jev-auto-compact
notque/vexjoy-agent
Jev-powered verbatim compaction: once context reaches 60%, prunes stale tool calls with zero generation. Skips (never falls back to the LLM summarizer) when nothing is prunable; records evidence for learning.db.
8,943 mods
notque/vexjoy-agent
Jev-powered verbatim compaction: once context reaches 60%, prunes stale tool calls with zero generation. Skips (never falls back to the LLM summarizer) when nothing is prunable; records evidence for learning.db.
data-goblin/claude-code-filetree
An IDE-style file tree for Claude Code that shows what Claude is doing and where in files
tobihagemann/turbo
A human-gated agentic software factory: you decide what to build and judge the result, while skills shape, build, polish, and ship the change, and learn from it.
karanb192/cache-tax
A Claude Code mod that keeps the one-hour prompt cache warm during breaks and asks before a cold send, showing its estimated rewrite cost. Warming uses model requests and costs tokens. Requires Claude Code 2.1.287+.
sonichi/sutando
Feeds a Claude Code session from a Sparrow task inbox and writes its replies as Sparrow result files
sonichi/sutando
Observes the Claude main loop for HealthStatus and draws a compact status band above the prompt
sonichi/sutando
Turns GitHub pull request events from gh webhook forward into session turns, with no polling and no Monitor expiry
sonichi/sutando
Runs the session's task watcher and starts a turn for each task it announces, in place of a Monitor
JohnnyVizz/claude-kit
Progress bar above the prompt for /savvy-flow, plus an agents panel (/agents-info): running, finished and planned subagents with model, task progress, context, cost and time.
JohnnyVizz/claude-kit
Band above the prompt: turn number, output speed, turn and session cost, prompt cache countdown and context fill; notifies before the cache expires.
Atoll92/agent-standup
A line above your Claude Code prompt when another Claude Code session on this computer needs you (an approval, an answer), and a toast when one finishes its turn. Reads only the status files Claude Code keeps for its sessions; sends nothing.
qf-studio/navigator
Finish What You Start - Sessions that last, AI that learns, Features that ship. Context engineering + Theory of Mind + Knowledge Graph + Loop Mode + Task Mode. Features Project Knowledge Graph (unified search, experiential memory), unified workflow orchestration, auto-update on session start, ToM-based verification checkpoints, bilateral modeling, quality detection, enhanced context markers...
athola/claude-night-market
Resource optimization and performance monitoring toolkit for efficient Claude Code workflows
athola/claude-night-market
Autonomous agent orchestrator for full development lifecycles with zero human input, session budget management, and crash recovery
HeyCubit/effortless
Sets the reasoning effort for every prompt automatically, shows it under the prompt box, and counts down how long the prompt cache stays warm.
HeyCubit/effortless
While Claude works, the chat shows one tall pixel-art card of Clawd instead of every step. Its buttons sit on the card, which minimizes to one line, and under the newest answer; /textless toggles it too.
scasella/claude-flightdeck
Flightdeck: a live agent dashboard for Claude Code. Main model vitals, an on-call architect, every permission check, subagent cards and swimlanes, a turn receipt and a session log, all from real session events
iamumeransari/claude-show-your-work
Claude shows its finished work right in your terminal: screenshots, videos of it clicking through your app, and synced before/after QA
hellosverre/claude-skins
Skins for Claude Code: tool rows that open onto their input and answer, highlighted code, diff, table, math, Mermaid and shell cards, links, folding, a usage band, a calm mode and fifteen themes. /skin swaps them live.
yonatangross/orchestkit
Displays lesson hint cards when tool calls match known patterns. Advisory only: a lesson never blocks a tool call.
yonatangross/orchestkit
Recalls the few memories related to each prompt you send (never on automated turns or file tool calls): one line for the human, one context entry for the model. Local files only, no network on the hot path.
yonatangross/orchestkit
Shows CI status lights above the prompt while a promote PR (base main) is open. One REST page per minute, PR-open only. Cancelled is not-pass.
yonatangross/orchestkit
Masks secret values in tool results before the model reads them: named vendor variables, value-shape patterns, and high-entropy tokens. No reveal path.
yonatangross/orchestkit
Review enhanced prompts before sending them: short, stack-aware rewrites
No tracking cookies, no third-party scripts. How we handle data