What is sunset-agent?

A workflow for querying sunset-colour forecasts and air-quality particle data for a city. It uses weather models and a service called sunsetbot.top.

Use it to ask about sunset vividness, evening glow, or aerosol data, or to operate the related local LangGraph and MCP project.

It turns a natural-language city request into a summary of predicted evening colour and aerosol conditions.

sunset-agent — Skill for Claude Code and Codex by PyzmxU

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 PyzmxU/sunset-agent-hermes-skill --skill sunset-agent-hermes-skill

Clone the repo

git clone --depth 1 https://github.com/PyzmxU/sunset-agent-hermes-skill

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/pyzmxu/sunset-agent-hermes-skill/sunset-agent-hermes-skill/github.svg)](https://agentmods.dev/skills/pyzmxu/sunset-agent-hermes-skill/sunset-agent-hermes-skill)

Your own site

<a href="https://agentmods.dev/skills/pyzmxu/sunset-agent-hermes-skill/sunset-agent-hermes-skill"><img src="https://agentmods.dev/badge/skills/pyzmxu/sunset-agent-hermes-skill/sunset-agent-hermes-skill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/pyzmxu/sunset-agent-hermes-skill/sunset-agent-hermes-skill"><img src="https://agentmods.dev/badge/skills/pyzmxu/sunset-agent-hermes-skill/sunset-agent-hermes-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,311 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00029	$0.01311
Opus 5.5	$0.00012	$0.00524
Sonnet 5.5	$0.00006	$0.00262
Haiku 4.5	$0.00003	$0.00131

Measured 2mo ago against content hash 9255a50cfd9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sunset-agent 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 2mo 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.

SKILL.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sunset Agent Hermes Skill

Use this skill when the user wants to query sunset / evening-glow / 火烧云 prediction data, or when they want to operate a local sunset-agent-langgraph project that exposes a Hermes MCP server.

The expected end-to-end flow is:

user natural language
  -> LLM extracts city
  -> sunsetbot.top query
  -> EC + GFS model results
  -> vividness / AOD aerosol summary

What this skill provides

This skill is an operation guide for a LangGraph + MCP workflow. It does not contain API keys or private runtime state.

It assumes a companion Python project that contains:

src/sunset_agent/graph.py        LangGraph workflow
src/sunset_agent/sunsetbot.py    sunsetbot.top EC/GFS query wrapper
src/sunset_agent/mcp_server.py   MCP stdio server
src/sunset_agent/main.py         CLI entry point

LangGraph workflow

The current recommended graph is linear:

__start__
  ↓
build_messages
  ↓
call_model
  ↓
fetch_sunsetbot
  ↓
format_answer
  ↓
__end__

Business node responsibilities:

build_messages:
  Convert user input into a prompt that asks the LLM to output only the city name.

call_model:
  Call an OpenAI-compatible LLM and extract a city, e.g. Beijing / Shanghai / Guangzhou.

fetch_sunsetbot:
  Query sunsetbot.top and fetch both EC and GFS results.

format_answer:
  Format city, event time, EC/GFS vividness, EC/GFS AOD aerosol, forecast cycles, and trace_id.

Expected result fields

The sunset query wrapper should expose normalized fields like:

city
 event_name
 event_time
 models.EC.quality
 models.EC.aod
 models.EC.times
 models.GFS.quality
 models.GFS.aod
 models.GFS.times

Example final answer shape:

城市：北京市-北京
事件：日落
时间：2026-06-05 19:37:23
EC：鲜艳度 0.0（不烧）；AOD气溶胶 0.33（一般）；时次 2026060412z
GFS：鲜艳度 0.017（微烧）；AOD气溶胶 0.33（一般）；时次 2026060500z
trace_id：...

CLI usage

From the companion project directory:

python -m pip install -e .
python -m unittest discover -s tests -v

Read the full file on GitHub · 235 lines

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.

2mo ago First seen · 235 lines · 29 tokens per session scan A 9255a50cfd9b

Subscribe to this mod's changes

sunset-agent is a skill published in the GitHub repository PyzmxU/sunset-agent-hermes-skill (2 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 1,311 once invoked, about $0.0001 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 2026-08-31.

Scientific

sunset-agent next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
sunset-agentPyzmxU/sunset-agent-hermes-skill	Skill	2	5mo ago	MIT	A	29	Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-plugins	Skill	35k	3d ago	Apache-2.0	A	123	Claude Code
exploratory-data-analysisK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	83	Claude Code
matlabK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	44	Claude Code
phylogeneticsK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	71	Claude Code, Codex
research-engineerdavila7/claude-code-templates	Skill	33k	yesterday	MIT	A	43	Claude Code, Codex
mapping-to-snomedmaziyarpanahi/openmed	Skill	5.8k	yesterday	Apache-2.0	A	205	Claude Code