/honey-compress
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 losing meaning. Backs up the original first. Use when asked to shrink or compress context files, trim CLAUDE.md, or cut
$ npx -y skills add Green-PT/honey-for-devs --skill honey-compress --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/honey-compress
Context preview
The summary Claude sees to decide when to auto-load this skill.
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 losing meaning. Backs up the original first. Use when asked to shrink or compress context files, trim CLAUDE.md, or cut
SKILL.md
honey-compress.SKILL.mdname: honey-compress
description: >-
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
losing meaning. Backs up the original first. Use when asked to shrink or
compress context files, trim CLAUDE.md, or cut per-session input cost. Prose
only — never code, config, or data.
license: MIT
Honey Compress
Apply Lever 2 to a file the agent re-reads every session. The cheapest token is the one not re-sent — a one-time rewrite that saves on every future load.
Do
1. **Back up first.** Copy `FILE` → `FILE.original.md`. If that backup already exists, stop and ask — never clobber a restore point. If no backup can be written, refuse. 2. **Rewrite the prose tersely** — drop wind-up, hedging, narration, and redundancy; fragments over paragraphs; merge guidance that repeats. 3. **Preserve every distinct instruction** — terser words, identical rules. If unsure whether a line changes behavior, keep it verbatim. 4. **Report** original vs new line/byte count and the backup path.
Keep exact — never compress
- Code blocks, commands, paths, identifiers, versions.
- Any **load-bearing directive** — MUST/NEVER rules, and anything touching auth, secrets, money, migrations, or deletes. Compressing an instruction that changes behavior moves cost, it doesn't remove it.
Don't
- Don't touch code, config, or data files — prose context only.
- Don't merge two rules into one if they differ in effect.
- Don't compress a file you can't back up.
Boundaries
Reversible by design — `FILE.original.md` is the restore path. Verify the rewrite still carries every rule before reporting done.
Read more
name: honey-compress description: >- 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 losing meaning. Backs up the original first. Use when asked to shrink or compress context files, trim CLAUDE.md, or cut per-session input cost. Prose only — never code, config, or data. license: MIT
Honey Compress
Apply Lever 2 to a file the agent re-reads every session. The cheapest token is the one not re-sent — a one-time rewrite that saves on every future load.
Do
1. **Back up first.** Copy `FILE` → `FILE.original.md`. If that backup already exists, stop and ask — never clobber a restore point. If no backup can be written, refuse. 2. **Rewrite the prose tersely** — drop wind-up, hedging, narration, and redundancy; fragments over paragraphs; merge guidance that repeats. 3. **Preserve every distinct instruction** — terser words, identical rules. If unsure whether a line changes behavior, keep it verbatim. 4. **Report** original vs new line/byte count and the backup path.
Keep exact — never compress
- Code blocks, commands, paths, identifiers, versions.
- Any **load-bearing directive** — MUST/NEVER rules, and anything touching auth, secrets, money, migrations, or deletes. Compressing an instruction that changes behavior moves cost, it doesn't remove it.
Don't
- Don't touch code, config, or data files — prose context only.
- Don't merge two rules into one if they differ in effect.
- Don't compress a file you can't back up.
Boundaries
Reversible by design — `FILE.original.md` is the restore path. Verify the rewrite still carries every rule before reporting done.
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
Other skills on honey.
- /honey-ccr
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
Open skill - /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 prompt. Strips filler, hedging, and pleasantries from every response while keeping facts, names, numbers, steps, and code
Open skill - /honey-debt
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 means never". Flags markers with no revisit trigger — those are the ones that go permanent silently. Use when the user
Open skill - /honey-design
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, pricing/feature section, dashboard, or any HTML/CSS UI component. Keeps the full rendered design (layout depth, hierarchy,
Open skill - /honey-eco
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 labelled with the bench stamp it came from. Use when asked how much Honey saved, the session's carbon/token footprint, or to
Open skill - /honey-gain
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 reproducible committed figures, never invents per-repo numbers. Use when asked how much Honey saves, how it compares to
Open skill