Prompt

Secrets found by betterleaks reach the model as ‹secret:…› tokens; Write/Edit restore them, other tools refuse them

Tallies the reminders Claude Code injects for the model, per session; drops the token counter and repeated attribution blocks; /reminders prints the last 30 days

A list of the things to look at with your own eyes after Claude changes something you can see, each with a link and a tick.

/coach: live cost, cache, context and subagent stats, SDLC habit checks and architect lessons; one tip after a turn when it matters.

Live plan, % done, time left and a one-line 'now' for long tasks, in a pane and on the working row.

/mods: every mod in your mods folder, what it does in detail, and an on/off switch for each.

After longer turns, suggests 3 next tasks for the project with a Do it button each, and a Dismiss.

Status bar++: an animated pixel-art band above the prompt with model, context, rate limits, cost and git

A Claude Code companion: a Markdown kanban board pane (/board), a "please look" queue, a mood sprite, and rate-limit usage bars

At 95% of a usage window, has Claude stop at a safe point, commit, push and leave a resume note; after the reset, one tap resumes from it.

Ends each reply with one status line: context fill, usage windows and their resets, each repo's unpushed work, and what the turn did. For sessions watched in an app that draws no status lines.

A band above the prompt showing running background tasks, their elapsed time and last output line

Saves a handoff when you /clear or exit, and offers it back on your next prompt

Watches your PRs, and when one merges it pulls main and deletes the branch, then tells Claude

Keeps review findings (H1, M3, L2...) per repo across sessions and ticks them off when their PR merges

Cutroom: a cutting-room pane for HyperFrames projects inside Claude Code — frame preview, timeline, trim/split/move/delete/undo, Studio selection bridge, and point-and-ask edits sent to Claude.

Second opinions inside Claude Code: GPT as fresh eyes when you go in circles, Codex acceptance of every handover, and Codex+Claude review of each change.

Measures a command: warmup and timed runs, median/p95/stddev and outliers, two commands compared or a saved baseline per project, and a pane with a block distribution plot. Bounded, one at a time, never during Claude's turn unless Claude asked.

Finds the commit that broke something: git bisect with your test command in a temporary worktree (your working tree is never touched), live progress in a pane, the culprit with its diff stat handed to Claude.

An HTTP tool for API work: status, timing, trimmed headers and a body shaped to fit; localhost runs freely, other hosts ask once a session; an /http pane of the session's requests with replay and copy-as-curl.

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.

Runs your dev server or watcher for the session, flags its errors above the prompt, and lets Claude read its output.

Keeps long sessions going through API errors and rate limits: resubmits after a backoff when idle, waits out rate limits with a countdown, never loops, and stops the moment you type.