Index

中文 | English

This index is the catalog layer for the vault: it groups durable pages by role and source family so readers can decide where to drill deeper.

Start Here

• Wiki Overview - Guided entry point for the vault, including reading paths, core topics, and source families.

Concepts

• LLM Wiki - Persistent knowledge pattern that compiles synthesis into markdown and treats raw-path refactors as maintenance rather than re-ingest.

Entities

Topics

• Agent-First Repositories - Repository-local docs, tools, and control systems that make autonomous agent work legible and enforceable.
• Agent-Readable Design Systems - Versioned markdown design contracts that make frontend taste and UI constraints legible to agents.
• Agent Harness Design - Planner-generator-evaluator patterns, handoff artifacts, and simplification heuristics for long-running agent systems.
• Codex Operating Practices - Durable operating model for configuring Codex, packaging repeatable workflows, and choosing the right execution surface.
• Knowledge Operations - Canonical ingest, screenshot OCR, query, lint, and raw-taxonomy-refactor loop for maintaining the bilingual vault and its newest-first log.
• Vault Architecture - Three-layer model tying together reorganizable raw sources, bilingual indexes, the markdown wiki, and the schema contract.

Source Families

Anthropic / Claude Code / Everything Claude Code

• Affaan Mustafa Claude Code Shorthand Guide - Source on skills versus commands, hook design, MCP and plugin budgeting, subagent scoping, and practical Claude Code setup surfaces.
• Affaan Mustafa Claude Code Longform Guide - Source on session logs, strategic compaction, token-aware delegation, eval loops, bounded parallelization, and reusable Claude Code operating patterns.
• Everything Claude Code GitHub Repository - Repository snapshot showing ECC as a multi-harness distribution surface for rules, hooks, skills, Codex config, and packaged agent workflows.

Anthropic

• Anthropic Harness Design For Long-Running Application Development - Source on planner-generator-evaluator harnesses, skeptical evaluation, and reducing scaffolding as models improve.
• Claude Managed Agents Overview - Product overview defining Anthropic's managed agent primitives, beta constraints, rate limits, and the hosted alternative to building your own loop.
• Scaling Managed Agents: Decoupling The Brain From The Hands - Engineering source on meta-harness interfaces, externalized session state, credential separation, and many-brains many-hands scaling.
• Claude Code Auto Dream Memory Consolidation - Source on periodic memory consolidation, contradiction repair, absolute dating, and keeping index files compact.
• Claude Mythos Preview Cybersecurity Assessment - Source on real-world zero-day evaluation, exploit-capable model scaffolds, and coordinated defensive rollout.
• Claude Mythos Preview System Card - Source on Anthropic's full release-governance, capability, cyber, alignment, welfare, and safeguards record for Mythos Preview.

OpenAI / Codex

• OpenAI Harness Engineering In An Agent-First World - Source on Codex-first engineering, repository legibility, and treating docs and tooling as the agent control plane.
• Codex Best Practices - Source on prompt structure, AGENTS.md usage, testing, MCP, skills, automations, and session controls.
• Codex Config Basics - Source on configuration precedence, common control knobs, trust-gated project config, and feature flags.
• Codex Advanced Configuration - Source on profiles, one-off overrides, providers, hooks, telemetry, and deeper Codex runtime controls.
• Codex Configuration Reference - Source on the authoritative config schema, key renames, and admin-enforced requirements.
• Codex Sample Configuration - Source containing the annotated config.toml specimen for selective copying and comparison.
• Codex CLI Slash Commands - Source on the interactive control surface for live sessions, including permissions, compaction, diff review, and diagnostics.
• Codex Non-Interactive Mode - Source on codex exec, machine-readable output, CI auth, and non-interactive guardrails.
• Codex LLM Wiki Skill - Source bundle that operationalizes the abstract LLM Wiki pattern as a Codex skill with root-resolution, bilingual, automation, and safe-refactor helpers.
• Codex Agent Skills - Source on skill packaging, discovery scopes, implicit invocation boundaries, and plugin distribution.
• Codex Subagents - Source on delegation limits, custom agent files, and concurrency/depth controls.

Karpathy

• Karpathy LLM Wiki Gist - Foundational source describing the LLM-maintained wiki pattern and its operating model.

Ralph

• Ralph Wiggum Loop Technique - Source on simple monolithic agent loops, one-item iterations, repo-persisted memory, and bounded subagent use.
• Ralph Step-By-Step Guide - Source on the concrete scripts/ralph/ loop, PRD/progress files, commit-after-pass discipline, and fresh-context operation.
• Ralph GitHub Repository - Source on the concrete snarktank/ralph repository, including the shell loop, packaged skills, plugin metadata, and distribution model.

VoltAgent

• VoltAgent Awesome DESIGN.md - Source on DESIGN.md as an agent-readable design contract and on style-reference catalogs as reusable frontend control surfaces.

Answers

• How To Make Agents Run Longer - Practical checklist for improving long-running agent reliability through harness design, repo legibility, and control loops.