defer-artifact

Tekkiiiii/the-agency

Band above the prompt: context %, tokens, model, cost, prompt-cache size/share/TTL countdown, 5h and weekly usage-window reset timers and next-request estimate; /ctx opens a detail pane; toast when a background subagent finishes; Jev router line (today's calls, tokens, USD, Haiku fallback) and outage warning, hidden unless the router usage log exists

h-zahran/delivery-kit

A side pane with robots: the main loop, every subagent and its tools, context, cost, rate limits and files touched

Zoria-Lind/cc-token-optimizer

Claude Code token optimizer — read de-dup, output trimming, cold-start guard, model-tier nudges, plus a live token / cache-hit bar and /token-status. Tokens only, no cost estimate (billing differs per gateway). 中文:会话 token 监视与档位导演,装完即用 —— 只报 token、不折算金额(各厂商计费口径不同)。

ofeklevy11/claude-code-hud

Session Tracker above the prompt box: context window with a /compact recommendation, 5-hour plan limit, prompt clocks and session cost.

andreichiritescu/claude-code-cache-keep-warm

Shows how long your session's prompt cache stays warm, and can keep it warm in the background while you are away

wasd96040501/taskcut

Compacts when the work moves on from one sub-task to the next instead of when the context window fills, including in the middle of a long turn. Once the context is past a floor, a model judges each step, reading what you asked for and where Claude has got to but never any tool output, for whether the work moves on from a finished piece to another; if it does, taskcut runs Claude Code's own compaction. Below the floor it does nothing and costs nothing.