agentmods.dev

solocrawl: Instructions file for Claude Code

CLAUDE.md

solocrawl CLAUDE.md is an instructions file for Claude Code from hlavacm/solocrawl. It costs 1,388 tokens per session, scanned A, original, MIT.

Repository-specific instructions for SoloCrawl, a self-hosted Python tool for web search, web-page scraping, and package-version lookup. They describe its specification-led development process, architecture, quality checks, and project limits.

In plain words
What is it for?
Use them when planning or implementing SoloCrawl features, especially before non-trivial work, API integrations, tests, and checks that confirm the project still runs.
Why use it?
They give an AI coding assistant the project context needed to make changes that follow the repository’s design and development rules.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is hlavacm/solocrawl's own configuration. It tells Claude Code how to work on solocrawl itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything solocrawl configures →

not rated 2repo 18d ago A scan 1,388 tokens original MIT
View source ↗ hlavacm/solocrawl
Reuse

Borrowing it

Nothing to install: this file belongs to hlavacm/solocrawl. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/hlavacm/solocrawl/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/hlavacm/solocrawl

Made for: Claude Code.

Wrote 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.

agentmods badge for solocrawl CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hlavacm/solocrawl/claude-md/github.svg)](https://agentmods.dev/instructions/hlavacm/solocrawl/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/hlavacm/solocrawl/claude-md"><img src="https://agentmods.dev/badge/instructions/hlavacm/solocrawl/claude-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.

agentmods 80×15 button for solocrawl CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hlavacm/solocrawl/claude-md"><img src="https://agentmods.dev/badge/instructions/hlavacm/solocrawl/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,388 This file is loaded in full into every session.
When invoked 1,388 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01388 $0.01388
Opus 5.5 $0.00555 $0.00555
Sonnet 5.5 $0.00278 $0.00278
Haiku 4.5 $0.00139 $0.00139

Measured 2mo ago against content hash 715b623ee706, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

solocrawl CLAUDE.md 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `core/fetch/` — one shared `httpx.AsyncClient` per process. `fetcher.fetch(url, force_browser=False)`
CLAUDE.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

SoloCrawl is a self-hosted, fully async Python tool for web search, scraping, and package-version lookup, exposed three ways: an MCP server (FastMCP, stdio), a CLI, and a library. Zero accounts/API keys for the default setup. Requires Python 3.14+.

Spec-driven workflow

This project is built from specs in docs/, not ad hoc. Before non-trivial work:

  • Read docs/context/ — project.md (scope + non-goals), architecture.md (how it's assembled + performance guardrails), conventions.md (how to write code), agent-workflow.md (Definition of Done).
  • Features live in docs/features/NN_*.md and are built one at a time in the order of docs/features/ROADMAP.md. Each feature must leave the project runnable.
  • Stick to the intent of a spec, not its literal wording; verify real-world API shapes when they differ. Never cross the non-goals in project.md (no RAG/embeddings, no own version DB, no ToS/robots bypass, no paid-key default providers, no logic in the MCP/CLI shells).

Quality gate (mandatory — must all pass before a feature is "done")

ruff check . && ruff format --check .   # lint + format, must be clean
pyright                                  # standard mode, no errors (this is the gate, not Pylance)
pytest                                   # green; runs against fixtures, never the live web

Run a single test: pytest tests/test_federation.py::test_name -q

Setup

python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"          # add ".[browser]" for Playwright fallback, ".[all]" for everything
playwright install chromium      # only if using the browser fallback

Run locally: solocrawl scrape <url> / solocrawl search "<q>" / solocrawl package <name> --ecosystem <eco>. MCP entry point is solocrawl-mcp (stdio).

Read the full file on GitHub · 104 lines

Changes

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.

  1. 2mo ago First seen · 104 lines · 1,388 tokens per session scan A 715b623ee706

Subscribe to this mod's changes

solocrawl CLAUDE.md is an instructions file published in the GitHub repository hlavacm/solocrawl (2 stars, last pushed 18d ago), licensed MIT. It adds 1,388 tokens to every session, about $0.0056 per session on Opus 5.5. 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.

Related

solocrawl CLAUDE.md compared with instructions from other repositories

solocrawl CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
solocrawl CLAUDE.mdhlavacm/solocrawlInstructions file218d agoMITA1,388Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode