interactive

An interactive agent class for mini-swe-agent, a tool that helps coding agents work through tasks from the command line.

In plain words
What is it for?
Use it as the interactive agent behind the mini command-line tool.
Why use it?
The provided information only identifies the class and its role; it does not describe its specific behavior in detail.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/swe-agent/mini-swe-agent/interactive
Clone the repo
git clone --depth 1 https://github.com/SWE-agent/mini-swe-agent
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 150 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00150
Opus 5 $0.00000 $0.00075
Sonnet 5 $0.00000 $0.00030
Haiku 4.5 $0.00000 $0.00015

Measured yesterday against content hash 6dd8db73ddde, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

interactive scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

docs/reference/agents/interactive.md · 20 lines

What it actually says

Interactive

!!! note "InteractiveAgent class"

- [Read on GitHub](https://github.com/swe-agent/mini-swe-agent/blob/main/src/minisweagent/agents/interactive.py)

??? note "Full source code"

    ```python
    --8<-- "src/minisweagent/agents/interactive.py"
    ```

!!! tip "See also"

* This agent subclass builds on top of the [default agent](default.md), make sure to read that first.
* This class powers the `mini` command line tool, see [usage](../../usage/mini.md) for more details.

::: minisweagent.agents.interactive

{% include-markdown "../../_footer.md" %}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 20 lines · 0 tokens per session scan A 6dd8db73ddde

Subscribe to this mod's changes

interactive is an agent published in the GitHub repository SWE-agent/mini-swe-agent (6,860 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 150 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.