菜单
Report the session's Honey savings: output tokens, CO2, and CO2/$ saved vs a no-Honey baseline, via the committed EcoLogits port.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | honey-eco |
| description | Report the session's Honey savings: output tokens, CO2, and CO2/$ saved vs a no-Honey baseline, via the committed EcoLogits port. |
| homepage | https://github.com/Green-PT/honey-for-devs |
| license | MIT |
Surface the numbers the carbon badge is based on. Never estimate by hand — run the committed report so the figure matches hooks/eco.js (the verified EcoLogits v0.8.2 port) exactly.
Run, from the repo root — zero-dependency, reuses the same hooks/eco.js the badge uses:
node scripts/eco-session.js # newest session
node scripts/eco-session.js --transcript PATH --mode full
Then report terse — output tokens, CO₂eq (g), and saved (~R% vs no-Honey) — in a line or two. Keep the exact numbers the script prints; don't round away precision.
For the authoritative breakdown (usage + embodied + primary energy) the user can run the Python path, which needs the real package:
pip install ecologits && python scripts/eco_report.py
The params are speculative (Anthropic discloses none). The badge shows served impact — EcoLogits' single-stream (batch-1) ceiling divided by serving_concurrency (continuous-batching amortization); eco-session.js/eco_report.py also print the raw ceiling. State that once, briefly, then give the number. The badge renders only in Claude Code (its transcript is all Claude models).
Report only — don't change config or mode (that's the /honey command). The number is a range, not a meter reading; present it as one.
Compress-Cache-Retrieve huge repetitive array tool output before it hits context: keep a sample, cache the rest, leave a hash.
Compress-Cache-Retrieve for huge, repetitive array tool output (logs, scan results, time series, event streams) before it enters context. Keeps an informative sample — endpoints, anomalies/change-points, head/tail — drops the redundant rest to a local cache, and leaves a retrievable hash. Use when a tool returns a long uniform JSON array you must read but mostly skim, and the full set is one command away if needed. Lossy-but-recoverable.
Write less code and say less about it: YAGNI, stdlib-first, terse prose. Cuts agent token cost on every coding and writing task.
Write less code and say less about it. Applies YAGNI and stdlib/native-first so the agent writes the minimum code that needs to exist, and responds tersely — stripping filler, hedging, and pleasantries while keeping code, identifiers, and technical terms exact. Use whenever writing, modifying, refactoring, reviewing, or explaining code, or any response where output volume drives token cost — even if the user never says "minimal" or "concise". Especially in agentic coding, where the volume of generated code and prose runs up the bill.
Honey for plain Claude — the terse-prose core with no agent-harness features. Paste into a claude.ai Project's custom instructions, a Style, or an API system prompt. Strips filler, hedging, and pleasantries from every response while keeping facts, names, numbers, steps, and code exact. No tools required.
Read huge dense read-only text as PNG pages via pxpipe export: ~60-75% fewer input tokens. Lossy on exact strings; never for files you will edit.