turn-budget
VedantAndhale/claude-pro-kit
When one turn uses more than +5 session points or 500,000 uncached input tokens, writes a handoff from exact session data and copies it for a new session; the old session is never cleared. No model calls.
1,948 mods
VedantAndhale/claude-pro-kit
When one turn uses more than +5 session points or 500,000 uncached input tokens, writes a handoff from exact session data and copies it for a new session; the old session is never cleared. No model calls.
VedantAndhale/claude-pro-kit
Steers Claude to Edit instead of rewriting an existing file in full with Write: the first rewrite in a conversation goes through with a one-line note, a later one is held back once; a deliberate retry still goes through.
kakha13/claude
Translates the Georgian in each prompt to English before Claude reads it, without echoing the translation
kakha13/claude
Fixes the grammar and spelling of each English prompt before Claude reads it, and shows what changed
RANDSUM/randsum
RDN-conformant dice notation skills for Claude Code — roll dice, analyze probability, and create game specs for tabletop RPGs
KilimcininKorOglu/claude-code-mods
Shrinks each Bash result before the model reads it: per-command filters for git, test runners, linters, package managers, containers and file tools, the full output kept in a file.
KilimcininKorOglu/claude-code-mods
Shows the background shell tasks of the session on the status line or in the shared sidebar, with the oldest one's age, and stops one from the /bg-tasks pane.
KilimcininKorOglu/claude-code-mods
Keeps the 1-hour prompt cache warm for a window you set, or with no end in every session under always, with one cache-shared fork per idle stretch and one keep-warm message after a resume, arms a window for you after a paid cold write, and shows the cache state, the cold price and this session's cold writes.
KilimcininKorOglu/claude-code-mods
Measures the build artifacts of the repository, shows them on the status line from 5 GB, and deletes the ones you pick in the /disk-janitor pane; data directories are never listed.
KilimcininKorOglu/claude-code-mods
Shows the subscription usage limits, the per-model weekly ones such as Fable's included, under the prompt or in the shared sidebar with a reset countdown and a projection, opens a /limit-watch pane, gives the model a tool that reads them, logs once when a limit passes 80% and 95%, tells the model when one passes 80%, 90% and 95%, and stops sampling entirely with /limit-watch off.
KilimcininKorOglu/claude-code-mods
Loads MEMORY.md into the session and saves project learnings to it after every turn through a tool-less fork in the background, without blocking the stop.
KilimcininKorOglu/claude-code-mods
Keeps project and global memories in SQLite through a shared local daemon, hands the model the entries that match its file tool calls, prompts and subagent tasks, and saves new ones with a haiku consolidator after each main-loop turn.
KilimcininKorOglu/claude-code-mods
Shows this session's state in the sidebar: context fill, token totals, cost, model and effort, the Claude Code version, the other sessions of this machine, and the git branch and status.
KilimcininKorOglu/claude-code-mods
Shows each subagent of the session with its turns, time, model and tokens, the costliest first, yellow while it runs and green once it answered, and marks one that passed the token limit.
mucida-claude-mods/critical-decisions
Shows you, above the prompt, the critical decisions the agent made without being asked: red to rethink, yellow to know, each with a rethink button. Works out of the box for any kind of project; /critical-areas auto lets the agent learn what is critical in yours.
bruw/workflow-conductor
Terminal UI for planning, running and understanding complex agent workflows inside Claude Code.
drkokorev/cockpit-for-claude
Agent cockpit for Claude Code: live context, limits, cost, tools, files, tests and a guard for risky commands
Akramovic1/jev-pilot
TypeSafe's Jev decides how Claude Code works on each prompt: the main conversation's reasoning effort (low to xhigh, raised to max mid-turn when tool calls keep failing), each subagent's model, whether to split the work across subagents, and the one skill the prompt needs. Brings in custom OpenRouter models (a junior coder reviewed by Opus, or cheap bulk work) and Codex or OpenCode as...
xuanji86/claude-agentpane
A side pane for Claude Code that lists the subagents a session runs, what each is doing and what it costs in tokens, with each one's conversation a click away.
alexandernicholson/agent-router
Choose a model and effort for five agent roles and for agent team teammates with /agent-models, and inspect routing and usage. Requires Claude Code Mod function hooks enabled.
SmelterLabs/claude-account-switcher
Bill a Claude Code session to a different Claude subscription per project (a .claude/account marker), on demand (/account ), or with one click in the band above the prompt, through a local token-swapping relay. The desktop app keeps its own login.
noopz/commonplace
A knowledge vault Claude reads and keeps for any folder of notes: graph-indexed vault tools, private domains that stay sealed, connections to what you already wrote surfaced under answers, and [[note]] links in replies that are checked against the vault.
ice-lfernandes/claude-code-mods
Subagents at a glance: a card per agent with its mascot, step and tokens, a band above the prompt, a toast when one stalls, and a summary naming the heaviest agent when they finish
ice-lfernandes/claude-code-mods
Test runs at a glance: passing over total on the hint line under the prompt, colored by the result, a sparkline of failures across runs, the failing tests grouped by file, and toasts when the suite turns green or a test turns flaky
No tracking cookies, no third-party scripts. How we handle data