메뉴
Per-project persistent memory: save and recall durable facts across sessions as small frontmatter files, indexed in MEMORY.md.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Compress-Cache-Retrieve huge repetitive array tool output before it hits context: keep a sample, cache the rest, leave a hash.
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.
Write less code and say less about it: YAGNI, stdlib-first, terse prose. Cuts agent token cost on every coding and writing task.
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.
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.
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.
| name | honey-memory |
| description | Per-project persistent memory: save and recall durable facts across sessions as small frontmatter files, indexed in MEMORY.md. |
| homepage | https://github.com/Green-PT/honey-for-devs |
| license | MIT |
Lever 2 applied to discovery cost. Every cold session re-greps the same things — where auth lives, the build command, why X is shaped Y. One committed file replaces N rediscovery round-trips with a single cached read, on every future session. The cheapest token is the one not re-derived.
The win is per-session and recurring. The risk is staleness — a wrong cached fact costs more than no file. So the file lives in git, next to the code that can invalidate it, and is fixed in the same change that breaks it.
PROJECT.md at the root, committed (not ~/.claude).
If the repo already has CLAUDE.md/AGENTS.md, add/refresh a ## Memory
section there instead — don't add a second file.FILE.original.md.
If that backup already exists, stop and ask. Never clobber a restore point.If a fact is stable + expensive-to-rediscover + not-in-the-code, write it. Everything else, let agents derive on demand — caching it is where these systems quietly lose money.
A markdown file does not update itself. Reliability = discipline, not infra:
Start with one file. Split only when it crosses ~150–200 lines or covers clearly separable domains — then go to a thin index + topic files loaded on demand. Below that, an index costs more (the always-loaded tax) than it saves.
Apply Honey Lever 2 to the content — fragments over paragraphs, no narration of what the code already says. A bloated memory file is a per-session input tax. Keep it human-readable markdown: you (and reviewers) hand-edit it, so don't use a wire format — staleness costs more than the tokens a dense format would save.
Reversible — FILE.original.md is the restore path when overwriting. Verify
every written fact against the current code before reporting done; an unverified
fact is worse than an absent one.