honey-chat
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…
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
$ npx -y skills add Green-PT/honey-for-devs --skill honey-ccr --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/honey-ccrContext preview
The summary Claude sees to decide when to auto-load this skill.
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
name: honey-ccr description: >- 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. license: MIT
The cheapest token is the one not sent. A 500-row log read for one error line costs 500 rows of context. CCR keeps the rows that carry signal and caches the rest — recoverable by hash, so nothing is lost.
Borrowed from headroom's SmartCrusher. **Lossy by design** — only for data you skim, never for payloads where every row matters (e.g. a code-review handoff where the implementer needs all findings; use `eson encode` losslessly there).
tool-that-spews-json | eson crush # → sampled view + sentinel; originals cached eson retrieve <hash> # → the full original array, verbatim
`crush` prints the kept sample plus a sentinel `{"_ccr":"<<ccr:HASH N_rows_offloaded>>"}`. When you need a dropped row, read the hash from the sentinel and run `eson retrieve <hash>`.
While Honey is active, a registered PostToolUse hook applies this automatically to Bash output — no opt-in per call. Big uniform JSON arrays (≥20 items, ≥2k chars) are crushed; repetitive text (≥25 lines) gets consecutive repeats collapsed to `⟨×N⟩`. The original is always stashed first, and the rewritten result ends with the exact `eson retrieve <hash>` command that restores it. `/honey off` disables the hook; history already in context is immutable — this fires at entry, the only place a hook can act.
Caveat: Claude Code builds affected by anthropics/claude-code#68951 ignore the hook's Bash rewrite, making it inert (a session-start warning tells you when this applies). Manual `some-tool | eson crush` piping is unaffected — prefer it there.
Write less code and say less about it. Honey (I Shrunk the AI) by GreenPT is a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — making agents emit less code and less prose without losing correctness.
Repo: Green-PT/honey-for-devs
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…
Rewrite a memory or context file (CLAUDE.md, AGENTS.md, a todo or notes file) into Honey-terse form so it costs fewer input tokens every session, without…
Harvest every `honey:` comment in the codebase into a debt ledger, so the deliberate shortcuts Lever 1 leaves behind get tracked instead of rotting into "later…
Same pixels, fewer tokens — for user-facing deliverables where visual polish is the spec. Use when building or editing a landing page, marketing site, hero,…
Report this session's output tokens and CO₂ by running the repo's committed EcoLogits port, plus the modelled CO₂/$ saved vs a no-Honey baseline — always…
Show Honey's benchmark scoreboard — the committed quality and token results per task tier (code, user-facing, agent-to-agent) from bench/. Reports only the…