Back to Vault
Claude Code Internals
Tier 1

claude-code-evolution

View on GitHub Fetched 2026-07-02 2 related flows

Summary

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.

Key Takeaways

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

Reliability Note

Independent reverse-engineering effort - unofficial, verify against official Anthropic docs and behavior. Original text in Chinese.

Flows informed by this source

2
Flows category icon
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.

01Extract behavior into versioned artifacts
02Start the behavior changelog
03Build the smoke eval and behavioral diffing

+1 more steps to Done

Best foryour first pass at this - no prior setup assumed

4 steps45-75 minutesBeginner
Flows category icon
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.

01Profile spend by call class
02Build the routing table and wire it
03Add escalation on failure

+1 more steps to Done

Best forproduction-grade builds with strict verification

4 steps90-120 minutesAdvanced

Made with Emergent