agentleFS
Sign inStart free
lohi-ailohi-ai/babysit/llms.txt

babysit

llms.txt0 starsChanged 7 days agoMITView on GitHub

Give Autopilot a task. Preview the interface, then let it write, review, test and fix the code. 2build provides open-source skills and a companion CLI for Claude Code, Codex, Antigravity, OMP, Grok and any coding agent that supports Claude Code skills. Only Team needs Orca.

The file

Create a free account to mount
Files
llms.txt
# 2build

> Give Autopilot a task. Preview the interface, then let it write, review, test and fix the code. 2build provides open-source skills and a companion CLI for Claude Code, Codex, Antigravity, OMP, Grok and any coding agent that supports Claude Code skills. Only Team needs Orca.

## Start here

- [README and installation prompt](https://raw.githubusercontent.com/2found/2build/main/README.md): Value, one copyable install prompt, prerequisites and first-ticket handoff.
- [Installation contract](https://raw.githubusercontent.com/2found/2build/main/docs/install.md): Detect the current harness, install CLI plus skills, verify both layers and troubleshoot missing prerequisites.
- [Skill index](https://raw.githubusercontent.com/2found/2build/main/docs/skills.md): Choose a workflow or a directly invocable skill by task.

## Execute and verify

- [Autopilot](https://raw.githubusercontent.com/2found/2build/main/.claude/skills/autopilot/SKILL.md): One ticket on the current checkout; init, plan review, goal handoff and a verified change left uncommitted.
- [Skill preamble](https://raw.githubusercontent.com/2found/2build/main/.claude/skills/references/preamble.md): Harness-specific invocation, bootstrap, telemetry and escalation contract. Resolve sibling references relative to the installed skill directory.
- [Companion CLI](https://raw.githubusercontent.com/2found/2build/main/docs/companion-cli.md): CLI commands, durable snapshots and recovery helpers. Skill invocations are agent chat instructions, not CLI subcommands.
- [Project starters](https://raw.githubusercontent.com/2found/2build/main/docs/starters.md): Generate a verified project with `bbs bootstrap`; inspect committed starter provenance and applicable updates with `bbs starter check`.
- [Team](https://raw.githubusercontent.com/2found/2build/main/docs/team.md): An autonomous product team on Orca — you approve the design, then review the handover and give the release go.
- [Operations](https://raw.githubusercontent.com/2found/2build/main/docs/operations.md): Configuration, progress, evidence, telemetry and health checks.

## Optional

- [Vietnamese README](https://raw.githubusercontent.com/2found/2build/main/README.vi.md): Localized installation prompt and first-run guide.
- [Chinese README](https://raw.githubusercontent.com/2found/2build/main/README.zh.md): Localized installation prompt and first-run guide.
- [Japanese README](https://raw.githubusercontent.com/2found/2build/main/README.ja.md): Localized installation prompt and first-run guide.
- [Korean README](https://raw.githubusercontent.com/2found/2build/main/README.ko.md): Localized installation prompt and first-run guide.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free