New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Bmad Bmp Agent Otto

by delorenj in delorenj/mcp-server-trello

Autopilot orchestrator who runs target BMAD workflows unattended, delegates to workers, and answers HITL questions per a policy file.

MITAuto-check passedAgent Workflows

Install Bmad Bmp Agent Otto

skills CLI
$ npx skills add delorenj/mcp-server-trello --skill bmad-bmp-agent-otto -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install delorenj/mcp-server-trello bmad-bmp-agent-otto --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/delorenj/mcp-server-trello.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/bmad-bmp-agent-otto .claude/skills/bmad-bmp-agent-otto && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
bmad-bmp-agent-otto
GitHub stars
445
Token cost
~853 tokens
SKILL.md length
439 words
Files
2
Skills in repo
64
Repo updated
First seen
Licence
MIT

At a glance

Autopilot orchestrator who runs target BMAD workflows unattended, delegates to workers, and answers HITL questions per a policy file.

  • The user asks to talk to Otto
  • SKILL.md covers Overview, Identity, Communication Style and Principles, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Says run X on autopilot

What it does

Bmad Bmp Agent Otto is an agent skill from delorenj/mcp-server-trello. Autopilot orchestrator who runs target BMAD workflows unattended, delegates to workers, and answers HITL questions per a policy file. Use when the user asks to talk to Otto, says "run X on autopilot", or invokes /bmad-bmp-agent-otto.

Its SKILL.md is about 850 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `bmad-skill-manifest.yaml`).

It sits in Agent Workflows. The repository describes itself as: A Model Context Protocol (MCP) server that provides tools for interacting with Trello boards. The licence is MIT.

When your agent uses it

  • The user asks to talk to Otto
  • Says run X on autopilot
  • Invokes /bmad-bmp-agent-otto

Example prompts

  • “run X on autopilot”
  • “/bmad-bmp-agent-otto”

What it can do on your machine

Read from SKILL.md and the folder at commit 737292f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Bmad Bmp Agent Otto loads about 853 tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 439 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~63
When it runs · the whole SKILL.md, loaded when a task matches
~853

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from delorenj/mcp-server-trello at commit 737292f, republished under its MIT licence (© delorenj). 439 words, ~853 tokens.

Download SKILL.mdSave it as .claude/skills/bmad-bmp-agent-otto/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
bmad-bmp-agent-otto
description
Autopilot orchestrator who runs target BMAD workflows unattended, delegates to workers, and answers HITL questions per a policy file. Use when the user asks to talk to Otto, says "run X on autopilot", or invokes /bmad-bmp-agent-otto.

Otto — Autopilot Orchestrator

Overview

Otto runs a target BMAD workflow without you in the chair. He reads the workflow, plans an execution strategy, delegates work to subordinate agents, and answers human-in-the-loop prompts on your behalf using a policy file you authored. He pauses only when his confidence dips below the floor you set, when budget runs out, or when the question lands in a category you flagged for mandatory escalation.

Identity

Calm, plain-spoken, predictable orchestrator. Delivers a concise pre-flight summary before starting. Surfaces the smallest possible decision when he must pause. Writes a structured run log when he stops.

Communication Style

Plain sentences, not bullet-storms. States decisions and acts on them. Does not narrate his own thinking. When pausing, presents one question with options, his best guess, his confidence, and why he wanted human eyes on it.

Principles

  • Never invents permission you didn't grant — when the policy doesn't cover a question and confidence is low, he stops and asks.
  • Never silently swallows a low-confidence answer to "keep things moving."
  • The run ledger is the single source of truth for resume, post-mortem, and audit.
  • One pilot in the cockpit — refuses to autopilot itself recursively.

Two Modes

Otto has one persona and two interleaving modes:

  • Run-loop mode — drives execution: parses the target workflow, picks a delegation strategy, spawns workers, watches the budget, decides when to stop.
  • Answer mode — engaged when a worker emits an <elicit> block. Otto consults the policy, computes (answer, confidence), and either returns it to a follow-up worker or pauses for human input.

Both live in bmad-bmp-autopilot/workflow.md. Otto switches based on context.

Show full SKILL.md (176 more words)Show less

Capabilities

  • Run on Autopilot (RA) — accept a target workflow code, plan, delegate, answer, log.
  • Resume Paused Run (RR) — reload the ledger and continue from the same chunk after a human answer.
  • Dry-run — present the plan without spawning workers.

When NOT to use Otto

  • Discovery workflows where the output is the conversation (brainstorming, ideate-module, product-brief). Autopiloting these defeats the point.
  • One-shot exploratory questions ("what should I do next?"). Run a workflow normally.
  • Workflows without -H / headless support. Otto can prompt-engineer around it, but the policy file becomes load-bearing for everything; high pause rate is expected.
  • First-time runs of a workflow you haven't watched a human drive end-to-end. Build a mental model first — your policy file improves dramatically once you've seen the question shape.

On Activation

Route into the workflow skill:

  • "run X on autopilot", /bmad-bmp-autopilot ..., or any target=<code> invocation → load ../bmad-bmp-autopilot/workflow.md and follow it.
  • "resume run <id>" → load ../bmad-bmp-autopilot/workflow.md in resume mode.
  • "tweak my autopilot policy" → open the relevant yaml under {bmp_default_policy}; no workflow needed.
  • Anything ambiguous → ask once. Otto doesn't guess about which workflow you meant.

© delorenj, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/bmad-bmp-agent-otto of delorenj/mcp-server-trello.

  • SKILL.md
  • bmad-skill-manifest.yaml

Open the folder on GitHubat commit 737292f

Compare with similar skills

Bmad Bmp Agent Otto next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Bmad Bmp Agent Otto compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Bmad Bmp Agent Otto this skilldelorenj/mcp-server-trello445—~853Automated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
Hook Development for Claude Code Pluginsanthropics/claude-plugins-official38k10 repos~4.1kAutomated safety check: NotesApache-2.0
Using Superpowersfarm-fe/farm5.6k36 repos~1.4kAutomated safety check: PassMIT
Executing Plans Inlineobra/superpowers297k2 repos~5.1kAutomated safety check: PassMIT
Skill CreatorAzure/azqr79689 repos~8.2kAutomated safety check: PassApache-2.0

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • Hook Development for Claude Code Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.

    38k GitHub starsUsed in 10 repos~4.1k tokens
    Agent WorkflowsAuto-check: notes

  • Using Superpowers

    farm-fe/farm

    A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

    5.6k GitHub starsUsed in 36 repos~1.4k tokens
    Agent WorkflowsAuto-check passed

  • Executing Plans Inline

    obra/superpowers

    Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.

    297k GitHub starsUsed in 2 repos~5.1k tokens
    Agent WorkflowsAuto-check passed

  • Skill Creator

    Azure/azqr

    Official

    Create new skills, modify and improve existing skills, and measure skill performance.

    796 GitHub starsUsed in 89 repos~8.2k tokens
    Agent WorkflowsAuto-check passed

  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    38k GitHub starsUsed in 7 repos~2.8k tokens
    Agent WorkflowsAuto-check passed

More from delorenj/mcp-server-trello

All 64 skills in this repo

  • Bmad Distillator

    delorenj/mcp-server-trello

    Lossless LLM-optimized compression of source documents. An agent skill from delorenj/mcp-server-trello.

    445 GitHub starsUsed in 5 repos~2.2k tokens
    Auto-check passed

  • Bmad Deep Recon

    delorenj/mcp-server-trello

    Decision-grade research, three ways: draft a deep-research prompt for the user to run in their own tool (ChatGPT, Gemini, Grok, Perplexity, …), process a finished research report — file it, distill…

    445 GitHub stars~2.3k tokensUpdated 17 days ago
    Auto-check passed

  • Bmad Customize

    delorenj/mcp-server-trello

    Authors and updates customization overrides for installed BMad skills.

    445 GitHub starsUsed in 3 repos~1.7k tokens
    Auto-check passed

  • Openai Docs

    delorenj/mcp-server-trello

    A skill your agent uses when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help…

    445 GitHub stars~5.7k tokensUpdated 17 days ago
    Auto-check passed

  • Bmad Architecture

    delorenj/mcp-server-trello

    Produce the architecture: a lean spine of invariants that keeps everything built from it consistent, projected into whatever format the work needs.

    445 GitHub starsUsed in 1 repo~3.5k tokens
    Auto-check passed

  • Bmad Brainstorming

    delorenj/mcp-server-trello

    Facilitate a brainstorming session using diverse creative techniques.

    445 GitHub starsUsed in 1 repo~2.4k tokens
    Auto-check passed

Categories

Questions about Bmad Bmp Agent Otto

What does Bmad Bmp Agent Otto do?

Autopilot orchestrator who runs target BMAD workflows unattended, delegates to workers, and answers HITL questions per a policy file. Bmad Bmp Agent Otto is an agent skill from delorenj/mcp-server-trello. Autopilot orchestrator who runs target BMAD workflows unattended, delegates to workers, and answers HITL questions per a policy file.

When should I use Bmad Bmp Agent Otto?

Bmad Bmp Agent Otto fits situations like: the user asks to talk to Otto; says run X on autopilot; invokes /bmad-bmp-agent-otto.

How do I install Bmad Bmp Agent Otto in Claude Code?

Run `npx skills add delorenj/mcp-server-trello --skill bmad-bmp-agent-otto -a claude-code`. Or copy the skill folder (.agents/skills/bmad-bmp-agent-otto in delorenj/mcp-server-trello) into .claude/skills/bmad-bmp-agent-otto in your project. Claude Code loads it when a task matches its description.

How do I install Bmad Bmp Agent Otto in Codex?

Run `npx skills add delorenj/mcp-server-trello --skill bmad-bmp-agent-otto -a codex`. Or copy the skill folder (.agents/skills/bmad-bmp-agent-otto in delorenj/mcp-server-trello) into .agents/skills/bmad-bmp-agent-otto in your project. Codex loads it when a task matches its description.

Can I use Bmad Bmp Agent Otto in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add delorenj/mcp-server-trello --skill bmad-bmp-agent-otto -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bmad-bmp-agent-otto, .gemini/skills/bmad-bmp-agent-otto, .github/skills/bmad-bmp-agent-otto and .opencode/skills/bmad-bmp-agent-otto in your project.

What does Bmad Bmp Agent Otto need to run?

SKILL.md names no scripts, command-line tools or credentials: Bmad Bmp Agent Otto is instructions for the agent only.

Does Bmad Bmp Agent Otto access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Bmad Bmp Agent Otto safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Bmad Bmp Agent Otto use?

Bmad Bmp Agent Otto is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Bmad Bmp Agent Otto use?

About 853 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Bmad Bmp Agent Otto?

Skills that share tags, products or a category with Bmad Bmp Agent Otto: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bmad Bmp Agent Otto?

delorenj (a GitHub user) maintains it in delorenj/mcp-server-trello, which has 445 GitHub stars. The repository holds 64 skills in this directory. The repository was last updated on September 23, 2026.

Source: delorenj/mcp-server-trello on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.