Status line

Keeps credentials out of your code, your shell commands and Claude's context: blocks hard-coded secrets in edits, asks before commands with literal keys, redacts secrets from tool results and flags them in prompts.

Redacts API keys, tokens, private keys and .env secrets from tool output before the transcript stores it and before the model reads it.

Picks the model and the reasoning effort for each task with TypeSafe's Jev, a System One decision model reached either through TypeSafe's own API or the Vercel AI Gateway. Routes subagent models at agent.spawn and the main loop's effort and model at turn.step, in both directions, falling back to the engine's built-in classifier when no key is set.

Know whether your auto-memory index loaded whole. Reports the index's size against a limit you set at every session start, names the entries past the cut, and warns when a session pushes it over.

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...

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

Verinoda in Claude Code: keeps the code index fresh while Claude edits, checks each edit for names that do not exist, reviews commits, lists what could be changed for you to choose (/verinoda-improve), and shows it all in a Turkish pane with an animated mascot.

Prompt-cache meter above the Claude Code prompt: how many tokens each request read from, wrote to and sent past the cache, a live countdown to the cache's expiry, and what to do about it (keep going, compact or clear). The TTL follows Claude Code's own rules for your account (1 hour on a Claude subscription, 5 minutes on an API key, cloud provider or usage credits, plus the TTL variables and...

Verinoda in Claude Code: keeps the code index fresh while Claude edits, checks each edit for names that do not exist, reviews commits, lists what could be changed for you to choose (/verinoda-improve), and shows it all in a Turkish pane with an animated mascot.

Keeps secrets out of Claude's context: gitleaks scans every tool output, prompt and attachment before the model reads it, and you decide what the model sees.

A vim-style status bar in the Claude Code footer: editor mode, permission mode, model, effort, git state, usage and cursor; numbers the draft's lines and keeps the prompt box taller.

Picks the model and reasoning effort for each task with TypeSafe's Jev. Routes subagent models at agent.spawn and subagent and main-loop effort at turn.step, with optional main-loop model routing. Falls back to the engine's built-in classifier when no key is set.

Before each prompt reaches the model, TypeSafe's Jev ranks your installed skills against it and attaches one line naming the skill to load. Sends the prompt text to api.typesafe.ai. Needs function hooks (early access).

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; an MR whose branch lacks the target's latest commit is refused; a pushed series must leave the project working at every commit; commit messages kept tidy (format and the issue it is about, then a Haiku review of the body).

Hinweise, wann /compact, /clear oder Weitermachen sinnvoll ist: Kontextfüllung, Prompt-Cache, Auto-Compact und Limits. Schreibt die Werte für die Statuszeile, die Warnungen zeigt offene-punkte über der Eingabe; /kontext zeigt Details, /kontext test probiert Einblendung, Statuszeile und Systemmeldung aus.

Idle-session guard for Claude Code's 1-hour prompt cache (macOS): about 50 idle minutes after the last turn of a large session it notifies you, optionally after a cache-read fork judges whether to compact, keep warm or leave it; every request and change it makes is audited. Derived from cache-tax (MIT, Karan Bansal).

Picks the model and the reasoning effort for each task with TypeSafe's Jev, a System One decision model reached either through TypeSafe's own API or the Vercel AI Gateway. Routes subagent models at agent.spawn and the main loop's effort and model at turn.step, in both directions, falling back to the engine's built-in classifier when no key is set.

KB health in the status line: the kb-intelligence snapshot's verdicts, and whether kb-serve runs the code on disk

Choose the model versions Claude and its subagents may use: /models lists the newest of each family from Anthropic's Models API (older versions one key away); block a version, or a family's new ones, and subagents, workflows and /model asking for it are refused or moved to an allowed version. One list shared by every Claude Code window on the machine; a repo can keep its own.

Keeps the prompt cache warm while you step away: a short poke before the cache expires, so the next turn reads the cache instead of writing it again. A row above the prompt turns it on and off and edits the message. Near the usage limit it books Claude a wake right after the reset.

Prompt-cache meter above the Claude Code prompt: how many tokens each request read from, wrote to and sent past the cache, a live countdown to the cache's expiry, and what to do about it (keep going, compact or clear). The TTL follows Claude Code's own rules for your account (1 hour on a Claude subscription, 5 minutes on an API key, cloud provider or usage credits, plus the TTL variables and...

Reads Claude's responses aloud with local Kokoro neural voices (macOS say as fallback), detecting English and Spanish per paragraph: a speaker button on each reply block, /speak and /speak-stop, /speak-install to set up Kokoro, and /speak-engine, /speak-voice and /speak-rate settings.

Keeps unattended sessions going: continues after usage limits reset, retries API overload with backoff, resumes cut-off responses, and compacts idle sessions before the prompt cache expires.

The record of orchestrated work: runs of units and tasks, the subagents spawned for them, each gate's verdict and the findings reviewers report, summed up in the status line while there is something to say. It can follow a superpowers plan document as its input. Run /ledger.