Crawl4AI is an open-source web crawler and scraper that converts online content into clean Markdown for language-model retrieval, agents, and data pipelines. It is used for web extraction at scale where structured, LLM-ready content is needed. The catalogue includes a command for working with Crawl4AI.
Borrowing it
Nothing to install: this file belongs to unclecode/crawl4ai. 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/unclecode/crawl4ai/main/.claude/commands/c4ai-check.mdgit clone --depth 1 https://github.com/unclecode/crawl4aiWrote 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/commands/unclecode/crawl4ai/c4ai-check)<a href="https://agentmods.dev/commands/unclecode/crawl4ai/c4ai-check"><img src="https://agentmods.dev/badge/commands/unclecode/crawl4ai/c4ai-check/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/commands/unclecode/crawl4ai/c4ai-check"><img src="https://agentmods.dev/badge/commands/unclecode/crawl4ai/c4ai-check.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 | $0.00013 | $0.00768 |
| Opus 5.5 | $0.00005 | $0.00307 |
| Sonnet 5.5 | $0.00003 | $0.00154 |
| Haiku 4.5 | $0.00001 | $0.00077 |
Grade A, and why
c4ai-check 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crawl4AI Change Verification (c4ai-check)
You are verifying that recent code changes work correctly AND haven't broken anything else. This is a two-phase process.
Input: $ARGUMENTS
PHASE 1: Adversarial Testing of Current Changes
Based on the change description above:
-
Understand the change: Read the relevant files that were modified. Use
git diffto see exactly what changed. -
Write targeted adversarial tests: Create a temporary test file at
tests/regression/test_tmp_changes.pythat HEAVILY tests the specific changes:- Normal cases (does it work as intended?)
- Edge cases (boundary values, empty inputs, None, huge inputs)
- Regression cases (does the OLD bug still occur? it shouldn't)
- Interaction cases (does it break anything it touches?)
- Adversarial cases (weird inputs that could expose issues)
- At least 10-15 focused tests per change area
Rules for the temp test file:
- Use
@pytest.mark.asynciofor async tests - Use real browser crawling where needed (
async with AsyncWebCrawler()) - Use the
local_serverfixture from conftest.py when needed - NO mocking - test real behavior
- Each test must have a clear docstring explaining what it verifies
-
Run the targeted tests:
.venv/bin/python -m pytest tests/regression/test_tmp_changes.py -v --tb=short -
Report results: Show pass/fail summary. If any fail, investigate and determine if it's a real bug in the changes or a test issue. Fix the tests if needed, fix the code if there's a real bug.
PHASE 2: Full Regression Suite
After Phase 1 passes:
-
Run the full regression suite (skip network tests for speed):
.venv/bin/python -m pytest tests/regression/ -v -m "not network" --tb=short -q -
Analyze failures: For any failures:
- Determine if the failure is caused by the current changes (REGRESSION) or pre-existing
- Regressions are blockers - report them clearly
- Pre-existing failures should be noted but don't block
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 · 90 lines · 13 tokens per session scan A b7d2ef948acd
c4ai-check is a command published in the GitHub repository unclecode/crawl4ai (86,470 stars, last pushed yesterday), licensed Apache-2.0. It adds 13 tokens to every session and 768 once invoked, about $0.0001 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 commands, from other repositories
expect
Diff-aware AI browser testing — reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, or running regression checks on…
fire-verify-uat
Conversational User Acceptance Testing with automatic parallel diagnosis on failures.
tdd
Test-driven change — write the failing test first, then implement.
story-and-test
For the component(s) in scope.
install
This page explains how the livewiki install CLI command detects installed coding agents and safely configures the livewiki MCP server entry, hook templates, shared skills, and optional pointer files.
pointer
This page documents the livewiki pointer subcommand, which manages an opt-in "pointer" block inside an AGENTS.md or CLAUDE.md file at the repository root.