From water-footprint
Show the estimated fresh-water and energy footprint of Claude Code usage — current session breakdown by model, plus lifetime totals across all sessions on this machine. Use when the user asks about water usage, environmental footprint, or "/water-report".
How this skill is triggered — by the user, by Claude, or both
Slash command
/water-footprint:water-reportThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Generate a water-consumption report for the user's Claude Code usage.
Generate a water-consumption report for the user's Claude Code usage.
Run the report script, passing the current session transcript if you can locate it:
node "${CLAUDE_PLUGIN_ROOT}/scripts/water.js" --report
To include a per-model breakdown of the current session, find this session's transcript (the most recently modified .jsonl under ~/.claude/projects/<encoded-cwd>/) and pass it:
node "${CLAUDE_PLUGIN_ROOT}/scripts/water.js" --report --transcript "<path-to-transcript.jsonl>"
Present the script's markdown output to the user verbatim (it already includes water/energy totals, equivalents like glasses of water, a per-model table, and the assumptions used).
If the user asks how the numbers are derived, explain: energy is estimated per token by model tier (Haiku-class < Sonnet-class < Opus/Fable-class), multiplied by datacenter overhead (PUE), then converted to liters using water-use-effectiveness for on-site cooling plus off-site electricity generation. All constants are overridable with WATER_* environment variables documented in the plugin README.
npx claudepluginhub nlok5923/water-script --plugin water-footprintSearches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.
Guides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Implements vector databases with Pinecone, Weaviate, Qdrant, Milvus, pgvector for semantic search, RAG, recommendations, and similarity systems. Optimizes embeddings, indexing, and hybrid search.