superpowers
claudecodexCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
A fair, defensive guardian for a solo builder's usage meter, ported from CONCIERGE's bash token-scheduler to one tested Rust binary (tf). Estimates fan-out cost with a converging estimate→actual EWMA, requires an explicit +Xk budget, throttles waves, and gates each wave against the LIVE rate-limit window (fail-closed) — halting before a paid lockout and resuming cheaply from a per-job ledger that records only what's LEFT. Off-peak runs reserve a morning allowance. Durable, session-safe scheduled jobs (project + per-machine registry) re-arm after a crash and install as OS-cron. A Stop hook writes the session.json .tokens actual-spend signal that makes convergence work. Determinism is proven by cargo frozen-vectors + a byte-for-byte differential against the bash oracle. /schedule routes a job; the token-scheduler skill is the discipline that calls tf.
Plugin scheduler from marketplace token-fairness in agentic-underground/token-fairness. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.
checkVerify TOKEN-FAIRNESS's dependencies are installed and reachable — a ✓/✗ table by tier. Trigger with /scheduler:check (or "check the scheduler prerequisites", "is tf installed?"). The deterministic core is a static binary (bin/tf) with zero runtime deps; the hooks use jq, off-peak cron uses flock +
tf-helpShow the token-fairness CLI surface. Trigger with /scheduler:tf-help (or "what tf commands are there?", "show the tf help"). Runs `tf --help` LIVE through the hook wrapper and surfaces the binary's own output verbatim — the subcommand list is never hardcoded, so it can never drift from the installed
tf-reportShow the token-fairness honesty report for this project. Trigger with /scheduler:tf-report (or "show the honesty report", "what has this project spent?"). Runs `tf report . --honesty` LIVE through the hook wrapper and surfaces the output verbatim. If the report tool exits non-zero (e.g. a bad path),
tf-resetRe-baseline the token-fairness session. Trigger with /scheduler:tf-reset (or "reset the budget baseline", "re-baseline the session"). WARNS first if a cost-journal entry is still open, then runs `tf budget set --reset` and `tf session-boundary` and surfaces the new baseline. type: mutating output: t
token-schedulerRun a large, token-intensive, wide-reaching job SAFELY — without ever exhausting the usage limit or causing a paid lockout. Trigger with /concierge:schedule (or "this is a big fan-out", "review every reviewer/handler", "run this overnight", "schedule this off-peak", "will this blow my token budget?"
/scheduler:scheduleRun a large, token-intensive fan-out SAFELY — estimate cost, require an explicit +Xk budget, gate every wave against the LIVE 5-hour window, halt before a lockout, and run off-peak (22:00–08:00) while reserving your morning allowance.
/scheduler:tf-helpShow the token-fairness CLI surface — runs `tf --help` live and surfaces every subcommand, then lists the slash commands that wrap them. The list is never hardcoded; it always reflects the installed binary.
/scheduler:tf-reportShow the token-fairness honesty report for this project — runs `tf report . --honesty` live and surfaces the output verbatim. If the report tool errors (e.g. a bad path), the error is surfaced, never a fabricated report.
/scheduler:tf-resetRe-baseline the token-fairness session — runs `tf budget set --reset` then `tf session-boundary`, confirming the new baseline. Warns first if a cost-journal entry is still open, so an in-flight unit of work is not silently re-baselined.
tfruns: bash ${CLAUDE_PLUGIN_ROOT}/hooks/tf-hook.sh mcp
bash ${CLAUDE_PLUGIN_ROOT}/hooks/tf-hook.sh preflight-fanout 2>/dev/null || true
bash ${CLAUDE_PLUGIN_ROOT}/hooks/tf-hook.sh preflight-spend 2>/dev/null || true
bash ${CLAUDE_PLUGIN_ROOT}/hooks/ensure-statusline-widget.sh 2>/dev/null || true
bash ${CLAUDE_PLUGIN_ROOT}/hooks/tf-hook.sh session-boundary >/dev/null 2>&1 || true
bash ${CLAUDE_PLUGIN_ROOT}/hooks/tf-hook.sh snapshot 2>/dev/null || true
bash ${CLAUDE_PLUGIN_ROOT}/hooks/startup-report.sh 2>/dev/null || true
bash ${CLAUDE_PLUGIN_ROOT}/hooks/inject-token-safety.sh 2>/dev/null || true
bash ${CLAUDE_PLUGIN_ROOT}/hooks/offer-scheduler.sh 2>/dev/null || true
bash ${CLAUDE_PLUGIN_ROOT}/hooks/tf-hook.sh snapshot 2>/dev/null || true
bash ${CLAUDE_PLUGIN_ROOT}/hooks/spend-capture-throttled.sh 2>/dev/null || true
bash ${CLAUDE_PLUGIN_ROOT}/hooks/tf-hook.sh snapshot 2>/dev/null || true
bash ${CLAUDE_PLUGIN_ROOT}/hooks/session-tokens.sh 2>/dev/null || true
bash ${CLAUDE_PLUGIN_ROOT}/hooks/tf-hook.sh spend --capture >/dev/null 2>&1 || true
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
AI-supervised issue tracker for coding workflows
1 skill · 1 agent · hooks
Use Superset to spawn agents, create workspaces, manage tasks, and schedule automations from Claude Code.
14 skills · 1 command
MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows
18 skills
Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.
2 skills · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.