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.
npx agentmods add instructions/hanabiovo/atmosphere777/agents-mdgit clone --depth 1 https://github.com/hanabiovo/Atmosphere777Wrote 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/instructions/hanabiovo/atmosphere777/agents-md)<a href="https://agentmods.dev/instructions/hanabiovo/atmosphere777/agents-md"><img src="https://agentmods.dev/badge/instructions/hanabiovo/atmosphere777/agents-md.svg" alt="Measured on agentmods" 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 | $0.00649 | $0.00649 |
| Opus 5 | $0.00324 | $0.00324 |
| Sonnet 5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
Atmosphere777 AGENTS.md scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -f http://127.0.0.1:8002/healthz What it actually says
AGENTS.md
本文件供 Codex、Claude Code、Cursor 等编程代理读取。
项目目标
Atmosphere777 是轻量、自托管、默认安全的环境观测站。它同时提供 MCP、只读 REST、室内传感器写入和静态 PWA。
先读这些文件
README.mddocs/architecture.mddocs/deployment.mddocs/customization.md
结构
server.py：MCP 工具定义；兼容面最重要。qweather.py：和风 JWT、请求与缓存的唯一实现。weather_api.py：复用QWeatherClient的只读 REST 包装。sensor_api.py：室内数据写入、持久化与读取。compose.yml：三个后端服务及资源/安全约束。frontend/：无构建步骤的静态 PWA 与 Nginx 示例。examples/：外部传感器上报示例。
不可破坏的约束
- 不得提交
.env、sensor.env、keys/、私钥、Token、真实域名或私人坐标。 - 不得把和风 JWT 或传感器写入 Token 放进前端。
- 未经明确要求，不得修改 5 个 MCP 工具名称、参数或返回字段。
/mcp必须继续使用 Streamable HTTP。- REST 必须复用
qweather.py，不要复制第二份天气查询逻辑。 /sensor/update必须保持认证；不要为了调试临时关闭认证后忘记恢复。- 前端无法取得实时数据时必须显示失败或过期状态，不得把缓存冒充实时值。
- 室内传感器是可选模块；无硬件部署时用
frontend/config.js隐藏，不得伪造室内读数。
允许的常规定制
- 页面标题、位置文案、阈值、配色和模块顺序；
.env中的默认位置、语言、单位和缓存时间；- Nginx 域名和访问控制；
- 传感器采集器实现，只要上报 JSON 契约不变。
最小验证
python -m compileall server.py qweather.py weather_api.py sensor_api.py
docker compose config --quiet
docker compose up -d --build
docker compose ps
curl -f http://127.0.0.1:8002/healthz
curl -f http://127.0.0.1:8003/healthz
curl -f http://127.0.0.1:8003/weather/now
随后通过 MCP 客户端执行 tools/list，并逐个调用 5 个工具。任何变更都应说明修改文件、兼容性影响和回退方法。
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.
- 5d ago First seen · 57 lines · 649 tokens per session scan A b2d869816ab4
Atmosphere777 AGENTS.md is an instructions file published in the GitHub repository hanabiovo/Atmosphere777 (0 stars, last pushed 26d ago), licensed MIT. It adds 649 tokens to every session, about $0.0032 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
edgeever AGENTS.md
AGENTS.md instructions for tianma-if/edgeever, covering agents.md, 文档与分支约束, 变更风险评估, github actions 与 release 约束及流程 and 🇨🇳 中文说明 / chinese changelog.
wolfpack AGENTS.md
AGENTS.md instructions for almogdepaz/wolfpack: This repo ships deep architectural context generated by EDC.
cairn CLAUDE.md
Claude Code instructions for zilet/cairn, covering claude.md, what cairn is, commands, hard requirements and the traps that actually bite.
cairn AGENTS.md
AGENTS.md instructions for zilet/cairn, a project described as: Self-hosted wellness OS for training, nutrition and longevity. Connects your labs, lifting, running, food and sleep into one agentic brain that suggests the one thing worth doing today. PWA + REST + MCP server. No scores, no nudges.
dograh AGENTS.md
AGENTS.md instructions for dograh-hq/dograh, covering dograh - project overview, project structure, tech stack, local development and environment configuration.
n8n CLAUDE.md
Claude Code instructions for n8n-io/n8n, a project described as: Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.