board
Show the wanted-poster bounty board: this repo's TODO/FIXME/HACK debt priced as aging XP bounties
Show this session's prompt-cache state, the cold-comeback price, and the cache writes paid so far
Claude Code
$ npx -y skills add karanb192/claude-code-hooks --skill status --agent claude-code
Codex
$ npx skills add karanb192/claude-code-hooks --skill status -a codex -y
Cursor
$ npx skills add karanb192/claude-code-hooks --skill status -a cursor -y
Gemini CLI
$ npx skills add karanb192/claude-code-hooks --skill status -a gemini-cli -y
GitHub Copilot
$ npx skills add karanb192/claude-code-hooks --skill status -a github-copilot -y
OpenCode
$ npx skills add karanb192/claude-code-hooks --skill status -a opencode -y
Windsurf
$ npx skills add karanb192/claude-code-hooks --skill status -a windsurf -y
name: status description: Show this session's prompt-cache state, the cold-comeback price, and the cache writes paid so far disable-model-invocation: true
!`node "${CLAUDE_SKILL_DIR}/../../cache-tax.js" --render 2>/dev/null || node "${CLAUDE_PLUGIN_ROOT}/cache-tax.js" --render`
The card above is this session's prompt-cache state from its own transcript: which cache tier the main conversation is on, whether the cache is warm or has lapsed, how many tokens the next message re-writes if it is cold and what that costs at list price, and the session's cache writes, reads and full re-writes so far.
State what the next message will cost in one sentence. If the cache is cold and the context is large, say whether /clear plus a short handoff note is the cheaper move. Keep it short; do not re-run any commands.
🪝 Ready-to-use hooks for Claude Code, shipped as a 22-plugin installable marketplace: safety, automation, notifications, and more. 🌐 Live site & catalog Claude Code and agents like it run shell commands, edit files, and install packages on their own.
Show the wanted-poster bounty board: this repo's TODO/FIXME/HACK debt priced as aging XP bounties
Show this repo's context-cost leaderboard: the files that pulled the most tokens into context
List this repo's recorded dead ends: approaches already tried and abandoned, with reasons and cost
Show the CLAUDE.md compliance scorecard: which rules Claude actually follows vs ignores
Show your personal model-quality trend card (failure rate, edit churn, tokens/task by model version)
Preview the provenance receipt (prompts, est. spend, tests run, agent-authored lines) for the current session ledger
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.