Borrowing it
Nothing to install: this file belongs to hjl2004-10/Agent-Worlds. 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/hjl2004-10/Agent-Worlds/main/AGENTS.mdgit clone --depth 1 https://github.com/hjl2004-10/Agent-WorldsWrote 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/hjl2004-10/agent-worlds/agents-md)<a href="https://agentmods.dev/instructions/hjl2004-10/agent-worlds/agents-md"><img src="https://agentmods.dev/badge/instructions/hjl2004-10/agent-worlds/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/hjl2004-10/agent-worlds/agents-md"><img src="https://agentmods.dev/badge/instructions/hjl2004-10/agent-worlds/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 | $0.00624 | $0.00624 |
| Opus 5.5 | $0.00250 | $0.00250 |
| Sonnet 5.5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
Agent-Worlds 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 2mo 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Scope
These instructions apply to the entire repository rooted at this directory.
General
- Prefer concise Chinese when replying to the user, unless the user asks for another language.
- Read only the files needed for the current task. Do not bulk-read the whole repo.
- Before editing code, inspect the relevant files first.
- Prefer
rg/rg --filesfor search. - Use non-destructive commands by default.
Project Notes
- Backend entry:
main.py - Frontend workspace:
static/ - Frontend dev URL is usually
http://localhost:5173/ - Backend API is usually on port
5000
MCP Usage
This workspace is configured with two browser MCPs:
mcp__playwright__*mcp__chrome-devtools__*
Use them with clear division of responsibility instead of mixing them randomly.
Playwright MCP
Prefer Playwright MCP for user-like interaction and functional UI testing.
- Use it for:
- opening pages
- clicking buttons, tabs, links
- typing into forms
- running short end-to-end UI flows
- taking interaction-oriented snapshots/screenshots
- Prefer it when the goal is:
- "test whether the page works"
- "reproduce the user path"
- "verify a control can be clicked"
Guidelines:
- Use role/text/ref-based actions when possible.
- Keep flows short and deterministic.
- Avoid repeatedly requesting full-page snapshots if a single action result is enough.
- If token cost matters, do not overuse
browser_snapshotafter every step.
Chrome DevTools MCP
Prefer Chrome DevTools MCP for browser-side debugging and inspection.
- Use it for:
- console inspection
- network request inspection
- page structure snapshots
- performance or low-level browser debugging
- request-level investigation
- Prefer it when the goal is:
- "find frontend errors"
- "inspect polling / xhr / fetch traffic"
- "check what the browser is actually loading"
- "analyze console warnings"
Guidelines:
- Prefer DevTools MCP over Playwright MCP for network-heavy analysis.
- Use filtered request listing where possible instead of dumping everything.
- Use console listing before guessing about frontend failures.
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.
- 2mo ago First seen · 98 lines · 624 tokens per session scan A 33b1e7ff6ece
Agent-Worlds AGENTS.md is an instructions file published in the GitHub repository hjl2004-10/Agent-Worlds (9 stars, last pushed 2mo ago), licensed MIT. It adds 624 tokens to every session, about $0.0025 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 2026-08-31.
Agent-Worlds AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Agent-Worlds AGENTS.mdhjl2004-10/Agent-Worlds | Instructions file | 9 | 2mo ago | MIT | A | 624 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |