all publishers

green-pt

@green-pt source repo

54 published skills

  1. ▌
    Honey Memory 4 · green-pt
    Per-project persistent memory: save and recall durable facts across sessions as small frontmatter files, indexed in MEMORY.md.
    356 repo stars
  2. ▌
    Honey Review 4 · green-pt
    Review a diff for over-engineering and verbosity. Terse delete-list of what to cut and the lines each saves. One-shot.
    356 repo stars
  3. ▌
    Honey Compress 4 · green-pt
    Rewrite a memory or context file (CLAUDE.md, AGENTS.md, notes) into Honey-terse form to cut per-session input tokens. Backs up first.
    356 repo stars
  4. ▌
    Honey Superpowers 4 · green-pt
    Stack Honey onto Superpowers-style subagent workflows: dispatched subagents skip the session hook, so inject the levers into each dispatch prompt.
    356 repo stars
  5. ▌
    Honey Px 4 · green-pt
    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.
    356 repo stars
  6. ▌
    Honey Ccr 4 · green-pt
    Compress-Cache-Retrieve huge repetitive array tool output before it hits context: keep a sample, cache the rest, leave a hash.
    356 repo stars
  7. ▌
    Honey Eco 4 · green-pt
    Report the session's Honey savings: output tokens, CO2, and CO2/$ saved vs a no-Honey baseline, via the committed EcoLogits port.
    356 repo stars
  8. ▌
    Honey Debt 4 · green-pt
    Harvest every `honey:` shortcut marker into a debt ledger, flagging the ones with no revisit trigger. One-shot report, changes nothing.
    356 repo stars
  9. ▌
    Honey Gain 4 · green-pt
    Show Honey's benchmark scoreboard: committed quality and token results per task tier vs Caveman, Ponytail, and no-skill. One-shot.
    356 repo stars
  10. ▌
    Honey Hive 4 · green-pt
    Delegate search- and review-heavy work to Honey's read-only subagents so large reads return compressed instead of bloating context.
    356 repo stars
  11. ▌
    Honey Loop 4 · green-pt
    Cost discipline for recurring /loop runs: cache-aware pacing, event-driven-over-polling, no-change short-circuit, compact state handle, stop condition.
    356 repo stars
  12. ▌
    Honey Design 4 · green-pt
    Same pixels, fewer tokens. For user-facing markup: keeps the full design, expresses it densely with CSS vars, shorthand, fluid units.
    356 repo stars
  13. ▌
    Honey 4 · green-pt
    Write less code and say less about it: YAGNI, stdlib-first, terse prose. Cuts agent token cost on every coding and writing task.
    356 repo stars
  14. ▌
    Honey Px 3 · green-pt
    Read huge read-only text as PNG pages; big input cut.
    356 repo stars
  15. ▌
    Honey Ccr 3 · green-pt
    Compress-cache-retrieve huge array tool output.
    356 repo stars
  16. ▌
    Honey Eco 3 · green-pt
    Report session token and CO2 savings vs no-Honey baseline.
    356 repo stars
  17. ▌
    Honey Debt 3 · green-pt
    Harvest honey shortcut markers into a debt ledger.
    356 repo stars
  18. ▌
    Honey Gain 3 · green-pt
    Honey benchmark scoreboard vs baseline and rival skills.
    356 repo stars
  19. ▌
    Honey Hive 3 · green-pt
    Delegate search/review to subagents; compressed returns.
    356 repo stars
  20. ▌
    Honey Loop 3 · green-pt
    Cost discipline for recurring loop runs.
    356 repo stars
  21. ▌
    Honey Design 3 · green-pt
    Same pixels, fewer tokens: dense CSS for user-facing UI.
    356 repo stars
  22. ▌
    Honey Memory 3 · green-pt
    Per-project persistent memory files indexed in MEMORY.md.
    356 repo stars
  23. ▌
    Honey Review 3 · green-pt
    Review a diff for over-engineering; terse delete-list.
    356 repo stars
  24. ▌
    Honey Compress 3 · green-pt
    Rewrite context files terse to cut per-session tokens.
    356 repo stars
  25. ▌
    Honey Superpowers 3 · green-pt
    Inject Honey levers into dispatched subagent prompts.
    356 repo stars
  26. ▌
    Honey 3 · green-pt bundle
    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.
    356 repo stars
  27. ▌
    Honey Px 2 · green-pt
    Read huge, dense, read-only text as rendered PNG pages instead of raw text — image tokens scale with pixels, not characters, so token-dense bulk (big files, vendored code, diffs, logs) costs ~60–75% less as an image. Use when you must skim or reason over thousands of lines you will NOT edit or byte-copy. Lossy on exact strings: never for files you'll Edit, secrets, hashes, or byte-exact values. Fable-class readers only.
    356 repo stars
  28. ▌
    Honey Ccr 2 · green-pt
    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.
    356 repo stars
  29. ▌
    Honey Eco 2 · green-pt
    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 expand the 🍯 statusline badge into a full breakdown.
    356 repo stars
  30. ▌
    Honey Chat 2 · green-pt bundle
    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.
    356 repo stars
  31. ▌
    Honey Debt 2 · green-pt
    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.
    356 repo stars
  32. ▌
    Honey Gain 2 · green-pt
    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 Caveman / Ponytail / no-skill baseline, or for the headline numbers.
    356 repo stars
  33. ▌
    Honey Hive 2 · green-pt
    Decide when to delegate to Honey's read-only subagents (hive-scout, hive-reviewer) instead of working inline, so the expensive tokens — large file reads and review passes injected back into the orchestrator's context — come back compressed (Honey Lever 3). Use when a task is search-heavy or review-heavy, spans many files, or you want to keep the orchestrator's context small. Not for trivial one-file work.
    356 repo stars
  34. ▌
    Honey Loop 2 · green-pt
    Cost discipline for recurring /loop runs. A loop multiplies per-iteration cost by iteration count, so waste compounds. Encodes cache-aware pacing (avoid the 300s dead zone), event-driven-over-polling, a no-change short-circuit, a compact state handle carried between ticks, and a stop condition. Use when a /loop is running or being set up — especially long-lived or frequently-firing ones.
    356 repo stars
  35. ▌
    Honey Design 2 · green-pt
    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, motion, responsive richness, a11y) and cuts tokens by expressing that design densely — CSS custom properties, shared classes, shorthand, fluid units — instead of by cutting the design. The honey core trims code and prose; this trims how the design is *written*, never how it looks. Reach for it whenever output is user-facing markup, even if the user never says "minimal".
    356 repo stars
  36. ▌
    Honey Memory 2 · green-pt
    Create and maintain one committed per-project memory file (PROJECT.md) so agents stop re-discovering the same facts every cold session. Stores only the stable, expensive-to-rediscover, not-in-the-code context — architecture + why, build/test/run commands, decisions and dead-ends — as human-readable markdown, versioned with the code so it can't silently rot. Use when asked to set up project memory/context, stop agents re-grepping the codebase, scaffold or refresh a PROJECT.md / CLAUDE.md memory section, or cut cold-start rediscovery cost. Prose context only — never code, config, or data.
    356 repo stars
  37. ▌
    Honey Review 2 · green-pt
    Review a diff for what Honey would cut — over-engineering (speculative generality, hand-rolled stdlib, single-caller abstractions) and over-verbosity (dead code, narration, redundant comments). Outputs a terse delete-list, one line per finding, with the line count each cut saves. Use when asked to review, trim, or de-bloat a change, or before opening a PR. Quality lever only — it finds waste, not correctness bugs.
    356 repo stars
  38. ▌
    Honey Compress 2 · green-pt
    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.
    356 repo stars
  39. ▌
    Honey Superpowers 2 · green-pt
    Stack Honey onto Superpowers-style workflows (subagent-driven-development, dispatching-parallel-agents, executing-plans) and any orchestration that dispatches fresh subagents. Dispatched subagents run in isolated context and do NOT inherit the session's Honey hook, so they emit full-fat code and verbose reports. Use when you are about to dispatch implementer/reviewer/fixer/parallel subagents: it gives the exact Honey directive to paste into each dispatch prompt, with a worker variant and a reviewer variant, so the levers apply inside the subagents too — where the multiplied cost actually is.
    356 repo stars
  40. ▌
    Honey 2 · green-pt
    Write less code and say less about it. Cuts token cost.
    356 repo stars
  41. ▌
    Honey · green-pt bundle
    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.
    356 repo stars
  42. ▌
    Honey Px · green-pt
    Read huge, dense, read-only text as rendered PNG pages instead of raw text — image tokens scale with pixels, not characters, so token-dense bulk (big files, vendored code, diffs, logs) costs ~60–75% less as an image. Use when you must skim or reason over thousands of lines you will NOT edit or byte-copy. Lossy on exact strings: never for files you'll Edit, secrets, hashes, or byte-exact values. Fable-class readers only.
    356 repo stars
  43. ▌
    Honey Ccr · green-pt
    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.
    356 repo stars
  44. ▌
    Honey Eco · green-pt
    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 expand the 🍯 statusline badge into a full breakdown.
    356 repo stars
  45. ▌
    Honey Chat · green-pt bundle
    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.
    356 repo stars
  46. ▌
    Honey Debt · green-pt
    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.
    356 repo stars
  47. ▌
    Honey Gain · green-pt
    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 Caveman / Ponytail / no-skill baseline, or for the headline numbers.
    356 repo stars
  48. ▌
    Honey Hive · green-pt
    Decide when to delegate to Honey's read-only subagents (hive-scout, hive-reviewer) instead of working inline, so the expensive tokens — large file reads and review passes injected back into the orchestrator's context — come back compressed (Honey Lever 3). Use when a task is search-heavy or review-heavy, spans many files, or you want to keep the orchestrator's context small. Not for trivial one-file work.
    356 repo stars
  49. ▌
    Honey Loop · green-pt
    Cost discipline for recurring /loop runs. A loop multiplies per-iteration cost by iteration count, so waste compounds. Encodes cache-aware pacing (avoid the 300s dead zone), event-driven-over-polling, a no-change short-circuit, a compact state handle carried between ticks, and a stop condition. Use when a /loop is running or being set up — especially long-lived or frequently-firing ones.
    356 repo stars
  50. ▌
    Honey Design · green-pt
    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, motion, responsive richness, a11y) and cuts tokens by expressing that design densely — CSS custom properties, shared classes, shorthand, fluid units — instead of by cutting the design. The honey core trims code and prose; this trims how the design is *written*, never how it looks. Reach for it whenever output is user-facing markup, even if the user never says "minimal".
    356 repo stars
  51. ▌
    Honey Memory · green-pt
    Create and maintain one committed per-project memory file (PROJECT.md) so agents stop re-discovering the same facts every cold session. Stores only the stable, expensive-to-rediscover, not-in-the-code context — architecture + why, build/test/run commands, decisions and dead-ends — as human-readable markdown, versioned with the code so it can't silently rot. Use when asked to set up project memory/context, stop agents re-grepping the codebase, scaffold or refresh a PROJECT.md / CLAUDE.md memory section, or cut cold-start rediscovery cost. Prose context only — never code, config, or data.
    356 repo stars
  52. ▌
    Honey Review · green-pt
    Review a diff for what Honey would cut — over-engineering (speculative generality, hand-rolled stdlib, single-caller abstractions) and over-verbosity (dead code, narration, redundant comments). Outputs a terse delete-list, one line per finding, with the line count each cut saves. Use when asked to review, trim, or de-bloat a change, or before opening a PR. Quality lever only — it finds waste, not correctness bugs.
    356 repo stars
  53. ▌
    Honey Compress · green-pt
    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.
    356 repo stars
  54. ▌
    Honey Superpowers · green-pt
    Stack Honey onto Superpowers-style workflows (subagent-driven-development, dispatching-parallel-agents, executing-plans) and any orchestration that dispatches fresh subagents. Dispatched subagents run in isolated context and do NOT inherit the session's Honey hook, so they emit full-fat code and verbose reports. Use when you are about to dispatch implementer/reviewer/fixer/parallel subagents: it gives the exact Honey directive to paste into each dispatch prompt, with a worker variant and a reviewer variant, so the levers apply inside the subagents too — where the multiplied cost actually is.
    356 repo stars