Borrowing it
Nothing to install: this file belongs to laurentvv/crawl4ai-mcp-llm. 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/laurentvv/crawl4ai-mcp-llm/main/AGENTS.mdgit clone --depth 1 https://github.com/laurentvv/crawl4ai-mcp-llmWrote 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/laurentvv/crawl4ai-mcp-llm/agents-md)<a href="https://agentmods.dev/instructions/laurentvv/crawl4ai-mcp-llm/agents-md"><img src="https://agentmods.dev/badge/instructions/laurentvv/crawl4ai-mcp-llm/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/laurentvv/crawl4ai-mcp-llm/agents-md"><img src="https://agentmods.dev/badge/instructions/laurentvv/crawl4ai-mcp-llm/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 | $0.02235 | $0.02235 |
| Opus 5.5 | $0.00894 | $0.00894 |
| Sonnet 5.5 | $0.00447 | $0.00447 |
| Haiku 4.5 | $0.00224 | $0.00224 |
Grade A, and why
crawl4ai-mcp-llm 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 12d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — crawl4ai-mcp-llm
Instructions for any AI coding agent working in this repository. Structure: common block (delimited, resyncable) + project-specific part (free).
Priority on conflict: explicit user instruction > this repo's §7 > this common block. The §5 prohibitions are lifted only on a formal explicit request. This block is overwritten on every sync: add nothing here (lessons → §7, see §6).
§1 Environment
- Default machine: Windows 11, shell Git Bash — any deviation (PowerShell 7, WSL, Linux…) is declared in §7; use ONLY the declared shell's commands.
- Python:
uvonly — neverpip install, neverrequirements.txt(uv add/uv run). - Machine paths: never hardcoded — go through the project configuration (config.py / .env / dedicated section).
- Code search: on large repositories (> 5k files, or a
.tgrep/index folder present), prefer the fast indexedtgrepCLI from the PATH over recursivegrep/findscans —tgrep -- "pattern" .,tgrep -t <type> -- "pattern" .(first use:tgrep index .; keep.tgrep/git-ignored). Below ~2k files, plaingit grepis already instant. - Text files: UTF-8 without BOM, line endings per
.gitattributes. Never markdown exported or pasted from a rich editor (Notion, Word…): it arrives escaped and becomes unreadable for the agent. - Language: English for everything written in the repository (code, comments, docs, commit messages, ledger); French for chat replies to the user. Any deviation is declared in §7.
- Long context (architecture, detailed lessons, ecosystem): see the repo's
PROJECT_MEMORY.mdordocs/— AGENTS.md stays deliberately short.
§2 On-disk state = source of truth
Never rely on the context window alone: it degrades, gets compressed, gets erased. Work state lives in one DuckDB database, .agent/state.duckdb, managed only through the agent-state skill CLI (shipped by the kit; another path is declared in §7):
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.
- 12d ago Changed · +3 lines · +136 tokens per session bafe01b62b2f
- 19d ago Changed · +20 tokens per session d1442e0de176
- 21d ago Changed · -17 lines · -202 tokens per session 2eb9c0b37b53
- 25d ago Changed · +1 lines · +105 tokens per session 1decc11e949e
- 1mo ago First seen · 120 lines · 2,176 tokens per session scan A 180b3ccfc151
crawl4ai-mcp-llm AGENTS.md is an instructions file published in the GitHub repository laurentvv/crawl4ai-mcp-llm (45 stars, last pushed 5d ago), licensed MIT. It adds 2,235 tokens to every session, about $0.0089 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 2026-10-02.
crawl4ai-mcp-llm AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| crawl4ai-mcp-llm AGENTS.mdlaurentvv/crawl4ai-mcp-llm | Instructions file | 45 | 5d ago | MIT | A | 2,235 | 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 | today | 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 |