b00t-ooda

Run an autonomous OODA (Observe-Orient-Decide-Act) loop via ralph to execute task queues with a chosen AI executor.

IndexedMIT★ 15

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/elasticdotventures-b00t-ooda

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Run an autonomous OODA (Observe-Orient-Decide-Act) loop via ralph to execute task queues with a chosen AI executor. Use when asked to run autonomously, start an agent loop, execute pending tasks without supervision, or run OODA cycles. Activates on "run ooda", "autonomous loop", "start ralph", "execute tasks with pi/opencode/claude".

Use cases: productivity, agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/b00t-ooda

What's inside

Skill name: b00t-ooda
Description: Run an autonomous OODA (Observe-Orient-Decide-Act) loop via ralph to execute task queues with a chosen AI executor. Use when asked to run autonomously, start an agent loop, execute pending tasks without supervision, or run OODA cycles. Activates on "run ooda", "autonomous loop", "start ralph", "execute tasks with pi/opencode/claude".
License: MIT
Instructions: 28 lines in SKILL.md · view on GitHub

Files (1)

SKILL.md

SKILL.md (first lines)

Launch a ralph OODA loop to execute tasks autonomously:

```bash
b00t ooda run                           # claude executor, 5 iterations
b00t ooda run --agent=pi --max-iter=10  # local ch0nky via pi-coding-agent
b00t ooda run --agent=opencode          # opencode executor
b00t ooda run --task=42                 # target specific task ID
b00t ooda run --dry-run                 # preview command without executing
b00t ooda status                        # task queue summary
b00t ooda phase                         # current OodaPhase from last run
```

Executor tiers:
- `claude` — frontier (claude-sonnet); best reasoning, highest cost
- `opencode` — ch0nky (qwen36-local when inference running); code-focused
- `pi` — ch0nky (llama-cpp); local, non-interactive, fastest for simple tasks
- `amp` — Amplitude agent; parallel tool use
- `codex` — OpenAI Codex; sandboxed execution

OODA task dispatch (title prefix → recipe):
- `review-soul: <T>` → `just review-soul topic=<T>`
- `research-soul: <T>` → `just research-soul topic=<T>`
- user story text → standard story implementation cycle

The loop terminates when the executor emits `<promise>COMPLETE</promise>`
or all pending tasks are done.

From elasticdotventures/_b00t_, MIT.

Signals

Stars: 15
Forks: 0
Open issues: 65
Last commit (this folder): Jun 19, 2026 (4 months ago)
Last release: Aug 17, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/elasticdotventures/_b00t_
Website: b00t.promptexecution.com
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from elasticdotventures

Cite this page

b00t-ooda skill. Agent Mart. https://agentmart.dev/skills/elasticdotventures-b00t-ooda (last updated 2026-10-24)