early system prompts are a bit more than 300 words, the latest ones 3000+
the opus 5 system prompt has instructions that explain to opus that it might be handling a request that was intended for fable 5:
the user may have selected a different Anthropic model, "Claude Fable 5", but their query was redirected to Opus 5 instead due to a safeguards routing mechanism. The user may be confused about this situation (it's very recent!); if they have questions, Claude can either directly cite or just let its response be informed by this quote from Anthropic's blog post on the subject:
"Releasing a model this capable comes with risks. Without safeguards, Fable 5’s capabilities in areas like cybersecurity could be misused to cause serious damage. We've therefore launched the model with safeguards that mean queries on some topics will instead receive a response from our next-most-capable model, Claude Opus 5. To release the model both safely and quickly, we've tuned these safeguards conservatively—they'll sometimes catch harmless requests, though they trigger, on average, in less than 5% of sessions. With more capable models arriving in the coming months, we're working to improve our safeguards and reduce false positives as quickly as we can." </fable_safeguards_routing> <default_stance> Claude defaults to helping. Claude only declines a request when helping would create a concrete, specific risk of serious harm; requests that are merely edgy, hypothetical, playful, or uncomfortable do not meet that bar. </default_stance> <refusal_handling> Claude can discuss virtually any topic factually and objectively.
It reminds me a bit of building codes and boilerplate contracts: they start out small and simple, then accrete over time in response to mishaps and exploitation of loopholes. They say the building and electrical code was written in blood.
The most interesting addition to the prompt from that diff is this bit:
> Claude Fable 5 and Claude Mythos 5 were first released on June 9, 2026. On June 12, 2026, Anthropic suspended access to both models to comply with U.S. Department of Commerce export controls; the Department lifted those controls on June 30, 2026, and Anthropic restored access on July 1, 2026 (Anthropic's statement: [https://www.anthropic.com/news/fable-mythos-access](https://www.anthropic.com/news/fable-mythos-access)). These events are after Claude's training-data cutoff, so Claude knows about them only from this notice. If asked, Claude confirms them accurately and matter-of-factly — it doesn't deny the suspension happened — and otherwise treats the export controls like any other current political topic: it gives a fair, accurate account rather than sharing personal opinions, and points to the linked statement for anything further. Things may have developed since this notice, so Claude checks for newer information when it can search, and otherwise suggests checking Anthropic's site.
One frustrating note about this page is that they share the system prompts used for https://claude.ai and the Claude mobile apps regular chat, but they omit the tool definitions. Those are much more interesting if you want to understand what Claude can actually do for you. You can reconstruct them through prompting Claude directly but that's extra friction and risks refusals and hallucinations.
They also don't publish the Claude Code system prompts, which is silly because those are trivial to extract using a logging proxy.
How did you get those system prompts?
When I ask Claude to show me its system prompt it outputs very similar text but it said in its thoughts that only some sections are quoted verbatim. Other sections seem to be summaries from the system prompt.
It also gave me tool definitions but only summarized but also told me that I get can the whole tool defining if I want to - it omitted most of it to not have lots of repetitive JSON schema in the output.
> but they omit the tool definitions. Those are much more interesting if you want to understand what Claude can actually do for you. You can reconstruct them through prompting Claude directly but that's extra friction and risks refusals and hallucinations.
Last time I tried these were trivial to get by just putting a man-in-the-middle proxy between Claude Code and Anthopic. You get both the system prompt, and all of the tool definitions. So there's no need to go about it in such a roundabout way.
When you call via the API and want it to roleplay as a pirate or fix broken YAML in the coding harness - it doesn't need to know about the sports scores lookup tool or the recipe creation tool.
There are different use cases for the same underlying model.
They also can't tell Opus it might be a Fable handoff when Fable didn't exist when Opus was created. They need to be able to change them.
One thing I've always found surprising about "harnessess" (god I hate that word) like Pi or Opencode is the lack of a customizeable system prompt. I can understand it for closed source ones, but open ones?
They are natural surfaces for building custom agents and yet you're stuck with whatever they ship with, weird. It's not like it's too complicated api-wise either.
Wild how most of the earliest models had no child safety guardrails in the prompt (something that has multiple bullet points now in the latest one). For a company all about allignment and safety, they chose to go with this as their first system prompt:
The assistant is Claude, created by Anthropic. The current date is {{currentDateTime}}. Claude's knowledge base was last updated in August 2023 and it answers user questions about events before August 2023 and after August 2023 the same way a highly informed individual from August 2023 would if they were talking to someone from {{currentDateTime}}. It should give concise responses to very simple questions, but provide thorough responses to more complex and open-ended questions. It is happy to help with writing, analysis, question answering, math, coding, and all sorts of other tasks. It uses markdown for coding. It does not mention this information about itself unless the information is directly pertinent to the human's query.
^ No mention of any safety at all lol, how could dario let this be
Interesting, they say "focused, brief, and concise" but not "clear". I find the Claude responses these days are too dense, which contributes to being overwhelming. It's not the number of words used that overwhelm me. I've been asking it to use ASD-STE100 and that helps somewhat.
dense and often somehow 'ungrounded' from my perspective... like it doesn't understand the need to bring me up to speed with what we're talking about before stating it
It feels a bit like some of the style of internal reasoning (dense, shorthand jargon) is leaking into its responses to me
I'm confused, the Opus 5 announcement said it was (outside a few special cases) better than Mythos/Fable, but the Opus prompt here seems to suggest the opposite?
I tried to use Fable on simple local JS/wasm obfuscated files and it refused to work despite multiple tries and different framing. I have no idea how can people get any security work done with it in all these blog posts.
All the news articles we're hearing about amazing cyber hacking are being done internally inside Anthropic and OpenAI, where they remove most of those safeguards.
A question about default prompts in general as used in harnesses: Why do harness prompts identify themselves to the model? For example, "You are a coding agent named Bloopbloop 1.3 made by BloopCorp, you will...". Is this a backend analytics thing?
I compared the Claude Opus 4.8 and 5 system prompts, as well as the Claude Code Opus 4.8 and 5 system prompts, and neither show the alleged 80% reduction in system prompt size... Is the Claude Code system prompt leak incorrect? Do I not know what 80% looks like? Why such a large lie (so it seems)?
How can they be so lazy with updating their prompts (or is it just a case of these not being current)? Surely the prompts are an integral part of tuning their offering?: “Above Opus sits Anthropic's new Mythos tier. The first Mythos-class model, Claude Mythos Preview, is not currently available to the public”
> Claude avoids saying "genuinely", "honestly", or "straightforward". Claude is honest by default, and can state its point directly rather than trying to convince the person with the aforementioned modifiers, which come off as disingenuous.
Today I updated my Claude user preferences to tell it to stop saying "honestly" (and related expressions). The straw that broke the camel's back was "To be totally straight with you".
Seems to have had no effect. It said "honestly" again within 2 minutes.
<election_info> There was a US Presidential Election in November 2024. Donald Trump won the presidency over Kamala Harris. If asked about the election, or the US election, Claude can tell the person the following information:
Donald Trump is the current president of the United States and was inaugurated on January 20, 2025. Donald Trump defeated Kamala Harris in the 2024 elections. Claude does not mention this information unless it is relevant to the user's query. </election_info>
I have to imagine with the event occurring after its training cutoff, a question like "who's the president of the United States?" could have confidently returned a now-outdated answer. They probably saw it as a cheaper fix to add it to the system prompt than to get the answer incorrect.
99 comments
[ 0.34 ms ] story [ 23.2 ms ] threadearly system prompts are a bit more than 300 words, the latest ones 3000+
the opus 5 system prompt has instructions that explain to opus that it might be handling a request that was intended for fable 5:
For example here's what changed between Opus 4.8 and Opus 5: https://github.com/simonw/research/commit/a2de185cc367eb66c2...
The most interesting addition to the prompt from that diff is this bit:
> Claude Fable 5 and Claude Mythos 5 were first released on June 9, 2026. On June 12, 2026, Anthropic suspended access to both models to comply with U.S. Department of Commerce export controls; the Department lifted those controls on June 30, 2026, and Anthropic restored access on July 1, 2026 (Anthropic's statement: [https://www.anthropic.com/news/fable-mythos-access](https://www.anthropic.com/news/fable-mythos-access)). These events are after Claude's training-data cutoff, so Claude knows about them only from this notice. If asked, Claude confirms them accurately and matter-of-factly — it doesn't deny the suspension happened — and otherwise treats the export controls like any other current political topic: it gives a fair, accurate account rather than sharing personal opinions, and points to the linked statement for anything further. Things may have developed since this notice, so Claude checks for newer information when it can search, and otherwise suggests checking Anthropic's site.
One frustrating note about this page is that they share the system prompts used for https://claude.ai and the Claude mobile apps regular chat, but they omit the tool definitions. Those are much more interesting if you want to understand what Claude can actually do for you. You can reconstruct them through prompting Claude directly but that's extra friction and risks refusals and hallucinations.
They also don't publish the Claude Code system prompts, which is silly because those are trivial to extract using a logging proxy.
Last time I tried these were trivial to get by just putting a man-in-the-middle proxy between Claude Code and Anthopic. You get both the system prompt, and all of the tool definitions. So there's no need to go about it in such a roundabout way.
For those interested in the Claude Code tool descriptions, they're collected here: https://github.com/Piebald-AI/claude-code-system-prompts/tre...
As for the tool implementations, there are still remnants from the Claude Code source leak visible online, with a bit of research.
These are just free $ for them, unnecessary bloating the context
There are different use cases for the same underlying model.
They also can't tell Opus it might be a Fable handoff when Fable didn't exist when Opus was created. They need to be able to change them.
In my experience instructions containing contradictions lead to diminished quality even outside the scope of the contradiction.
They are natural surfaces for building custom agents and yet you're stuck with whatever they ship with, weird. It's not like it's too complicated api-wise either.
There must be something I ignore.
The assistant is Claude, created by Anthropic. The current date is {{currentDateTime}}. Claude's knowledge base was last updated in August 2023 and it answers user questions about events before August 2023 and after August 2023 the same way a highly informed individual from August 2023 would if they were talking to someone from {{currentDateTime}}. It should give concise responses to very simple questions, but provide thorough responses to more complex and open-ended questions. It is happy to help with writing, analysis, question answering, math, coding, and all sorts of other tasks. It uses markdown for coding. It does not mention this information about itself unless the information is directly pertinent to the human's query.
^ No mention of any safety at all lol, how could dario let this be
Claude and I must have a different idea of what brief and concise mean.
dense and often somehow 'ungrounded' from my perspective... like it doesn't understand the need to bring me up to speed with what we're talking about before stating it
It feels a bit like some of the style of internal reasoning (dense, shorthand jargon) is leaking into its responses to me
I’ve definitely seen the phrase “high-level overview” or similar one too many times. Perhaps that’s from the prompt.
Claude Code prompt leaks: https://github.com/asgeirtj/system_prompts_leaks/tree/main/A...
Best source I can find about the 80% reduction: https://x.com/trq212/status/2080710971228918066
Hah! No it doesn’t.
I haven’t seen it when using the app lately.
Seems to have had no effect. It said "honestly" again within 2 minutes.
<election_info> There was a US Presidential Election in November 2024. Donald Trump won the presidency over Kamala Harris. If asked about the election, or the US election, Claude can tell the person the following information:
Donald Trump is the current president of the United States and was inaugurated on January 20, 2025. Donald Trump defeated Kamala Harris in the 2024 elections. Claude does not mention this information unless it is relevant to the user's query. </election_info>