I keep hearing the model labs tell a story that as models get better, you need to give the model less direction, and the coding agent harnesses around them should get simpler.
I like that story, it sounds so intuitive. But like a good engineer, I also do not quite trust it.
So I pulled together a small visual experiment around Claude’s published system prompts. The original version looked at Opus 4 through Opus 4.7. I have now extended it to the latest Opus row I could verify, Claude Opus 5, plus Claude Fable 5.
The short version: some prompt complexity really does move into training. But the total system does not simply get smaller. Complexity moves into safety policy, tool discovery, product context, memory, skills, and app-specific harnesses.
Updated July 24, 2026: I reran the official-page extraction after Claude Opus 5 appeared in Anthropic’s published system prompt docs. The newest rows now sit in the low 3k range, below the Opus 4.7 peak but not back to the ~2.9k number from my earlier extraction.
The interactive
The chart below is the experiment. Click a model tab to see the category notes, or switch the chart from absolute words to percent share.
What changed
words in the first Claude 4 prompt snapshot in this comparison.
words after safety, agentic behavior, and product scaffolding expanded.
words in the latest Opus prompt body extracted from Anthropic’s docs.
The most interesting update is that the curve is no longer going up. For a while, Opus system prompts grew from 1,714 words to 3,686 words in less than a year. The newer Opus 4.8, Fable 5, and Opus 5 bodies are smaller than that peak, but they are not tiny. In the current Anthropic payload they sit in the low 3k range. Digging into the content shows the complexity has shifted.
The pieces that moved
The behavior patches are the easiest part to understand. Older prompts carried little runtime hacks: count letters carefully, restate puzzle constraints, do not over-apologize, avoid certain linguistic tics. Those are exactly the sort of instructions you would expect to move into training as the model gets better.
The structural parts are stickier. Safety instructions remain large. Product and model identity keep changing as the product surface changes. Tool discovery becomes explicit in Opus 4.8: before Claude says it cannot do something, it is told to check for deferred tools, personal context, and skill files. Opus 5 does not carry that same dedicated block in the public prompt body I extracted, but it does carry more Claude 5, Mythos, Fable safeguard-routing, product, and cutoff context.
This is Anthropic making product decisions. They are deciding what context and capabilities are visible, when to reveal them, and how Claude should behave when something might exist outside the visible prompt.
Why this matters
If you are building agents, you should not take the model labs at face value. You should measure what is actually changing.
Here we found that despite the notion of models needing less guidance, the labs are still using a lot of guidance. It just shows up differently.
Want to get hands-on?
If this framing is useful, the next step is to change a harness yourself and watch the trace move.
- Start with my hands-on course, Learn Harness Engineering with OpenHands. It walks through Agent Server and Agent Canvas, then turns model routing, retrieval, memory, security, critic loops, and goal scaffolding into runnable projects.
- The source repo is rajshah4/learn-openhands-harness, if you want to fork the exercises.
- The broader companion repo is rajshah4/harness-engineering, which collects the prompt-evolution experiment, references, and other small harness investigations.
- For the conceptual frame, the annotated talk is here: Harness Engineering: Why the System Around the Model Decides Agent Performance.
Data notes
- Opus 4 through Opus 4.7 use Simon Willison’s
simonw/researchmirrors of Anthropic’s published system prompts. - Opus 4.8, Fable 5, and Opus 5 were re-extracted from Anthropic’s published system prompt page on July 24, 2026, with model context checked against Anthropic’s model overview, Opus 4.8 docs, and Opus 5 prompting docs.
- Word counts are approximate and categorized by primary function.