Menu
SkillsMP has collected 40 skills from Green-PT/honey-for-devs. Open a skill to review its source and details.
Showing 40 of 40 collected skills.
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,…
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,…
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…
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…
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…
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…
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,…
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).…
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…
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,…
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…
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…
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…
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…
Compress-cache-retrieve huge array tool output.
Rewrite context files terse to cut per-session tokens.
Harvest honey shortcut markers into a debt ledger.
Same pixels, fewer tokens: dense CSS for user-facing UI.
Report session token and CO2 savings vs no-Honey baseline.
Honey benchmark scoreboard vs baseline and rival skills.
Delegate search/review to subagents; compressed returns.
Cost discipline for recurring loop runs.
Per-project persistent memory files indexed in MEMORY.md.
Read huge read-only text as PNG pages; big input cut.
Review a diff for over-engineering; terse delete-list.
Write less code and say less about it. Cuts token cost.
Inject Honey levers into dispatched subagent prompts.
Harvest every `honey:` shortcut marker into a debt ledger, flagging the ones with no revisit trigger. One-shot report, changes nothing.
Show Honey's benchmark scoreboard: committed quality and token results per task tier vs Caveman, Ponytail, and no-skill. One-shot.
Write less code and say less about it: YAGNI, stdlib-first, terse prose. Cuts agent token cost on every coding and writing task.
Report the session's Honey savings: output tokens, CO2, and CO2/$ saved vs a no-Honey baseline, via the committed EcoLogits port.
Compress-Cache-Retrieve huge repetitive array tool output before it hits context: keep a sample, cache the rest, leave a hash.
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.
Delegate search- and review-heavy work to Honey's read-only subagents so large reads return compressed instead of bloating context.
Cost discipline for recurring /loop runs: cache-aware pacing, event-driven-over-polling, no-change short-circuit, compact state handle, stop condition.
Stack Honey onto Superpowers-style subagent workflows: dispatched subagents skip the session hook, so inject the levers into each dispatch prompt.
Rewrite a memory or context file (CLAUDE.md, AGENTS.md, notes) into Honey-terse form to cut per-session input tokens. Backs up first.
Same pixels, fewer tokens. For user-facing markup: keeps the full design, expresses it densely with CSS vars, shorthand, fluid units.
Per-project persistent memory: save and recall durable facts across sessions as small frontmatter files, indexed in MEMORY.md.
Review a diff for over-engineering and verbosity. Terse delete-list of what to cut and the lines each saves. One-shot.