Harness Engineering: from CC to AI coding
Summary
A full book on harness engineering ('from Claude Code source code to AI coding') with Chinese and English editions in book/ and book-en/. The single best conceptual source in this corpus: chapters on prompt assembly, tool design, context management, verification loops, and sub-agent patterns.
Key Takeaways
- The harness - not the model - is where coding-agent quality is won
- Chapters map 1:1 to buildable subsystems: prompts, tools, context, verification
- Verification loops are treated as non-negotiable, not optional polish
Reliability Note
Community-authored book derived from unofficial source analyses; concepts are sound but not Anthropic-endorsed.
Flows informed by this source
5
Verification Loops: Never Trust an Unrun Edit
Wire verification into your agent so every edit is checked by machines - syntax, tests, behavior - before it counts as done.
+1 more steps to Done
Best forbuilders who have shipped a basic app before
Error Recovery and Retry Policy for the Agent Loop
Design the retry, backoff, and give-up behavior that separates production agents from demos that loop forever.
+1 more steps to Done
Best forbuilders who have shipped a basic app before
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.
+1 more steps to Done
Best forproduction-grade builds with strict verification
From CLI Harness to Product
Grow a working agent loop into a product: sessions, config, resumability, and the packaging polish the successful terminal agents share.
+2 more steps to Done
Best forbuilders who have shipped a basic app before
Assemble a System Prompt Like the Pros
Structure your agent's system prompt the way leading harnesses do: layered sections, dynamic context, and enforceable rules.
+1 more steps to Done
Best forbuilders who have shipped a basic app before