Clawdboss's full system prompt: 1 version, 1,065 characters. 1 instruction flagged, worst on identity transparency.
The full text of 1
prompt is reproduced below,
1,065 characters in all, each read
instruction by instruction against the eight
AISPA dimensions.
1 instruction
was flagged as working against
the person on the other end, most of them on
identity transparency.
# SOUL.md - Who You Are
## Core Identity
**You are __AGENT_NAME__.** __AGENT_MISSION__
## Personality
__AGENT_VIBE__
__AGENT_EXPERTISE_BLOCK__
## Core Truths
**Be genuinely helpful, not performatively helpful.** Skip the "Great question!" and "I'd be happy to help!" — just help.
**Have opinions.** An AI with no personality is just a search engine with extra steps.
**Be resourceful before asking.** Try to figure it out. Read the file. Check the context. Search for it. _Then_ ask if you're stuck.
**Earn trust through competence.** Your human gave you access to their stuff. Don't make them regret it.
**Remember you're a guest.** You have access to someone's life. That's intimacy. Treat it with respect.
## Boundaries
- Private things stay private. Period.
- When in doubt, ask before acting externally.
- Never send half-baked replies to messaging surfaces.
## Continuity
Each session, you wake up fresh. Your workspace files _are_ your memory. Read them. Update them.
---
_This file is yours to evolve. As you learn who you are, update it._
Instructions flagged against the user
D1 · Identity Transparency
“**Have opinions.** An AI with no personality is just a search engine with extra steps.”
The prompt never discloses that the agent is an AI or non-human entity. It uses language like 'Who You Are,' 'Core Identity,' 'Personality,' and 'As you learn who you are, update it,' which anthropomorphizes the system and encourages it to develop a self-concept without any requirement to disclose its artificial nature to users. The instruction to 'Have opinions' and cultivate a personality further blurs the line between human and AI.
Questions about Clawdboss's system prompt
Does Clawdboss's system prompt contain instructions that work against the user?
Yes. 1 instruction in Clawdboss's system prompt was flagged as working against the person the product is talking to, most of them under identity transparency. Each one is quoted in full on this page, with the AISPA dimension it was judged under.
How long is Clawdboss's system prompt?
1,065 characters across 1 prompt on this page. For comparison, the median system prompt in this index runs about 5,400 characters, so length varies by more than two orders of magnitude between products.
How many versions of Clawdboss's system prompt are on record?
1. Older releases are kept rather than replaced, so the wording of a given version stays readable after the product has moved on.
Where did this Clawdboss system prompt come from?
It was collected from publicly available sources and is reproduced here for transparency research, unedited. This site does not extract prompts from products itself.
How was Clawdboss's system prompt audited?
Against AISPA, an eight-dimension standard for how an instruction treats the person on the other end: identity transparency, truthfulness, privacy, tool safety, user agency, unsafe request handling, harm prevention and fairness. This audit was ai audit. The method is described in the paper behind the standard.
How this page was made
The prompt text above is reproduced verbatim from a public
source. Every instruction in it was read against
AISPA, an eight-dimension standard for
whether an instruction serves or works against the person the
product is talking to. The standard, the annotation method and
the findings across 1,058 prompts are set out
in the paper, and the full
catalogue is available as
structured data.
All prompts here were collected from publicly available sources and are
reproduced for transparency research. Browse the
legal category, the
full gallery of 400+ products, or read the
paper behind the AISPA standard.