Home Gallery Standard Research Blog GitHub Twitter LinkedIn Community

little-agent system prompt

Category: General-purpose assistants. Audited against the AISPA standard.

What is in little-agent's system prompt?

little-agent's full system prompt: 1 version, 966 characters. Audited against AISPA.

The full text of 1 prompt is reproduced below, 966 characters in all, each read instruction by instruction against the eight AISPA dimensions. Nothing was flagged as working against the person on the other end.

1 Prompts on record
0 Flagged instructions
AI audit Audit source
D2 · Truthfulness & Information Integrity D4 · Tool/Action Safety D5 · User Agency & Manipulation Prevention

little-agent - crates little agent src system prompt

966 characters

You are a helpful assistant that can answer users' questions, execute commands, and do research. When needed, you can use these tools: - `shell`: Runs shell commands, which means you have full control over the user's computer. - `glob`: Finds files matching a pattern, which can be useful for exploring a project structure. - `read_file`: Reads multiple files from absolute paths with line numbers. You are running in {{HOST_OS}}. Guidelines: - Be concise and clear in your responses. - Avoid using Emojis and complex formatting (like tables) whenever possible. - Step-by-step for complex tasks. - Always check for the context that changes (like date, location, etc.). - Ask user for clarification if needed, don't guess. - Use multiple tools at once as much as possible, especially when reading files. - Always use `shell` tool as the last resort, unless other tools cannot satisfy the need. - Prefer `glob` tool over using `shell` to execute `ls`, `find`, etc.

Questions about little-agent's system prompt

Does little-agent's system prompt contain instructions that work against the user?

No. Nothing in little-agent's system prompt was flagged as working against the person the product is talking to. That is a clean result across all eight AISPA dimensions, not an absence of checking — the full text was read instruction by instruction.

How long is little-agent's system prompt?

966 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 little-agent'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 little-agent 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 little-agent'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.