superpowers
claudecodexCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Token telemetry for Claude Code and Glitch: measure spend by tool, session, model and pipeline. Measurement-only by default; truncation is opt-in and off.
Plugin tokendog from marketplace tokendog in jawahar4k/tokendog. 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.
tokendog-frugalFrugal Claude Code tool-use habits that cut token spend without losing quality. Apply during any coding task involving Read, Grep, Glob, Bash, or MCP tool calls.
tokendog-hygieneSession-hygiene practices that stop token spend from ballooning over long sessions. Use when a session has run long, switched topics, or accumulated large pasted context.
/tokendog:tokendog-auditAudit token spend for the current session (or a given session id), broken down by tool.
/tokendog:tokendog-bandsShow where your tokens actually are — context-size bands, concentration, and peak context.
/tokendog:tokendog-budgetView or set TokenDog spend budgets (daily / session / alert threshold / webhook).
/tokendog:tokendog-costShow a TokenDog token-spend rollup (Claude Code + Glitch) for this environment.
/tokendog:tokendog-doctorTokenDog environment check — telemetry sink, tiktoken, Glitch DB.
/tokendog:tokendog-effectDid an optimization actually reduce tokens? Cost-by-turn-position, cache-TTL economics, and tool-payload sizes before vs after a change.
/tokendog:tokendog-initInstall TokenDog's canonical CLAUDE.md + settings.json into this repo (preserves your org section).
/tokendog:tokendog-learningsLessons captured from sessions in this repo — list, forget one, or share now.
bulk-readerRead one or more large files and return a short summary with file:line references. Use when a file is too large to be worth carrying in the main window for the rest of the session. The read stays in this subagent's context; only the summary comes back.
tokendog-costruns: python3 ${CLAUDE_PLUGIN_ROOT}/mcpServers/tokendog-cost/server.py
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/token_count.py
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/budget_enforce.py
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/read_guard.py
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/token_count.py
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/truncate_output.py
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/token_count.py
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/session_summary.py
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/budget_alert.py
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/split_refresh.py
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/token_count.py
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/sink_health.py
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/surface_autorefresh.py
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/floor_advice.py
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/learn_apply.py
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/learn_capture.py
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/learn_capture.py
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
CMEM Pro for the Claude app - hooks stream tool use to cmem.ai and inject observations into new sessions and agents
3 skills · 1 MCP server · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
Observability plugin for Claude Code with MLflow tracing
AI-supervised issue tracker for coding workflows
1 skill · 1 agent · 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.