Results for “pa”

A shot clock for the prompt cache's TTL: a small countdown in the bar under the prompt, and a big LED clock above it for the last seconds before the next turn pays a full cache write.

A pane with the tree of child chats spawned from this chat: what each is doing, which branch it sits on, and what is still not merged. Read-only, no model calls.

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...

Routes each Claude Code turn to the model and effort TypeSafe's Jev picks, weighed against what a switch costs, and compacts with Jev instead of a lossy summary.

Toolbox for Claude Code's Workflow tool — author deterministic multi-agent workflow scripts (workflow-composer, with the @workflow-toolbox compile-time pattern toolkit as its standard library), scaffold a build-clean workflow skeleton from a spec (toolkit-scaffold), diagnose a failed run from its journal and decide whether resumeFromRunId helps (workflow-debugger), re-verify the runtime...

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...

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.

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

Agents info Mod (Claude Code 2.1.287, Mods API in early access): starting agent, timeline of agents per prompt (new, resumed, forked), resolved model and effort of each, tokens per agent × model × effort, 5 h / 7 day limits with forecast, alerts. Read-only: alters and blocks nothing.

Tools menu for Claude Code: Clean View, Prompt Upgrade, model/effort control panel, Agent Dock, Roadtrip minigame.

VS Code style file tree of the session's working directory in a pane

Claude Mod Manager: fetches the cmod program for every mod, runs the uninstall step of each mod Claude Code removes, and carries calls from one mod to another.

Side panel that opens when Claude edits files: the whole folder tree, every edited file numbered in order, and a highlighted trail from the project root to the file being edited. /folder-map toggles it.

Stops Claude from passing a check by lowering the bar: weakened or deleted tests, new suppressions, relaxed config, softened CI, lowered coverage, skipped git hooks.

What Claude carries, in colour: a bar above the prompt with system, rules, conversation and large tool results, and a pane to turn rules off for the session, edit and save them, and take out large results.

Open, start and stop this project's browser apps from the Git panel

A band above the prompt with context size, per-turn cost and the prompt-cache countdown. Past the handoff line it counts down 60 s, writes a handoff file with a fork, runs /clear and resumes in the new conversation; a new conversation lists unclaimed handoff files, press 1 to resume.

Stops Claude before it deletes or overwrites files: a side panel lists every folder and file at stake, with Cancel and Allow buttons

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.

astir inside Claude Code's terminal: a footer count of agents waiting on you, a warning line when no one would be told, and /astir, a pane with a key that takes you to the one waiting.

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.

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.

Notices files that land in Downloads while you work (PDFs, 3MF models, images, notes) and offers them in a band above the prompt: Attach puts @"path" mentions in the prompt box, Dismiss clears them. /downloads lists the newest files and attaches any by number. 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.