Results for “M-i-k-e-l”

The learning loop: every main turn is kept in a ledger across sessions (phase, effort, steps, failed tool calls, agents, advisor calls), joined with the outcomes observed at tool.call (commits kept or reverted, test exits, PR verdicts and merges, no transcript) and the ones /insights writes, and the project's goals; probe sessions are counted and kept out; a phase whose evidence, read on the...

Läuft ein Testbefehl grün durch und liegen danach uncommittete Änderungen im Repo, bekommt Claude still einen Hinweis, den Arbeitsschritt zu committen. Keine Dauerabfrage, kein Git-Hook.

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.

Colours what needs you at the end of Claude's replies (must-know, decide now, decide later, defaults, your actions) and pins open decisions above the prompt

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).

Keep your API keys and tokens out of your Claude Code conversations: tokens pasted as keyfob: lines are stored before the model sees them, Claude asks for a key through the /keyfob panel, a guard stops Bash commands that would print one, and each command gets only the keys it needs from the OS keystore

Claude Code speaks through murmur (Kokoro on the Apple Neural Engine): turn summaries, needs-you alerts, background tasks, progress check-ins and rate-limit warnings, each session in its own voice (/say picks one)

Keeps the prompt cache warm while a session idles: every 50 minutes (configurable) one tiny request over the conversation prefix, so the entry does not lapse after an hour

Shows the state of Claude (working, permission, input, idle, background, compacting) in the iTerm2 tab subtitle.

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.

Sends each local session's status (what Claude is doing, task progress, context and usage) to the Claude Widget desktop app on this computer, and takes its Stop button

A live forecast above the prompt: context window fill (cached and uncached) updated on every model request, and the 5-hour and weekly usage limits as /usage reports them, kept in step across every session, with bars on a smooth color gradient, weather icons and reset countdowns.

/today: the day's agenda for Claude and for you. Calendar events, E3 deadlines and Reminders are read through the macos and nycu plugin scripts, shown as one line above the prompt with a countdown to the next event, and handed to Claude as a context block so it knows your day.

Picks the reasoning effort for each turn of the main conversation with a System One classifier (hosted Jev or a compatible service) and shows the level on the spinner and on the line that closes the turn. In shadow mode it shows and logs its pick and sends the session's effort; in enforce mode it sends the pick. Requires CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1.

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

Rules for Claude Code alerts: when one is worth sending (done, blocked, error, usage limits) and where it goes (chime, macOS notification, ntfy, Slack, Discord or a JSON webhook).

In a worktree session, tells Claude up front which commands the worktree guard refuses (heredoc and inline-script edits, multi-line scripts, cd to computed paths), so it uses Edit and plain commands instead of retrying.

Git only when you asked: commits, pushes, pull requests, merges and destructive git commands run only when your latest message (or /ship, /kickoff (also as /progress-pane:kickoff), or your answer to Claude's question) allowed them; everything else is refused with a note telling Claude to ask. No UI.

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.

Mission control for Claude sessions, in a Notebook look: a band and /progress pane in every session (model, effort, tokens, context, agents, gate, git), and with a worklog a validated worklog tool Claude updates at every step (done only after a green gate), facts the mod sees for itself (gate runs, commits, branch, agents, context and cost), drift hints where the two disagree, a band above the...

カニード が Claude の作業中にダンジョンを自動探索する Claude Mod。回復は Lv アップとテスト成功、あとはマップで見つけたショップだけ。倒れると Lv 1 からやり直し。会話ログのパス・#N・URL もクリックで開ける。Needs function hooks (CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1) and an interactive terminal.

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.

The Loadout's core work board and orchestration loop for Claude Code. Tickets are classified into categories that route each one to a concrete model and effort, then dispatched to token-gated executors; side issues you mention mid-task get captured on the spot, and a live, self-hosted Kanban dashboard spans every project you work in.

Right-to-left for Claude Code mods: one file to copy into a mod that orders Hebrew and Arabic right on every surface, aligns wrapped text right, draws markdown, cards, tabs, tables and SVG headers, and reorders text for the terminal