Tier 1 · Claude Code internals Claude Code internals · fetched 2026-07-02

claude-code-evolution

Tracks how Claude Code changed version over version and ports the strongest architecture, prompt-engineering, and skill-system ideas into the OpenClaw platform (analysis scale: 1,903 files, ~512k lines). The best single source for 'what the leading harness added over time' insights.

View source on GitHub

Key takeaways

01
Version-over-version deltas reveal which harness features earned their keep
02
Prompt and skill-system changes are catalogued alongside code changes
03
Demonstrates migrating harness patterns to another platform

Flows built on this research

Harness Engineering

Version Your Harness and Track Behavior

Treat prompts, tools, and loop logic as versioned, changelogged artifacts - so behavior changes are decisions, not surprises.

4 steps · 45-75 minutes

Harness Engineering

Cost Control: Model Routing and Effort Tiers

Route work to the cheapest model that can do it and match reasoning effort to task difficulty - with quality guardrails.

4 steps · 90-120 minutes

From the archive

Verbatim excerpts mined from our local archive of this repository — the prompts, schemas, and patterns worth stealing.

Prompt

The /remember skill: memory triage with a destination table

Review the user's memory landscape and produce a clear report of proposed changes, grouped by action type. Do NOT apply changes - present proposals for user approval.

Classify each auto-memory entry:
| CLAUDE.md | Project conventions all contributors should follow | "use bun not npm", "API routes use kebab-case" |
| CLAUDE.local.md | Personal instructions not applicable to others | "I prefer concise responses", "don't auto-commit" |
| Team memory | Org-wide knowledge across repositories | "deploy PRs go through #deploy-queue" |
| Stay in auto-memory | Working notes, temporary context | Session-specific observations |

When unsure, ask rather than guess.

A reconstruction of Claude Code's memory-review flow: memories get promoted up a visibility ladder (auto -> personal -> project -> team), never silently.

skills/claude-code-remember/SKILL.md

Agent pattern

The /simplify skill: three parallel review lenses

Launch all three agents concurrently. Pass each agent the full diff.

Agent 1: Code Reuse Review - search for existing utilities that could replace newly written code; flag any new function that duplicates existing functionality.

Agent 2: Code Quality Review - redundant state, parameter sprawl, copy-paste with slight variation, leaky abstractions, stringly-typed code, unnecessary comments explaining WHAT the code does.

Agent 3 (efficiency) reviews the same diff for performance issues.

Code review decomposed by failure mode rather than by file: each parallel reviewer hunts one specific class of problem across the whole diff.

skills/claude-code-simplify/SKILL.md