Borrowing it
Nothing to install: this file belongs to AetherHeart-AI/Aeloon. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AetherHeart-AI/Aeloon/main/AGENTS.mdgit clone --depth 1 https://github.com/AetherHeart-AI/AeloonWrote 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/aetherheart-ai/aeloon/agents-md)<a href="https://agentmods.dev/instructions/aetherheart-ai/aeloon/agents-md"><img src="https://agentmods.dev/badge/instructions/aetherheart-ai/aeloon/agents-md/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/instructions/aetherheart-ai/aeloon/agents-md"><img src="https://agentmods.dev/badge/instructions/aetherheart-ai/aeloon/agents-md.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 | $0.00995 | $0.00995 |
| Opus 5.5 | $0.00398 | $0.00398 |
| Sonnet 5.5 | $0.00199 | $0.00199 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
Aeloon AGENTS.md 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 1mo 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Common Commands
- Install for development:
pip install -e ".[dev]" - Run the CLI locally:
aeloon --help - First-time setup / config bootstrap:
aeloon onboard - One-shot agent run:
aeloon agent -m "Hello!" - Start gateway mode:
aeloon gateway - Inspect configured channels:
aeloon channels status - Run tests:
pytest - Run one test file:
pytest tests/test_kernel.py - Run matching tests:
pytest -k "wechat" - Lint and auto-fix:
ruff check --fix . - Format:
ruff format .
Use ruff==0.15.6; CI expects that exact version.
Architecture Overview
- Aeloon is a message-bus-based assistant runtime. The main flow is: channel receives inbound event →
MessageBus→Dispatcher→AgentLoop→ provider/tool execution → outbound message routed back throughChannelManager. aeloon/agent/loop.pyis the orchestration layer around the reusable kernel. It wires together context building, tool registration, sessions, memory consolidation, skill runtime, subagents, cron context, optional MCP connections, and outbound publishing.aeloon/agent/kernel.pyandaeloon/agent/task_graph.pyhandle one LLM turn. Tool-call batches are compiled into an internal DAG so independent read-only work can run concurrently while mutating/exclusive operations are serialized conservatively.aeloon/agent/dispatcher.pysits in front of the loop and owns slash-command handling, per-session task lifecycle, cancellation, and WeChat login/status coordination.aeloon/channels/is one integration per file, all inheritingBaseChannel. Channel discovery is automatic via registry scanning plus entry-point plugins; do not add manual registration for built-in channels.aeloon/channels/manager.pyowns channel startup/shutdown, lifecycle state tracking (pending,starting,running,failed,stopped), and outbound routing from the bus back to each channel.aeloon/providers/registry.pyis the source of truth for provider metadata and matching. Provider selection is driven by explicit provider name, model keywords/prefixes, API key prefixes, and API base URLs.aeloon/config/schema.py+aeloon/config/loader.pydefine the Pydantic config model and loading precedence. Config accepts camelCase aliases, and the effective file path is--configflag →AELOON_CONFIG→~/.aeloon/config.json.aeloon/skills/are markdown-driven capabilities. Skills are injected into the prompt progressively; workspace skills override built-ins. Helper scripts live alongside a skill and are typically invoked through tool execution.aeloon/templates/AGENTS.mdis the runtime prompt template for end-user agent behavior; it is separate from this repository-levelAGENTS.md.aeloon/channels/wechat.pyandaeloon/channels/wechat_ilink/implement the native WeChat login/runtime flow./wechat login|logout|statusbehavior is coordinated through the dispatcher and channel manager.bridge/is a separate Node.js/TypeScript WhatsApp bridge process.bridge/src/server.tsbinds WebSocket only to127.0.0.1and optionally enforces a bridge token; treat it as local-only infrastructure.
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.
- 1mo ago First seen · 49 lines · 995 tokens per session scan A 139af78dd4b0
Aeloon AGENTS.md is an instructions file published in the GitHub repository AetherHeart-AI/Aeloon (135 stars, last pushed 5mo ago), licensed MIT. It adds 995 tokens to every session, about $0.0040 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.