# Praxist Interactive Task Init

Build a Praxist task project through a confirmation-first interactive agent workflow.

- Repository: https://github.com/sapientinc/PRAXIST (5536 stars)
- Category: AI and agents
- License: see repository
- Last updated: 2026-09-23
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add sapientinc/PRAXIST --skill praxist-interactive-task-init -g -a claude-code -y`
Codex: `npx skills add sapientinc/PRAXIST --skill praxist-interactive-task-init -g -a codex -y`
Cursor: `npx skills add sapientinc/PRAXIST --skill praxist-interactive-task-init -g -a cursor -y`
Gemini CLI: `npx skills add sapientinc/PRAXIST --skill praxist-interactive-task-init -g -a gemini-cli -y`

## Description

Build a Praxist task project through a confirmation-first interactive agent workflow. Use when a user wants Praxist task initialization with human confirmation of research goals, constraints, metrics, ranking rules, evaluation protocol, compute budget, baseline handling, or launch readiness; when the user asks for an interactive task init skill; or when the agent should propose a task harness first and ask the user to approve or revise it before writing files.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Praxist Interactive Task Init

Use this skill when task initialization needs explicit user confirmation. It is
a thin interactive layer over `praxist-task-initialization`, not a separate
task format.

This layer inherits the complete current runtime contract from
`praxist-task-initialization`. Keep `agent_runtime:claude_sdk` as the default
unless the user approves another runtime. If the user selects
`agent_runtime:codex_sdk`, apply the SDK/MCP/relay readiness and task-boundary
rules from that skill; do not treat the interactive agent CLI hosting this
conversation as the peer runtime. Its saved ChatGPT authentication may be
approved for native OpenAI, but must remain operator-owned and outside the
generated task. Preserve the tested runtime pins inherited from task
initialization: `claude-agent-sdk==0.2.136`, `openai-codex==0.147.0`, and
`codex-relay==0.5.5`.

Provider-specific context efficiency is runtime-owned. When the user selects
Codex-native mode or OpenRouter, explain that Praxist automatically
coalesces finding-only continuation wakeups without deleting or compressing
canonical evidence. Do not offer task-local cache, memory-store, or
session-batching fields. Direct DeepSeek runs preserve their existing behavior.

Reasoning effort is inherited from the complete task-init contract. Propose
`agent.reasoning_effort: max`; ask for confirmation only when the user raised
reasoning depth, latency, or cost as a constraint, and preserve any explicit
`off`, `low`, `high`, or `max` answer.

## Interaction Principle

Use confirmation first, not input first:

1. Inspect the project and propose a concrete harness decision.
2. Ask the user whether to accept or correct it.
3. Apply accepted decisions to the normal task-initialization workflow.

The rest: https://github.com/sapientinc/PRAXIST/blob/HEAD/skills/praxist-interactive-task-init/SKILL.md