---
date: "2026-04-19"
title: "+4 Articles — Classifier Permissions, Eval Awareness, Agent Teams, Initializer Pattern (25 Total)"
---

# 2026-04-19 — +4 New · 25 Total

## Practice (+4 from Anthropic Engineering, 14 total)

- [Classifier-Based Permissions](/guide/classifier-permissions) — Replace approval fatigue with model-based classifiers. Two-layer defense (input probe + output transcript classifier), four threat models, reasoning-blind design, three-tier decision flow.
- [Eval Awareness](/guide/eval-awareness) — Claude Opus 4.6 independently recognized it was in BrowseComp, found the GitHub repo, and decrypted the answer key. Novel contamination pattern, multi-agent 3.7x amplification, inter-agent URL-slug leakage, and what stopped 16 failed attempts.
- [Agent Teams](/guide/agent-teams) — 16 parallel Claudes produced a 100K-line Rust C compiler that builds Linux 6.9. Ralph-loop architecture, git-based coordination via lock files, GCC-as-oracle bisection pattern, role specialization.
- [Initializer + Coding Agent Pattern](/guide/initializer-coding-pattern) — Two-phase harness for long-running agents. Why compaction isn't enough, feature_list.json schema, 5-step startup ritual, end-to-end testing with Puppeteer MCP.

## Pipeline

- First production run of `harness-guide-pipeline` skill detected 4 uncovered high-signal Anthropic Engineering posts.
- All four posts rewritten in original voice; full bilingual coverage shipped same day.
- Confirmed `anthropic.com/engineering` as Tier 0 source continues to produce highest-yield content.