Claude Code Prompt Cache Mods

Show session quality, context fill, cache countdown and usage limits above the prompt

Keeps project notes, catches Claude's usual slips, warms the cache, resumes sessions

Keep a big chat's prompt cache warm and warn before an expensive cold send

Shows when your prompt cache expires and what rebuilding it would cost

Keep an idle session's prompt cache warm before the 1-hour cache TTL lapses

Show turn number, cost, cache countdown and context fill above the prompt

Keeps the prompt cache warm while idle and holds the first cold-cache prompt

Shows when your chat's prompt cache goes cold and what re-warming costs

Holds a cold cache send and shows the rewrite cost before you pay for it

Show prompt-cache time left, hit rate and misses below your status line

Keeps Claude Code's prompt cache warm and shows what a cold cache costs

Show context-window fill and a prompt-cache countdown above the prompt

Passive 50-minute prompt-cache reminder with a keyboard/mouse panel: keep warm, ping once, or compact, with live cost estimates

Prompt-cache hit rate in one row above the prompt, with how long the cache stays warm and a Keep warm switch that refreshes it while you are away

Compacts the main conversation once it has sat idle for idleMinutes, while the prompt cache is still warm, and hands every compaction of the main…

Compacts at the right moment: after a commit or green tests, a minute before the prompt cache expires, or when Claude asks for it with its own…

See your Claude Code session at a glance: context left, cost, today's and month-to-date spend, rate limits, git diff and PR status, right above the…

One quiet line above the prompt: context, 5-hour and weekly usage, whether the prompt cache is warm, and a Clear & continue button

Picks low, medium or high effort for each prompt, keeping the prompt cache warm

Keeps an idle session's prompt cache warm with a short prompt 2 min before it expires; capped per model, the last one a handoff

Prompt cache status above the prompt: how long the cache stays warm, what a re-cache would cost, plan limits near the cap

A prompt-cache countdown in the prompt footer, beside the model and effort: how long until your next message has to re-cache the whole conversation

A band above the prompt that counts down to your prompt cache expiring and shows what it costs your next message

Keeps the prompt cache warm while a session sits idle: shortly before the cache would expire, a small background request re-reads it, without…

Prompt cache, context and plan limits at a glance, in the prompt footer and above the prompt

Compacts an idle interactive session shortly before its prompt cache expires, so coming back later doesn't re-read the whole context uncached

Shows the model's real output speed, token and prompt-cache stats in a docked sidebar beside the transcript

Clawd, a token-saving assistant: trims noisy tool output and pasted logs before they fill your context, tells you when to compact (and does it in one…

A fuse above the prompt that burns down with the prompt cache, with context and rate limit meters and buttons to keep the cache warm or compact

Warns once before a message that will cost far more than usual: a large Claude Code context whose prompt cache has expired, or a model or effort…

Prompt-cache countdown, cost to re-warm, usage limits, cold-cache warnings and one-click handoff → clear & continue

Stop wasting tokens: keeps your prompt cache warm through breaks with /keepwarm, shows when it expires and what each answer costs

When an idle session's prompt cache is about to expire, summarizes it while the cache is still warm; when you come back, pick A (keep the full…

Shows how long the prompt cache stays warm and suggests compacting a large context at the right moment

J.A.R.V.I.S. HUD: arc-reactor spinner, live telemetry band (context, tok/s, agents by model), subagent uplink animations, input alerts, a…

Measures the prompt cache for a team, in Claude Code and, with its command-line companion, Codex CLI and Devin CLI: hit rate per session, subagent…

Shows when a session gets heavy or its prompt cache is about to go cold, and parks a session so the next one can resume it

A status line under the prompt: context, cache hit rate, cache TTL countdown, today's spend for this project, and why a turn missed the cache

Change the prompt-cache TTL (5m, 1h or automatic) of one Claude Code chat with /cache: instantly, with no model turn, for the main chat, its…

A countdown to when the conversation's prompt cache expires, in the prompt footer before the model name

Live countdown above the prompt until your session's prompt cache expires, with an optional keep-alive that keeps it warm while you're away