Agent skill

Agent Pipeline

by autopus-ai in autopus-ai/autopus-adk

Multi-agent pipeline orchestration skill. An agent skill from autopus-ai/autopus-adk.

MITAuto-check passedAgent Workflows

Install Agent Pipeline

skills CLI
$ npx skills add autopus-ai/autopus-adk --skill agent-pipeline -a claude-code

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

GitHub CLI
$ gh skill install autopus-ai/autopus-adk agent-pipeline --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/autopus-ai/autopus-adk.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.omp/skills/agent-pipeline .claude/skills/agent-pipeline && 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
agent-pipeline
GitHub stars
110
Token cost
~1.8k tokens
SKILL.md length
937 words
Files
9 (incl. references)
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

Multi-agent pipeline orchestration skill. An agent skill from autopus-ai/autopus-adk.

  • Tasks that involve Data pipelines and ETL
  • SKILL.md covers Execution Decision, Execution Owner, Native Dispatch and Context and Models, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Multi-agent orchestration

What it does

Agent Pipeline is an agent skill from autopus-ai/autopus-adk. Multi-agent pipeline orchestration skill

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including reference files (for example `references/completion.md`, `references/coordination.md` and `references/delegation.md`). Compatibility notes: omp

It sits in Agent Workflows, covering Data pipelines and ETL and Multi-agent orchestration. The repository describes itself as: Autopus-ADK is of the agents, by the agents. for the agents. Multi-model orchestration (consensus/pipeline/debate/fastest). Architecture-as-Code, Lore decision tracking… The licence is MIT.

When your agent uses it

  • Tasks that involve Data pipelines and ETL
  • Tasks that involve Multi-agent orchestration

Example prompts

  • “/agent-pipeline”

Requirements

  • Compatibility (from SKILL.md): omp

What it can do on your machine

Read from SKILL.md and the folder at commit a930e5f. 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.

  • Compatibility

    omp

    From compatibility in the SKILL.md frontmatter.

Context cost

Agent Pipeline loads about 1.8k tokens when it runs, and up to ~16k if it reads all its reference files. Until then it costs about 14 tokens; SKILL.md has 937 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~14
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~16k

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 autopus-ai/autopus-adk at commit a930e5f, republished under its MIT licence (© autopus-ai). 937 words, ~1,762 tokens.

Download SKILL.mdSave it as .claude/skills/agent-pipeline/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
agent-pipeline
description
Multi-agent pipeline orchestration skill
compatibility
omp

OMP Native Agent Pipeline

Use for /auto go SPEC-ID [--execution-owner omp|orca]. This entrypoint selects work and context; open only the reference needed for the current step.

NeedOpen
Phase entry, work, and exit conditionsreferences/phases.md
Worker ownership and context isolationreferences/delegation.md
Change classification and gate evidencereferences/gates.md
Tests, smoke checks, and UX verificationreferences/verification.md
Review authority and terminationreferences/review.md
Completion and sync readinessreferences/completion.md
Configured quality and permissionsreferences/quality-modes.md

Execution Decision

Work in the current session by default. Dispatch only genuinely independent slices, a necessary specialist review, or work that needs isolated context. File count and line count do not justify delegation. Keep dependent or same-file work sequential; one migration-numbering lane has one writer.

A verified low-risk compact change contract omits separate planning and test scaffold dispatch: implementation still starts with the relevant failing test, then validation and review run. Missing, ambiguous, or escalated authorization keeps the full route. Report the actual route_phase_set from auto pipeline run, not an imagined phase checklist. Explicit --solo, --team, and --multi requests must retain their requested semantics.

Execution Owner

Choose exactly one DAG owner before any dispatch: --execution-owner omp|orca. Omission selects omp. Reject duplicate, aliased, or conflicting owner flags; never retry a failed explicitly selected owner as another owner.

  • Owner omp: this session owns progress through native task, hub, and todo. --solo keeps work in this session; --team requests a native batch with explicit responsibilities. The two flags conflict.
  • Owner orca: only an explicit --execution-owner orca selects it. First run and read orca skills get orchestration --full; the Orca Run owns the DAG. Do not create a competing OMP task or progress DAG. --team and --solo conflict with this owner.
  • --multi requests risk-tiered provider-diverse evidence, not a second DAG.

auto pipeline run SPEC-ID --platform omp --execution-owner orca performs the integrity check and records pipeline_execution_owner_receipt.v1 before any worker session. The body-free .autopus/pipeline-state/<SPEC-ID>.execution-owner.json records owner, source, identity, and verification status.

Native Dispatch

Before dispatch, inspect the tools actually exposed by this runtime. Use their current schemas rather than copying static payloads. If the selected topology requires an unavailable tool, report that blocker; never simulate dispatch.

OMP registers five agents: scout, reviewer, security-reviewer, task, and sonic. There is no Autopus-specific agent to select, so pick by what the work needs:

  • task runs planning, implementation, debugging, test authoring, and UX work. It is the default for every writing slice; omitting the agent selects it.
  • scout is read-only exploration only. Never give it work that writes.
  • reviewer and security-reviewer keep their built-in review boundaries; use them for review and security findings, not for implementation.
  • sonic is only for an explicit mechanical request. Never route reasoning, planning, validation, or review to it.

The role a worker plays belongs in its assignment text, not in an agent name. State the responsibility, scope, and exit condition in the task itself.

Batch independent owned slices together. Native OMP owns isolated worktree creation, integration, and cleanup. Request isolation only if the current task schema exposes it; do not manually merge or remove its worktrees.

Each worker receives scope, forbidden paths, acceptance criteria, and only its needed context. Request the five-field result contract: owned_paths, changed_files, verification, blockers, next_required_step. Use native schema validation where supported; worker assertions are not execution proof. Record actual dispatch count and the native agents used. Follow up with the same revivable worker through hub; an isolated worker whose workspace has been released needs a new assignment. Only the parent owns todo.

A worker that stops at its turn limit returns a partial result; the turn-budget rule every assignment carries (references/delegation.md, Worker hygiene) keeps that rare. Never treat a partial result as a completed phase or feed it to the next phase. Follow up once with a narrowed instruction (finish and write the artifact, minimal further exploration), through hub or as a new assignment as above; if that run is partial again, stop and hand the phase to the user with what was produced.

Show full SKILL.md (285 more words)Show less

Context and Models

Keep required core/SPEC bodies complete and hash-verified. Ordinary auto workflow context includes optional architecture only when explicitly selected. The managed OMP evidence path independently rebuilds its canonical full context: do not substitute a smaller CLI manifest, alter its signed protocol, or promote an unmeasured compaction result.

Give workers task deltas and retrievable references instead of replaying raw provider/tool output. Validate paths and hashes; reject missing required context, traversal, symlinks, stale or wrong-SPEC input before dispatch. Use native context management rather than layering an extra summarization loop.

Inherit the current OMP session model and thinking configuration unless an explicit validated role-model profile has written task.agentModelOverrides for the native agent being dispatched. That configuration is the only model authority: never pass a guessed model ID, and never pick a cheaper agent to fit a larger task.

Gates and Completion

Use auto spec gates for applicability and exact-input evidence reuse. Security, validation, data-loss, and deterministic-oracle gates remain active; UI changes retain accessibility and UX verification. Annotation is opt-in via --annotation or a direct request, not an automatic extra worker phase. Honor explicit project/route numerical gates; do not invent universal floors.

Integrate changes before the merged verification run. Keep a verdict and real evidence per acceptance criterion. Failed tests or security findings cannot be overruled by provider consensus. Re-review only changed/open findings; unchanged input is not a reason to repeat discovery. Respect the existing retry limits.

Finish only after the changed path has run, required acceptance is satisfied, and blocking findings are closed. Use references/completion.md for the sync receipt. Status combines project/SPEC state with the selected owner's native job state; external commands must not inspect user-owned OMP session roots or claim they replace native hub observations.

© autopus-ai, 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 8 other files (references) in .omp/skills/agent-pipeline of autopus-ai/autopus-adk.

  • SKILL.md
  • references/completion.md
  • references/coordination.md
  • references/delegation.md
  • references/gates.md
  • references/phases.md
  • references/quality-modes.md
  • references/review.md
  • references/verification.md

Open the folder on GitHubat commit a930e5f

Compare with similar skills

Agent Pipeline 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.

Agent Pipeline compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Pipeline this skillautopus-ai/autopus-adk110—~1.8kAutomated safety check: PassMIT
Agent Orchestration SkillOpenLoaf/OpenLoaf108—~1.9kAutomated safety check: PassAGPL-3.0
Agent Orchestration SkillOpenLoaf/OpenLoaf108—~919Automated safety check: PassAGPL-3.0
Configuring Dbt MCP ServerKilo-Org/kilo-marketplace190—~2.5kAutomated safety check: NotesApache-2.0
Qwen Delegationathola/claude-night-market341—~1.1kAutomated safety check: PassMIT
Orca CLIstablyai/orca89k2 repos~593Automated safety check: PassMIT

Similar skills

  • Agent Orchestration Skill

    OpenLoaf/OpenLoaf

    Triggers when the master Agent faces a multi-step complex task and is deciding whether / how to outsource sub-tasks to built-in subagents (browser / doc-editor / data-analyst / extractor /…

    108 GitHub stars~1.9k tokensUpdated 4 mo ago
    Agent WorkflowsAuto-check passed
  • Agent Orchestration Skill

    OpenLoaf/OpenLoaf

    当主 Agent 面临多步骤复杂任务并正在判断要不要 / 怎样把子任务外包给内置子代理(browser / doc-editor / data-analyst / extractor / canvas-designer / coder 等)时触发。不用于:单步问答 / 读取 / 简单副作用(主 Agent 直接做)、已经明确要用 Agent 且知道 subagenttype 的场景。

    108 GitHub stars~919 tokensUpdated 4 mo ago
    Agent WorkflowsAuto-check passed
  • Configuring Dbt MCP Server

    Kilo-Org/kilo-marketplace

    Generates MCP server configuration JSON, resolves authentication setup, and validates server connectivity for dbt.

    190 GitHub stars~2.5k tokensUpdated 12 days ago
    Data & AnalyticsAuto-check: notes
  • Qwen Delegation

    athola/claude-night-market

    Delegates tasks to Qwen CLI via delegation-core for Alibaba's models.

    341 GitHub stars~1.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Orca CLI

    stablyai/orca

    Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser…

    89k GitHub starsUsed in 2 repos~593 tokens
    Agent WorkflowsAuto-check passed
  • Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.

    20k GitHub starsUsed in 1 repo~756 tokens
    Agent WorkflowsAuto-check passed

More from autopus-ai/autopus-adk

All 11 skills in this repo
  • Auto Idea

    autopus-ai/autopus-adk

    아이디어 브레인스토밍 — 멀티 프로바이더 토론과 ICE 평가로 아이디어를 정리합니다. An agent skill from autopus-ai/autopus-adk.

    110 GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Auto QA

    autopus-ai/autopus-adk

    QAMESH project QA mesh — plan, run, report, and publish deterministic QA evidence

    110 GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Auto Setup

    autopus-ai/autopus-adk

    프로젝트 컨텍스트 생성 — 코드베이스를 분석하고 ARCHITECTURE.md 및 .autopus/project 문서를 생성합니다

    110 GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Auto Sync

    autopus-ai/autopus-adk

    문서 동기화 — 구현 이후 SPEC, CHANGELOG, 문서를 반영합니다. An agent skill from autopus-ai/autopus-adk.

    110 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Ax Annotation

    autopus-ai/autopus-adk

    @AX code annotation workflow skill for agent-driven tag application

    110 GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Browser Automation

    autopus-ai/autopus-adk

    터미널 환경 자동 감지 브라우저 자동화 스킬 — AI 에이전트가 직접 웹 페이지를 조작하고 검증. An agent skill from autopus-ai/autopus-adk.

    110 GitHub stars~2.1k tokensUpdated today
    Auto-check passed

Questions about Agent Pipeline

What does Agent Pipeline do?

Multi-agent pipeline orchestration skill. An agent skill from autopus-ai/autopus-adk. Agent Pipeline is an agent skill from autopus-ai/autopus-adk.

When should I use Agent Pipeline?

Agent Pipeline fits situations like: tasks that involve Data pipelines and ETL; tasks that involve Multi-agent orchestration.

How do I install Agent Pipeline in Claude Code?

Run `npx skills add autopus-ai/autopus-adk --skill agent-pipeline -a claude-code`. Or copy the skill folder (.omp/skills/agent-pipeline in autopus-ai/autopus-adk) into .claude/skills/agent-pipeline in your project. Claude Code loads it when a task matches its description.

How do I install Agent Pipeline in Codex?

Run `npx skills add autopus-ai/autopus-adk --skill agent-pipeline -a codex`. Or copy the skill folder (.omp/skills/agent-pipeline in autopus-ai/autopus-adk) into .agents/skills/agent-pipeline in your project. Codex loads it when a task matches its description.

Can I use Agent Pipeline 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 autopus-ai/autopus-adk --skill agent-pipeline -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-pipeline, .gemini/skills/agent-pipeline, .github/skills/agent-pipeline and .opencode/skills/agent-pipeline in your project.

What does Agent Pipeline need to run?

SKILL.md names no scripts, command-line tools or credentials: Agent Pipeline is instructions for the agent only. Compatibility (from SKILL.md): omp.

Does Agent Pipeline 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 Agent Pipeline 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 Agent Pipeline use?

Agent Pipeline 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 Agent Pipeline use?

About 1.8k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 14k tokens, read only when the agent opens those files.

What are the alternatives to Agent Pipeline?

Skills that share tags, products or a category with Agent Pipeline: Agent Orchestration Skill (OpenLoaf/OpenLoaf, 108 stars), Agent Orchestration Skill (OpenLoaf/OpenLoaf, 108 stars), Configuring Dbt MCP Server (Kilo-Org/kilo-marketplace, 190 stars) and Qwen Delegation (athola/claude-night-market, 341 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Pipeline?

autopus-ai (a GitHub organization) maintains it in autopus-ai/autopus-adk, which has 110 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 10, 2026.

Source: autopus-ai/autopus-adk on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.