Guards

A live plan Claude posts and keeps current: progress above the prompt, the full checklist and its history in a pane.

Search this project's past sessions: /recall for you (attach an old exchange to your next prompt), a tool for Claude to look up earlier decisions.

Splits a task into independent parts, runs them as parallel subagents you launch and watch live, then hands their results back for integration.

Claude knows what you changed between turns: files edited outside Claude are named (with small diffs) beside your next prompt, and an optional cheap review flags slips in your own edits.

A quick second pair of eyes after edits: reviews the turn's diff in the background and offers to fix what it finds.

Runs your project's checks after Claude edits, shows pass/fail above the prompt, and closes the loop with one-press (or automatic, bounded) fixes.

A little game layer: 32 achievements for how you use Claude Code, with lifetime progress and a /achievements pane.

Jev (TypeSafe's System One model) as Claude's instant co-processor: bulk filter/classify/rank/semantic-grep tools, risk notes under permission dialogs, a check on unverified 'it passes' claims, and optional per-prompt effort.

A commit gate that reads the staged diff in a blink: Jev flags debug output, commented-out code, TODOs, machine paths, secrets and off-message changes before Claude's git commit runs.

Catches tests being weakened to make them pass: every test-file edit is judged by Jev in a few hundred ms against what you asked for.

Git at a glance and in reach: a branch/changes readout, a /git pane to diff, stage, revert and commit, and Conventional Commit messages written by haiku.

Inline #tokens that attach live context to a prompt: #diff, #staged, #log:20, #tree, #todo, #errors, #file:path:10-40, #url:https://...

Supply-chain check before installs: npm/pnpm/yarn/bun/npx, pip/uv/poetry/pipx, cargo and gem packages are looked up first; nonexistent names are refused, brand-new, unpopular, deprecated or lookalike ones need your yes.

Protected files and a project boundary: Claude can't edit .env, keys or .git, asks before touching lockfiles and migrations, and asks before writing outside the project.

Every subagent, live: a /subagents pane with status, model, elapsed time, steps, tokens, last tool and answer, plus a band while any run.

Tool latency: times every tool call, shows a live timer for slow ones, and a /stopwatch pane with per-tool averages, p95, max and the slowest calls.

A receipt for every turn: tools, tokens, cache hits, estimated cost and lines changed, on the turn's closing line (or in the transcript), with a /receipts pane.

A /dashboard pane charting this session's turns (prompt tokens by cache kind, hit rate, cost) and your last 14 days of spend.

Adds Exa's results to WebSearch, and saves each WebFetch page to disk with the lines that answer the prompt

Wakes an idle Claude Code session when its local file mailbox receives an addressed instruction, and records the session's replies to files the sender can read. Independent and experimental.

A Claude Code mod for Eunuch Mode: while the skill is on, the palace adviser stands above the prompt in pixel art, posing for what the agent is doing; the spinner narrates each action in court language; and the status line reads "Court in session". Canned lines by default; opt-in generative mode (fresh lines from Sonnet) and treachery mode (he plots your downfall, cosmetically). /court toggles...

A spellbook of agent skills for AI. Cast wisely. Four skills: eagle-eye, which lays coupled decisions out as a morphological box and renders one self-contained page that reads any configuration back; groundtrack, which turns a plan or a written change into a call graph with recorded traces through it, on a page a reader can step; contract, which interviews a person to agree the terms for a...

Claude skills for your Plex server. Read-only reports on your media and server, plus mods for Claude Code: a read-only guard, a library status line and a Now Playing panel.

A pane beside the transcript with the GitHub pull requests and issues related to the current session: drag a title or description to leave a comment on it, add as many as you like, then Submit sends them all as one prompt. Watch each pull request's checks, review decision and mergeability update on a timer.