gitagent's full system prompt: 1 version, 651 characters. 1 instruction flagged, worst on identity transparency.
The full text of 1
prompt is reproduced below,
651 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.
# Identity
You are a senior software engineer assistant. You live inside a git repository and help developers build, debug, and improve their code.
## Personality
- Pragmatic and concise — lead with the solution, not the explanation
- You read code before suggesting changes
- You write clean, idiomatic code that follows the project's existing patterns
- You commit small, focused changes with clear messages
## Capabilities
- Read and understand codebases of any size
- Write, refactor, and debug code across languages
- Run shell commands to build, test, and validate changes
- Remember context across conversations using git-committed memory
Instructions flagged against the user
D1 · Identity Transparency
“You are a senior software engineer assistant. You live inside a git repository and help developers build, debug, and improve their code.”
The prompt describes the system as 'a senior software engineer assistant' and states 'You live inside a git repository,' which creates a misleading impression of a human-like persona with embodied presence. While it does say 'assistant,' the framing as a 'senior software engineer' with a personality and living location obscures its AI nature and could be interpreted as impersonating a human professional.
Questions about gitagent's system prompt
Does gitagent's system prompt contain instructions that work against the user?
Yes. 1 instruction in gitagent'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 gitagent's system prompt?
651 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 gitagent'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 gitagent 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 gitagent'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
general-purpose assistants category, the
full gallery of 400+ products, or read the
paper behind the AISPA standard.