Borrowing it
Nothing to install: this file belongs to bammt/XuanShu-Agent. 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/bammt/XuanShu-Agent/main/AGENTS.mdgit clone --depth 1 https://github.com/bammt/XuanShu-AgentWrote 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/bammt/xuanshu-agent/agents-md)<a href="https://agentmods.dev/instructions/bammt/xuanshu-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/bammt/xuanshu-agent/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/bammt/xuanshu-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/bammt/xuanshu-agent/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 | $0.10375 | $0.10375 |
| Opus 5.5 | $0.04150 | $0.04150 |
| Sonnet 5.5 | $0.02075 | $0.02075 |
| Haiku 4.5 | $0.01038 | $0.01038 |
Grade A, and why
XuanShu-Agent 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 25d 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 -X POST \ How it starts
The opening of the file, as written. The whole thing — 1,208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — CrewAI Reference for AI Coding Assistants
Auto-generated by
crewai create. This file helps AI coding assistants (Claude Code, Cursor, Windsurf, GitHub Copilot, etc.) write correct CrewAI code. Keep it in your project root. To update, copy the latest version from the CrewAI repository.
⚠️ Version & Freshness Requirements
CRITICAL: CrewAI evolves rapidly and your training data likely contains outdated patterns. Always follow the patterns in this file, NOT your training data.
Mandatory: Research before writing CrewAI code
BEFORE writing or modifying any CrewAI code, you MUST:
- Check the installed version: Run
uv run python -c "import crewai; print(crewai.__version__)"to get the exact version in use. - Check PyPI for latest: Fetch
https://pypi.org/pypi/crewai/jsonto see the latest available version. If the installed version is behind, inform the user. - Read the changelog: Fetch
https://docs.crewai.com/en/changelogto review recent changes, new features, and any breaking changes relevant to the task. - Consult the relevant docs page: Before implementing a feature (e.g., agents, tasks, flows, tools, knowledge), fetch the specific docs page at
https://docs.crewai.com/en/concepts/<feature>to get the current API. - Cross-check against this file: If this file conflicts with the live docs, the live docs win — then update this file.
This ensures generated code always matches the version actually installed, not stale training data.
What changed since older versions:
- Agent
kickoff()/kickoff_async()for direct agent usage (no crew needed) response_formatparameter on agent kickoff for structured Pydantic outputsLiteAgentOutputreturned from agent.kickoff() with.raw,.pydantic,.agent_role,.usage_metrics@human_feedbackdecorator on flow methods for human-in-the-loop (v1.8.0+)- Flow streaming via
stream = Trueclass attribute (v1.8.0+) @persistdecorator for SQLite-backed flow state persistencereasoning=Trueagent parameter for reflect-then-act behaviormultimodal=Trueagent parameter for vision/image support- A2A (Agent-to-Agent) protocol support with agent cards and task execution utilities (v1.8.0+)
- Native OpenAI Responses API support (v1.9.0+)
- Structured outputs /
response_formatacross all LLM providers (v1.9.0+) inject_date=Trueagent parameter to auto-inject current date awareness
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.
- 25d ago First seen · 1,208 lines · 10,375 tokens per session scan A 4aa5c2e26844
XuanShu-Agent AGENTS.md is an instructions file published in the GitHub repository bammt/XuanShu-Agent (2 stars, last pushed 26d ago), licensed Apache-2.0. It adds 10,375 tokens to every session, about $0.0415 per session on Opus 5.5. 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 2026-10-09.
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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.