What is evident CLAUDE.md?

Project instructions for Evident, an open-source service that fetches and extracts web data while reporting how confident it is in each result.

Setting up Evident, running its MCP server or REST API, choosing optional features, and running its tests.

They give a coding agent the project's purpose, setup options, run commands, and test commands in one place.

How Kaushalendra-Marcus/evident configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Kaushalendra-Marcus/evident. 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/Kaushalendra-Marcus/evident/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Kaushalendra-Marcus/evident

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/kaushalendra-marcus/evident/claude-md/github.svg)](https://agentmods.dev/instructions/kaushalendra-marcus/evident/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/kaushalendra-marcus/evident/claude-md"><img src="https://agentmods.dev/badge/instructions/kaushalendra-marcus/evident/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/kaushalendra-marcus/evident/claude-md"><img src="https://agentmods.dev/badge/instructions/kaushalendra-marcus/evident/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,351 This file is loaded in full into every session.

When invoked 2,351 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.

Model	Per session	Once invoked
Fable 5.1	$0.02351	$0.02351
Opus 5.5	$0.00940	$0.00940
Sonnet 5.5	$0.00470	$0.00470
Haiku 4.5	$0.00235	$0.00235

Measured 2mo ago against content hash c0e390614f32, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

evident 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.

async def fetch(slug: str, entity_name: str) -> list[dict[str, Any]]:

CLAUDE.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 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.

Project Overview

Evident is an open-source, agent-agnostic extraction and fetch layer that returns typed data with a transparent confidence score on every result. The core thesis: orchestrate best-in-class scraping engines (Crawl4AI, Playwright) behind a resilience ladder, score trustworthiness, and expose through MCP/REST/SDK.

Not another scraper — a trust layer that tells autonomous agents how sure they should be that a result is correct.

Development Commands

Setup

python -m venv .venv && source .venv/bin/activate
pip install -e ".[all]"     # everything, including dev/test tooling
pip install -e ".[render]"  # Tier 2 JS-rendered pages only
pip install -e ".[llm]"     # LLM extraction only (needs ANTHROPIC_API_KEY)
pip install -e ".[api]"     # REST API only

Running

# MCP server (stdio, for Claude Desktop/Code/Cursor)
evident-mcp
# or
python -m evident.server

# REST API (if [api] extra is installed)
uvicorn evident.api.rest:app --reload

Testing

pytest                           # run all tests
pytest tests/test_ladder.py      # single test file
pytest -k test_tier1             # tests matching pattern
pytest -v                        # verbose output

Tests use respx to mock HTTP responses — they run deterministically without live network access. This was non-negotiable after silent breakage in the predecessor project.

Linting

ruff check src/ tests/          # check only
ruff check --fix src/ tests/    # auto-fix where possible

Ruff config is in pyproject.toml — pyflakes + pycodestyle essentials + import sorting + bugbear (B) to catch always-true conditionals and similar bugs.

Architecture

The Resilience Ladder (core differentiator)

src/evident/core/ladder.py orchestrates tier escalation:

Tier 1 (tier1_static.py): httpx + trafilatura — cheap, fast, covers server-rendered pages
Tier 2 (tier2_rendered.py): Crawl4AI/Playwright — JS-rendered pages, real browser
Tier 3 (not implemented): pluggable Tier3Strategy protocol for interactive/login-walled content

Read the full file on GitHub · 182 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.

2mo ago First seen · 182 lines · 2,351 tokens per session scan A c0e390614f32

Subscribe to this mod's changes

evident CLAUDE.md is an instructions file published in the GitHub repository Kaushalendra-Marcus/evident (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 2,351 tokens to every session, about $0.0094 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.

Research dataevaluation scroring webscraper webscraping-data

evident CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
evident CLAUDE.mdKaushalendra-Marcus/evident	Instructions file	3	3mo ago	Apache-2.0	A	2,351	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	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

evident: Instructions file for Claude Code