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/wecode-ai/wegent/agents-mdgit clone --depth 1 https://github.com/wecode-ai/WegentWhat 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 | $0.01396 | $0.01396 |
| Opus 5 | $0.00698 | $0.00698 |
| Sonnet 5 | $0.00279 | $0.00279 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade C, and why
Wegent AGENTS.md scanned grade C 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 3d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- prettier-ignore --> 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.
Wegent contributor guide
Wegent is an AI-native operating system for defining, organizing, and running agent teams. Keep the system simpler after every change: reuse existing abstractions, remove obsolete paths, and fix the primary flow rather than hiding defects behind fallbacks.
Repository map
| Area | Technology | Responsibility |
|---|---|---|
backend/ |
FastAPI, SQLAlchemy, MySQL | REST API and business logic |
frontend/ |
Next.js, React, TypeScript | Main web product |
wework/ |
Electron, Vite, React, TypeScript | Desktop workbench and local coding experience |
executor/, executor_manager/ |
Python, Docker | Agent execution and orchestration |
chat_shell/ |
FastAPI, LangGraph | Lightweight chat runtime |
knowledge_runtime/, knowledge_doc_converter/ |
FastAPI, Celery | RAG and document conversion |
shared/ |
Python | Shared utilities, models, cryptography and telemetry |
Use docs/en/ and docs/zh/ for detailed architecture and guides. Keep this file limited to durable contributor rules. New documentation needs frontmatter with sidebar_position; write Chinese first, then English.
Scoped instructions
- Before modifying
wework/**, read and followwework/AGENTS.md. It contains the desktop UI, local runtime, i18n, and Electron verification rules. - Before modifying
frontend/**, read and followfrontend/AGENTS.md. It contains web-frontend state, responsive UI, and i18n rules. - Add module-specific instructions beside a module only when they cannot be expressed as a repository-wide rule.
Domain model
Ghost (prompt, MCP servers, skills)
-> Bot (Ghost + Shell + optional Model)
-> Team (Bots + collaboration mode)
-> Task (Team + Workspace)
Code uses CRD terms. In Chinese UI, Team is “智能体” and Bot is “机器人”; English UI calls them Agent and Bot.
- A Kind resource is identified by
namespace,name, anduser_id; always query all three. TaskandWorkspaceuseTaskResourceintasks; other CRDs useKindinkinds.- Shell types:
ClaudeCode,Agno,Dify, andChat.
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.
- 3d ago First seen · 100 lines · 1,396 tokens per session scan C dcb84150643e
Wegent AGENTS.md is an instructions file published in the GitHub repository wecode-ai/Wegent (747 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,396 tokens to every session, about $0.0070 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
eliza AGENTS.md
Instructions for elizaOS/eliza, covering elizaos repository guide, how repository instructions work, naming, before editing and toolchain.
LobsterAI AGENTS.md
AGENTS.md instructions for netease-youdao/LobsterAI, covering agents.md, instruction scope, project snapshot, cowork vs openclaw and commands.
better-chatbot AGENTS.md
AGENTS.md instructions for keinsaasforever/better-chatbot, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
zhin CLAUDE.md
Instructions for zhinjs/zhin, covering claude.md, project overview, commands, bootstrap (first-time or after clean) and single package.
zhin zhin-plugin.instructions.md
Instructions for zhinjs/zhin, covering zhin plugin runtime authoring, package contract, convention directories, imports and native typescript and command routes.
skill-based-architecture AGENTS.md
Instructions for WoJiSama/skill-based-architecture, covering agents.md, quick routing (survives context truncation), auto-triggers and red flags — stop.