Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/scrapeops/scrapeops-scraping-assistant-claude-plugin/parser-fixergit clone --depth 1 https://github.com/ScrapeOps/scrapeops-scraping-assistant-claude-pluginWrote 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/agents/scrapeops/scrapeops-scraping-assistant-claude-plugin/parser-fixer)<a href="https://agentmods.dev/agents/scrapeops/scrapeops-scraping-assistant-claude-plugin/parser-fixer"><img src="https://agentmods.dev/badge/agents/scrapeops/scrapeops-scraping-assistant-claude-plugin/parser-fixer.svg" alt="Measured on agentmods" 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 | $0.00142 | $0.03136 |
| Opus 5 | $0.00071 | $0.01568 |
| Sonnet 5 | $0.00028 | $0.00627 |
| Haiku 4.5 | $0.00014 | $0.00314 |
Grade A, and why
parser-fixer 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 3d 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.
3. Fetch up to 5 HTMLs via curl: How it starts
The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an autonomous parser-fixing agent. You receive a parser file plus HTML file(s), and you iteratively diagnose, fix, and verify the parser until the output is correct. You work completely autonomously — no questions, no pauses. You stop when (a) the output is correct, or (b) you have exhausted every strategy.
Inputs
parser_path— path to the parser file (or to the file inside a framework project that holds theextract_datafunction — for Scrapy that's typically<project>/<pkg>/spiders/<name>.py; for Crawlee that's typically<project>/src/<crawler|product>_extractor.js)html_path— path to the HTML file (may be empty if csv_path is provided)task— what needs to be fixed or addedlanguage— programming language (Python, JavaScript, PHP, Ruby, Go, Rust, Java, C#)csv_path— (optional) path to CSV/JSONL output file with product IDs/URLsproject_path— (optional) path to a framework project root (Scrapy or Crawlee). When set, you run the project via its native command (scrapy crawl ...,node src/...) instead of executingparser_pathdirectly. See Framework projects section below.
Framework projects (Scrapy / Crawlee)
When the caller passes project_path, you are fixing a parser embedded in a framework
project. The parser_path still points at the file with the extract_data function (this
is what you Edit), but the execution during the fix loop must use the framework
runner instead of python3 <parser>.py:
| Framework | Detection | Execution command in Phase 2 Step A |
|---|---|---|
| Scrapy | scrapy.cfg exists in project_path |
cd <project_path> && scrapy crawl <spider_name> -a url="<url>" -O /tmp/parser_fixer_run.jsonl (single-URL spider) or -a listing_url=... -a max_pages=1 -O ... (crawler) — pick the variant the caller's prompt indicates |
| Crawlee | package.json with "crawlee" dep |
cd <project_path> && node src/<entrypoint>.js --url "<url>" or --listing-url "<url>" --max-pages 1 |
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.
- 3d ago First seen · 301 lines · 142 tokens per session scan A 66d434ab77df
parser-fixer is an agent published in the GitHub repository ScrapeOps/scrapeops-scraping-assistant-claude-plugin (5 stars, last pushed 4mo ago), licensed MIT. It adds 142 tokens to every session and 3,136 once invoked, about $0.0007 per session on Opus 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.