Borrowing it
Nothing to install: this file belongs to Xuanwo/xurl. 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/Xuanwo/xurl/main/AGENTS.mdgit clone --depth 1 https://github.com/Xuanwo/xurlWrote 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/xuanwo/xurl/agents-md)<a href="https://agentmods.dev/instructions/xuanwo/xurl/agents-md"><img src="https://agentmods.dev/badge/instructions/xuanwo/xurl/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/xuanwo/xurl/agents-md"><img src="https://agentmods.dev/badge/instructions/xuanwo/xurl/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 | $0.01598 | $0.01598 |
| Opus 5.5 | $0.00639 | $0.00639 |
| Sonnet 5.5 | $0.00320 | $0.00320 |
| Haiku 4.5 | $0.00160 | $0.00160 |
Grade A, and why
xurl 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines
Workspace Responsibilities
xurl-core: all URI parsing, provider resolution, raw file reading, and markdown rendering lives here. It owns provider-specific parsers for Codex, Claude, and OpenCode plus the shared service layer (resolve_thread,render_thread_markdown,render_thread_head_markdown).xurl-cli: thin CLI that parsesxurl <uri>arguments withclap, wires upProviderRoots::from_env_or_home, emits metadata warnings tostderr, and prints rendered markdown (render_thread_markdown).
CLI Parameter & Provider Behavior Matrix
- The CLI accepts a single
<uri>and an optional-I/--headflag for frontmatter-only output. ProviderRoots::from_env_or_homesources the base directories using:- Codex:
CODEX_HOMEthen~/.codex - Claude:
CLAUDE_CONFIG_DIRthen~/.claude - OpenCode:
XDG_DATA_HOME/opencodethen~/.local/share/opencode
- Codex:
render_thread_markdownconverts provider payloads into a markdown thread view with frontmatter metadata plus user/assistant-focused content; warnings fromresolved.metadata.warningsare emitted tostderrbefore the primary output.
Design Docs
- Design documents live under
docs/. - Before proposing, implementing, or revising URI behavior, query behavior, or other user-facing semantics, read the relevant design docs in
docs/first and align with them. - If implementation diverges from an existing design doc, update the design doc in the same change or explain clearly why the divergence is intentional.
Error Handling & Exit Contract
mainmaps anyxurl_core::Resultfailure to a non-zero exit code (1) and printserror: <message>onstderr; successes return exit code 0.- Common failure cases include invalid URI syntax, missing provider roots, unresolved session IDs, unreadable files, empty files, and non-UTF-8 payloads (
read_thread_rawexplicitly guards against empty and non-UTF8 data). - Metadata warnings and diagnostics are printed on
stderrbut do not change the exit code, making it clear that onlyErrresults trigger failure.
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 · 80 lines · 1,598 tokens per session scan A 697bb6b9009f
xurl AGENTS.md is an instructions file published in the GitHub repository Xuanwo/xurl (360 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 1,598 tokens to every session, about $0.0064 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.