/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
$ npx -y skills add Green-PT/honey-for-devs --skill honey-debt --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-debt
Context preview
The summary Claude sees to decide when to auto-load this skill.
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
SKILL.md
honey-debt.SKILL.mdname: honey-debt
description: >-
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 says "honey debt", "/honey-debt",
"what did honey defer", "list the shortcuts", or "what did we mark to do later".
One-shot report; changes nothing.
license: MIT
Honey Debt
Lever 1 trades code for a known ceiling. That trade is only honest if someone can see it later. Every deliberate simplification carries a `honey:` comment naming its ceiling and the trigger to revisit; this collects them into one ledger.
Scan
grep -rnE '(#|//|--|/\*) ?honey:' . --exclude-dir={node_modules,.git,dist,build,vendor}Each hit is one row. The comment prefix is what keeps prose that merely mentions the convention out of the ledger.
Output
One row per marker, grouped by file:
`<file>:<line> — <what was simplified>. ceiling: <the limit>. trigger: <when to revisit>.`
The convention is `honey: <ceiling>, <trigger>`, so both fields come straight from the comment. Add `git blame -L<line>,<line> -- <file>` per row only if the user asks who owns it.
Tag any marker with no trigger `no-trigger` — a ceiling without a revisit condition is the shape that rots. End with:
`<N> markers, <M> with no trigger.`
Nothing found: `No honey: debt. Clean ledger.`
Boundaries
- **Report only.** Don't fix, refactor, or remove markers — the user decides what to
pay down. Offer, don't act.
- **Don't invent debt.** A `TODO`/`FIXME` is not a `honey:` marker; mention the count
separately at most once if it's large, don't fold it into the ledger.
- **Don't editorialise per row.** The ledger is data. Save any judgement for one
closing line, and only if something is genuinely alarming.
Read more
name: honey-debt description: >- 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 says "honey debt", "/honey-debt", "what did honey defer", "list the shortcuts", or "what did we mark to do later". One-shot report; changes nothing. license: MIT
Honey Debt
Lever 1 trades code for a known ceiling. That trade is only honest if someone can see it later. Every deliberate simplification carries a `honey:` comment naming its ceiling and the trigger to revisit; this collects them into one ledger.
Scan
grep -rnE '(#|//|--|/\*) ?honey:' . --exclude-dir={node_modules,.git,dist,build,vendor}Each hit is one row. The comment prefix is what keeps prose that merely mentions the convention out of the ledger.
Output
One row per marker, grouped by file:
`<file>:<line> — <what was simplified>. ceiling: <the limit>. trigger: <when to revisit>.`
The convention is `honey: <ceiling>, <trigger>`, so both fields come straight from the comment. Add `git blame -L<line>,<line> -- <file>` per row only if the user asks who owns it.
Tag any marker with no trigger `no-trigger` — a ceiling without a revisit condition is the shape that rots. End with:
`<N> markers, <M> with no trigger.`
Nothing found: `No honey: debt. Clean ledger.`
Boundaries
- **Report only.** Don't fix, refactor, or remove markers — the user decides what to
pay down. Offer, don't act.
- **Don't invent debt.** A `TODO`/`FIXME` is not a `honey:` marker; mention the count
separately at most once if it's large, don't fold it into the ledger.
- **Don't editorialise per row.** The ledger is data. Save any judgement for one
closing line, and only if something is genuinely alarming.
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-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
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

