every failed command and tool error in one pane.

Warns when an edited file grows past a size that hurts readability.

A pane of every file read, edited or created in the session, with counts.

Detects tests that pass and fail at random and keeps a list of the suspects.

Prevents hand-editing lockfiles; they must change through the package manager.

One dashboard for every Claude session on your machine: what each is doing, cost, blockers, with pause and priorities.