New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Honey Loop

by Green-PT in Green-PT/honey-for-devs

Cost discipline for recurring /loop runs. An agent skill from Green-PT/honey-for-devs.

MITAuto-check passedBackend & APIs

Install Honey Loop

skills CLI
$ npx skills add Green-PT/honey-for-devs --skill honey-loop -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Green-PT/honey-for-devs honey-loop --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Green-PT/honey-for-devs.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/honey-loop .claude/skills/honey-loop && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
honey-loop
GitHub stars
313
Token cost
~799 tokens
SKILL.md length
427 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

Cost discipline for recurring /loop runs. An agent skill from Green-PT/honey-for-devs.

  • Works in 5 steps: Pace to the cache, skip the dead zone.… → Event-driven over polling.… → No-change short-circuit. Re-generating… → …
  • A /loop is running
  • SKILL.md covers The five levers, Per-tick output: ultra by… and Don't cut
  • Calls git

What it does

Honey Loop is an agent skill from Green-PT/honey-for-devs. 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.

Its SKILL.md is about 800 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Backend & APIs, covering Event-driven systems. The repository describes itself as: Honey (I Shrunk the AI) by GreenPT: a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — write less code, less prose, and denser agent-to-agent… The licence is MIT.

When your agent uses it

  • A /loop is running
  • Being set up — especially long-lived
  • Frequently-firing ones

Example prompts

  • “/honey-loop”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Pace to the cache, skip the dead zone. The prompt cache TTL is 5 min.
  2. Event-driven over polling. Harness-tracked work (background Bash, Agent,
  3. No-change short-circuit. Re-generating output is the bulk of per-tick cost.
  4. Carry a compact state handle, don't re-derive. Keep what the loop has done
  5. Define done; then stop. An unbounded loop is unbounded cost. State the exit

What it can do on your machine

Read from SKILL.md and the folder at commit 9169fc5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Honey Loop loads about 799 tokens when it runs. Until then it costs about 100 tokens; SKILL.md has 427 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~100
When it runs · the whole SKILL.md, loaded when a task matches
~799

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Green-PT/honey-for-devs at commit 9169fc5, republished under its MIT licence (© Green-PT). 427 words, ~799 tokens.

Download SKILL.mdSave it as .claude/skills/honey-loop/SKILL.md (or your agent's skills folder).
name
honey-loop
description
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.
license
MIT

Honey Loop

A loop is the one place token waste compounds: cost = per_tick × ticks. The honey levers still apply inside each tick (less code, less prose), but a loop adds two leaks the single-shot levers don't cover — re-paying for context every wake-up, and re-doing work that didn't change. Cut those.

The five levers

  1. Pace to the cache, skip the dead zone. The prompt cache TTL is 5 min.

    • < 270s → context stays warm; right for actively polling external state.
    • ≥ 1200s → one cache miss amortized over a long idle wait; the default for idle ticks (use 1200–1800s).
    • ~300s is the worst choice — pays the cache miss without amortizing it. Never round to "5 minutes." Drop to 270s or commit to 1200s+.

  2. Event-driven over polling. Harness-tracked work (background Bash, Agent, Workflow) re-invokes you automatically on completion. Don't schedule a short tick to poll it — that re-reads full context for nothing. Set a long fallback heartbeat (1200s+) and let the completion notification drive you. Poll only external state the harness can't see (CI, a deploy, a remote queue), at a cadence matched to how fast that state actually changes.

  3. No-change short-circuit. Re-generating output is the bulk of per-tick cost. Check cheaply first (a hash, a timestamp, a git rev-parse, a status field). If nothing changed: emit one line and reschedule. Don't redo the task, don't re-read the world, don't write a report.

  4. Carry a compact state handle, don't re-derive. Keep what the loop has done so far in a small file (.honey-loop/state.json or a <<honey:HASH>> stash via eso stash), and read that each tick — not the full history re-discovered from scratch. Lever 3b: the cheapest input token is the one that never re-enters context.

  5. Define done; then stop. An unbounded loop is unbounded cost. State the exit condition up front (target reached, N empty ticks, deadline). When met, end the loop — omit the wake-up reschedule. "Loop forever" is a bug, not a feature.

Show full SKILL.md (103 more words)Show less

Per-tick output: ultra by default

A loop tick is an agent-to-self / agent-to-log message, not a deliverable. Default to ultra: status line only, near-zero prose. One line is enough — tick 4/∞ · no change · next 1800s. Step up to a full report only on the tick where something actually needs the user (state changed, a decision, an error).

Don't cut

  • The stop/exit check — dropping it is how a loop runs all night.
  • Error surfacing — a tick that hit an error reports it; silent failure in a loop hides for hours.
  • The cheap pre-check in lever 3 — skipping it to "just redo it" defeats the point.

© Green-PT, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/honey-loop of Green-PT/honey-for-devs.

Open the folder on GitHubat commit 9169fc5

Compare with similar skills

Honey Loop next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Honey Loop compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Honey Loop this skillGreen-PT/honey-for-devs313—~799Automated safety check: PassMIT
Stripe Projectsfossasia/eventyay1.7k5 repos~2kAutomated safety check: NotesApache-2.0
MQTTX CLIemqx/MQTTX5.1k—~1.9kAutomated safety check: PassApache-2.0
AWS Serverless Edazxkane/aws-skills3674 repos~3.2kAutomated safety check: PassMIT
Windmill Trigger Type Checklistwindmill-labs/windmill18k—~4.7kAutomated safety check: PassCustom licence
FoundatioFoundatioFx/Foundatio2.1k—~3.9kAutomated safety check: PassApache-2.0

Similar skills

  • Stripe Projects

    fossasia/eventyay

    A skill your agent uses when the user wants to provision infrastructure or third-party services using Stripe Projects.

    1.7k GitHub starsUsed in 5 repos~2k tokens
    Backend & APIsAuto-check: notes

  • MQTTX CLI

    emqx/MQTTX

    Operates the `mqttx` command line client to connect, publish, subscribe, benchmark and simulate data against an MQTT broker, with TLS and MQTT 5 support.

    5.1k GitHub stars~1.9k tokensUpdated today
    Backend & APIsAuto-check passed

  • AWS Serverless Eda

    zxkane/aws-skills

    AWS serverless and event-driven architecture expert based on Well-Architected Framework.

    367 GitHub starsUsed in 4 repos~3.2k tokens
    Backend & APIsAuto-check passed

  • Windmill Trigger Type Checklist

    windmill-labs/windmill

    Checklist of every backend, frontend, CLI and capture change needed to add a new TriggerCrud-based trigger type, such as Azure, GCP or Kafka, to Windmill.

    18k GitHub stars~4.7k tokensUpdated today
    Backend & APIsAuto-check passed

  • Foundatio

    FoundatioFx/Foundatio

    A skill your agent uses when working with Foundatio infrastructure abstractions for .NET -- caching, queuing, messaging, file storage, distributed locking, or background jobs.

    2.1k GitHub stars~3.9k tokensUpdated today
    Backend & APIsAuto-check passed

  • Homerail Dag Ops

    xiaotianfotos/homerail

    Design, start, supervise, inspect, and continue HomeRail DAG workflows from any agent with CLI or HTTP access.

    992 GitHub stars~1.5k tokensUpdated 13 days ago
    Backend & APIsAuto-check passed

More from Green-PT/honey-for-devs

All 14 skills in this repo

  • Honey

    Green-PT/honey-for-devs

    Write less code and say less about it. An agent skill from Green-PT/honey-for-devs.

    313 GitHub stars~3.5k tokensUpdated 1 mo ago
    Auto-check passed

  • Honey Ccr

    Green-PT/honey-for-devs

    Compress-Cache-Retrieve for huge, repetitive array tool output (logs, scan results, time series, event streams) before it enters context.

    313 GitHub stars~674 tokensUpdated 1 mo ago
    Auto-check passed

  • Honey Eco

    Green-PT/honey-for-devs

    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.

    313 GitHub stars~608 tokensUpdated 1 mo ago
    Auto-check passed

  • Honey Gain

    Green-PT/honey-for-devs

    Show Honey's benchmark scoreboard — the committed quality and token results per task tier (code, user-facing, agent-to-agent) from bench/.

    313 GitHub stars~661 tokensUpdated 1 mo ago
    Auto-check passed

  • Honey Px

    Green-PT/honey-for-devs

    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%…

    313 GitHub stars~701 tokensUpdated 1 mo ago
    Auto-check passed

  • Honey Superpowers

    Green-PT/honey-for-devs

    Stack Honey onto Superpowers-style workflows (subagent-driven-development, dispatching-parallel-agents, executing-plans) and any orchestration that dispatches fresh subagents.

    313 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Honey Loop

What does Honey Loop do?

Cost discipline for recurring /loop runs. An agent skill from Green-PT/honey-for-devs. Honey Loop is an agent skill from Green-PT/honey-for-devs. Cost discipline for recurring /loop runs.

When should I use Honey Loop?

Honey Loop fits situations like: A /loop is running; being set up — especially long-lived; frequently-firing ones.

How do I install Honey Loop in Claude Code?

Run `npx skills add Green-PT/honey-for-devs --skill honey-loop -a claude-code`. Or copy the skill folder (skills/honey-loop in Green-PT/honey-for-devs) into .claude/skills/honey-loop in your project. Claude Code loads it when a task matches its description.

How do I install Honey Loop in Codex?

Run `npx skills add Green-PT/honey-for-devs --skill honey-loop -a codex`. Or copy the skill folder (skills/honey-loop in Green-PT/honey-for-devs) into .agents/skills/honey-loop in your project. Codex loads it when a task matches its description.

Can I use Honey Loop in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Green-PT/honey-for-devs --skill honey-loop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/honey-loop, .gemini/skills/honey-loop, .github/skills/honey-loop and .opencode/skills/honey-loop in your project.

What does Honey Loop need to run?

Going by SKILL.md and its folder, Honey Loop needs the command-line tools its instructions call (git).

Does Honey Loop access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Honey Loop safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Honey Loop use?

Honey Loop is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Honey Loop use?

About 799 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Honey Loop?

Skills that share tags, products or a category with Honey Loop: Stripe Projects (fossasia/eventyay, 1.7k stars), MQTTX CLI (emqx/MQTTX, 5.1k stars), AWS Serverless Eda (zxkane/aws-skills, 367 stars) and Windmill Trigger Type Checklist (windmill-labs/windmill, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Honey Loop?

Green-PT (a GitHub organization) maintains it in Green-PT/honey-for-devs, which has 313 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on September 7, 2026.

Source: Green-PT/honey-for-devs on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.