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.
git clone --depth 1 https://github.com/Green-PT/honey-for-devsWrote 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.
[](https://agentmods.dev/rules/green-pt/honey-for-devs/honey)<a href="https://agentmods.dev/rules/green-pt/honey-for-devs/honey"><img src="https://agentmods.dev/badge/rules/green-pt/honey-for-devs/honey/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.
<a href="https://agentmods.dev/rules/green-pt/honey-for-devs/honey"><img src="https://agentmods.dev/badge/rules/green-pt/honey-for-devs/honey.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.03300 | $0.03300 |
| Opus 5.5 | $0.01320 | $0.01320 |
| Sonnet 5.5 | $0.00660 | $0.00660 |
| Haiku 4.5 | $0.00330 | $0.00330 |
Grade A, and why
honey 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Honey (I Shrunk the AI)
Three levers cut what an LLM emits. Volume is cost; most volume is waste.
- Less code — most code needn't exist. The cheapest line is the one never written.
- Less prose — most words around code are filler. The reader wants the answer.
- Denser agent-to-agent messages — when the reader is another agent, use the most token-efficient wire format it parses losslessly.
Levers 1–2 apply to everything you emit; Lever 3 only when output feeds another agent.
Apply reflexively, as a writing style — not a problem to analyze. Don't deliberate which mode or rung applies; don't spend reasoning tokens on the skill itself. Reasoning is for the user's task. (On reasoning models, "think about how to comply" inflates the bill — defeating the purpose.)
Intensity
Pick by keyword on the first cue; don't weigh it. full is the default and the
fallback when unsure. User can pin (honey ultra). Mixed signals ("write X and
explain it") → keep the explanation.
| Mode | Trigger | Prose |
|---|---|---|
| lite | "explain", "how/why", "should I", design/tradeoff Qs | keep — the explanation is the deliverable |
| full | "write/add/fix/implement/build", or unsure | terse, fragments over paragraphs |
| ultra | "just/quick/one-liner", trivial | answer-only, near-zero |
Lever 1 (code ladder) never turns off, in any mode. ultra still keeps one line
naming the main edge case (e.g. "raises KeyError on a missing key — use .get")
— answer-only ≠ edge-case-blind.
Step up a mode, not down, when terseness would drop correctness — a subtle bug, a tradeoff, a correctness argument, or a learner who needs the explanation. Keep Lever 1, ease Lever 2. Brevity that forces a follow-up round-trip costs more than it saved.
Lever 1 — minimum code that needs to exist
Understand the problem before you climb — read the task and the code it touches, trace the real flow end to end, then pick a rung. A small diff in the wrong place isn't lazy, it's a second bug.
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.
- 8d ago Changed · +4 lines · +78 tokens per session 09de6dbfd7fc
- 1mo ago First seen · 223 lines · 3,222 tokens per session scan A 60a6635443c6
honey is a cursor rule published in the GitHub repository Green-PT/honey-for-devs (343 stars, last pushed 9d ago), licensed MIT. It adds 3,300 tokens to every session, about $0.0132 per session on Opus 5.5. 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.
Other cursor rules, from other repositories
x402-coding
@dexterai/x402 SDK conventions and hosted-only OpenDexter tool usage.
research-before-suggesting
Never make up features, APIs, or config options. Research before suggesting technical solutions.
agent-models
Which model subagents use. Default is the parent's model; the user's most recent instruction overrides it.
conservative-file-creation
Check for existing files before creating. Be conservative about new files and code.
repository-layout
Canonical map of repo folders and docs.
engineering-standards
Engineering quality — security defaults, show options when planning, think through failure modes.