honey-compress

honey-compress is a skill for Claude Code from Green-PT/honey-for-devs. It costs 15 tokens per session (355 once invoked), scanned A, original, MIT.

A tool for shortening context files that an agent reads repeatedly during coding sessions. It keeps the instructions while removing repeated or unnecessary wording and saves the original as a backup.

In plain words
What is it for?
Use it to compress prose-only context or instruction files, compare the old and new size, and retain a restore point before rewriting.
Why use it?
It reduces the amount of text sent in future sessions without losing rules that affect behavior, including instructions about security, money, migrations, or deletion.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the honey plugin — 14 skills, 3 agents, 3 hooks shipped together

Good fit Use it to compress prose-only context or instruction files, compare the old and new size, and retain a restore point before rewriting.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/green-pt/honey-for-devs/honey-compress
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Green-PT/honey-for-devs --skill honey-compress
Clone the repo
git clone --depth 1 https://github.com/Green-PT/honey-for-devs

Made for: Claude Code.

Or install honey, the plugin that ships this one along with the rest of its 14 skills, 3 agents, 3 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for honey-compress

README.md
[![agentmods](https://agentmods.dev/badge/skills/green-pt/honey-for-devs/honey-compress/github.svg)](https://agentmods.dev/skills/green-pt/honey-for-devs/honey-compress)
Your own site
<a href="https://agentmods.dev/skills/green-pt/honey-for-devs/honey-compress"><img src="https://agentmods.dev/badge/skills/green-pt/honey-for-devs/honey-compress/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for honey-compress

Your own site · 80×15
<a href="https://agentmods.dev/skills/green-pt/honey-for-devs/honey-compress"><img src="https://agentmods.dev/badge/skills/green-pt/honey-for-devs/honey-compress.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 355 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00015 $0.00355
Opus 5 $0.00008 $0.00178
Sonnet 5 $0.00003 $0.00071
Haiku 4.5 $0.00002 $0.00036

Measured 11d ago against content hash 5a1cb6884ece, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

honey-compress scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.hermes/skills/honey-compress/SKILL.md · 37 lines

What it actually says

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 FILEFILE.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.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 37 lines · 15 tokens per session scan A 5a1cb6884ece

Subscribe to this mod's changes

honey-compress is a skill published in the GitHub repository Green-PT/honey-for-devs (294 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 355 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

session-end

MUST use when user says 'bye', 'goodbye', 'good night', 'gnight', 'done for today', 'that's all', 'that's it', 'see you', 'see ya', 'let's stop', 'stopping here', 'wrapping up', 'signing off', 'closing down', 'done', 'finished for now', 'talk later', 'cya'. The user does NOT use slash commands; detect these natural…

faizkhairi/claude-code-blueprint · 107 tokens

ctx

Use ctx as working memory for prior agent work. Before starting or continuing work in an unfamiliar area, resuming earlier work, or revisiting an investigation, search prior sessions to ground yourself in earlier context. When ctx blame is available, use it to trace a line, file, commit, or PR to the agent session…

ctxrs/ctx · 91 tokens

save-session

MUST use when user says 'save', 'save session', or explicitly wants to preserve session state. {USERNAME} does NOT use slash commands; also trigger proactively when significant work has been completed and session context should be persisted. For session endings (bye/done/goodbye), use the session-end skill instead…

faizkhairi/claude-code-blueprint · 76 tokens

agent-memory

Use the agent-memory MCP server to retrieve, verify, and store durable project knowledge and global user knowledge before and after non-trivial work.

RashadAnsari/myagents · 31 tokens

memory-read

Query-first indexing and retrieval for Operator OS memory. Use when asked to find prior context, search memory, rebuild the memory index, or answer from the workspace without loading large files by default.

rangerrick337/operator-os · 41 tokens

load-session

Restore session context at the start of every new conversation. Auto-triggers on session start, or when user says 'continue', 'what were we doing', 'where did we leave off'.

faizkhairi/claude-code-blueprint · 41 tokens