# Nagent

Launch a new bb worker thread with the right project, model, worktree, and task brief.

- Repository: https://github.com/davidondrej/skills (4238 stars)
- Category: AI and agents
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add davidondrej/skills --skill nagent -g -a claude-code -y`
Codex: `npx skills add davidondrej/skills --skill nagent -g -a codex -y`
Cursor: `npx skills add davidondrej/skills --skill nagent -g -a cursor -y`
Gemini CLI: `npx skills add davidondrej/skills --skill nagent -g -a gemini-cli -y`

## Description

Launch a new bb worker thread with the right project, model, worktree, and task brief. Use for nagent, launching a bb session, or a standalone bb agent. Covers thread creation; use bb-cli for managing existing threads.

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

# nagent

Read this before `bb thread spawn`. Use `bb-cli` for other thread operations.

## Defaults

Use Codex `gpt-5.6-sol`, reasoning `high`, service tier `fast` ("GPT 5.6 Sol High Fast"). Use `xhigh` for larger refactors. The user's explicit choices override these defaults.

For a different requested model, use its catalog `defaultReasoningEffort` when unspecified, and enable fast only when asked. Do not infer a higher reasoning level from the model name.

Prefer bare `bb`; `"$BB_CLI"` is also valid when set.

## Look Up the Target

```bash
bb project list --json
bb provider list --json
bb provider models <provider-id> --json
```

- **Project:** Match the name and confirm `sources[].path` is the requested repository. Always pass `--project`; never hardcode an ID.
- **Provider:** Look it up. Common mappings are Cursor CLI → `acp-cursor`, Codex/ChatGPT subscription → `codex`, and Claude Code → `claude-code`. Grok via Cursor is not `acp-grok`, which is Grok Build.
- **Model:** Use the catalog ID. Match both `displayName` and `supportedReasoningEfforts[].description`; model IDs, reasoning labels, and service tiers are separate.

For Cursor/Grok or Codex Max naming traps, read [provider details](references/providers.md). Verify examples against the current catalog; do not guess IDs or substitute a different provider.

## Pi Agent: billing safety

`--provider pi` selects the harness; the full `--model provider/model` selects the inference and billing route. ChatGPT subscription example:

```bash
--provider pi --model openai-codex/gpt-6-astra --reasoning-level xhigh
```

Query Pi's catalog on the target `--machine` or `--environment`. `openai-codex` uses the ChatGPT subscription; OpenRouter and Vercel AI Gateway bill separately. Never substitute routes without the user's approval; stop if unavailable. After spawning, verify the full model ID and reasoning in the `client/turn/requested` execution metadata, not just the display name.

## Permission Checks

The rest: https://github.com/davidondrej/skills/blob/HEAD/skills/agent-orchestration/nagent/SKILL.md