content-core CLAUDE.md

content-core CLAUDE.md is an instructions file for coding agents from lfnovo/content-core. It costs 2,748 tokens per session, scanned A, original, MIT.

Repository instructions for content-core, a library and command-line tool for extracting and summarizing content from URLs, files, and text.

In plain words
What is it for?
Use them when changing extraction or summarization code, the command-line interface, configuration, or MCP interface, and when checking changes before submission.
Why use it?
They show agents how to install the project, run the required tests, lint the code, build the package, and use its commands without guessing.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/lfnovo/content-core/claude-md
Clone the repo
git clone --depth 1 https://github.com/lfnovo/content-core

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 content-core CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lfnovo/content-core/claude-md.svg)](https://agentmods.dev/instructions/lfnovo/content-core/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lfnovo/content-core/claude-md"><img src="https://agentmods.dev/badge/instructions/lfnovo/content-core/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,748 This file is loaded in full into every session.
When invoked 2,748 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.02748 $0.02748
Opus 5 $0.01374 $0.01374
Sonnet 5 $0.00550 $0.00550
Haiku 4.5 $0.00275 $0.00275

Measured 4d ago against content hash 73252dd5ec5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

content-core CLAUDE.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 4d 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.

CLAUDE.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Content Core

Library for extracting and summarizing content from URLs, files, and text.

Commands

  • Install dependencies: uv sync --group dev
  • Run tests: make test (unit + integration) or uv run pytest -v
  • Run single test: uv run pytest -k "test_name"
  • Run e2e tests: make test-e2e (requires network + API keys)
  • Run all tests: make test-all
  • Linting: make ruff (runs ruff check . --fix)
  • Build package: uv build

CLI

content-core extract <source> [--format text|json] [--engine ENGINE]
content-core summarize [content] [--context CONTEXT]
content-core mcp
content-core config list|set|delete

For Automated Agents

If you are an automated coding agent (harny, Claude Code in headless mode, etc.) working on this repo:

Install command

uv sync --group dev

Validator command

uv run pytest tests/unit tests/integration -v

This is the gate. It returns clean pass/fail in ~15s, requires no credentials or network, and matches what CI enforces on main (CI runs only tests/unit; integration tests are also safe locally — no network/API keys). For targeted feedback during iteration, use uv run pytest -k "<keyword>" per the table in the Testing section below.

Do NOT use as gates

  • ruff check — available via make ruff but NOT enforced in CI. Including it as a validator gate would surface unaudited pre-existing findings unrelated to your task.
  • mypy — not enforced in CI. No baseline configured. Same risk.
  • make test-e2e / make test-e2e-heavy — require network access, API keys for LLM/STT providers, and large model downloads. Will fail in a sandboxed worktree.

If you believe a task genuinely requires lint or type cleanup, do it as a separate task with explicit scope, not as a side effect of an unrelated change.

Scope guidance

  • Single processor changes (processors/url/*.py, processors/document/*.py, processors/media/*.py) are the natural unit of work — keep changes confined to one file plus its matching test in tests/unit/.
  • Avoid touching extraction.py (orchestrator) or config.py unless the task explicitly targets routing or configuration.
  • New processors should follow the Processor protocol in src/content_core/processors/protocol.py.

Read the full file on GitHub · 217 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. 4d ago First seen · 217 lines · 2,748 tokens per session scan A 73252dd5ec5e

Subscribe to this mod's changes

content-core CLAUDE.md is an instructions file published in the GitHub repository lfnovo/content-core (170 stars, last pushed 2d ago), licensed MIT. It adds 2,748 tokens to every session, about $0.0137 per session on Opus 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens