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 instructions/kaushalendra-marcus/evident/claude-mdgit clone --depth 1 https://github.com/Kaushalendra-Marcus/evidentWrote 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/instructions/kaushalendra-marcus/evident/claude-md)<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="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 5.1 | $0.02351 | $0.02351 |
| Opus 5 | $0.01175 | $0.01175 |
| Sonnet 5 | $0.00470 | $0.00470 |
| Haiku 4.5 | $0.00235 | $0.00235 |
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 5d 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]]: 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
Tier3Strategyprotocol for interactive/login-walled content
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.
- 5d ago First seen · 182 lines · 2,351 tokens per session scan A c0e390614f32
evident CLAUDE.md is an instructions file published in the GitHub repository Kaushalendra-Marcus/evident (2 stars, last pushed 29d ago), licensed Apache-2.0. It adds 2,351 tokens to every session, about $0.0118 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 instructions, from other repositories
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.
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).
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).