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/iflytek/astron-agent/agents-mdgit clone --depth 1 https://github.com/iflytek/astron-agentWhat 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 | $0.01791 | $0.01791 |
| Opus 5 | $0.00896 | $0.00896 |
| Sonnet 5 | $0.00358 | $0.00358 |
| Haiku 4.5 | $0.00179 | $0.00179 |
Grade A, and why
astron-agent 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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- astron-agent CLAUDE.md — 95% identical, 10 lines differ
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Overview
Astron Agent is an enterprise-grade Agentic Workflow development platform. It includes the console frontend and backend, multiple core microservices, a plugin system, and deployment and infrastructure configuration. The repository uses a multi-language, multi-module structure. The primary languages are TypeScript, Java, Python, and Go.
Repository Structure
Console
console/frontend- React 18 + TypeScript + Vite frontend application
- Responsible for the console UI, agent creation, chat interface, workflow visualization, model management, plugin marketplace, and related features
console/backend- Java Spring Boot backend
- Responsible for console REST APIs, SSE, authentication, management capabilities, and business aggregation
- Main submodules:
hubtoolkitcommons
Core Microservices
core/agent- Python FastAPI service
- Responsible for the agent execution engine, Chat/CoT/CoT Process Agent, plugin invocation, and session context handling
core/workflow- Python FastAPI service
- Responsible for workflow orchestration, execution, debugging, versioning, and event handling
core/knowledge- Python FastAPI service
- Responsible for the knowledge base, document processing, vectorization, retrieval, and RAG integration
core/memory- Python module
- Responsible for conversation history, short-term and long-term memory, and session persistence
core/tenant- Go service
- Responsible for multi-tenancy, space isolation, organization management, and resource quota management
core/plugin- Plugin capability directory
- Includes plugin services such as
aitools,rpa, andlink
core/common- Python shared capability module
- Responsible for abstractions around authentication, logging, observability, databases, cache, message queues, object storage, and other infrastructure concerns
Other Directories
docs- Project documentation, deployment, configuration, and module descriptions
- For architectural understanding, refer first to
docs/zh/PROJECT_MODULES.md
docker- Docker Compose and related infrastructure configuration
helm- Helm Charts and Kubernetes deployment configuration
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.
- 2d ago First seen · 100 lines · 1,791 tokens per session scan A 19e532ca1aa3
astron-agent AGENTS.md is an instructions file published in the GitHub repository iflytek/astron-agent (8,888 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,791 tokens to every session, about $0.0090 per session on Opus 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
astron-rpa AGENTS.md
Instructions for iflytek/astron-rpa, covering agents.md, project layout, toolchain, common commands and run the server (docker).
deer-flow copilot-instructions.md
Copilot instructions for bytedance/deer-flow, covering copilot onboarding instructions for deerflow, 1) repository summary, 2) runtime and toolchain requirements, 3) build/test/lint/run - verified command sequences and a. bootstrap and install.
LeAgent AGENTS.md
Instructions for vixues/LeAgent, covering leagent development guidelines, project overview, architecture, execution topology (one kernel, many ingresses) and surface map (where things live).
sprawling CLAUDE.md
Instructions for 2youg1/sprawling: See AGENTS.md. It is the whole instruction set for this repository — the loop, what to read first, the five steps of one change, the rules a machine holds, and the language and commit conventions.
wanwu-workflow CLAUDE.md
Instructions for UnicomAI/wanwu-workflow, covering claude.md, project overview, development commands, environment setup and clone and setup.
spacebot AGENTS.md
AGENTS.md instructions for spacedriveapp/spacebot, covering agents.md, what spacebot is, javascript tooling (critical), migration safety and delivery gates (mandatory).