superpipelines
v1.2.1
Published
Multi-agent AI orchestration framework with guaranteed spec compliance, write/review isolation, and full crash recovery
Maintainers
Readme
Superpipelines — Multi-Agent Orchestration Framework
Multi-agent AI pipelines with guaranteed spec compliance, write/review isolation, and full crash recovery. Superpipelines enables complex task decomposition into coordinated subagents with automated verification and state persistence.
Capabilities
Users achieve the following outcomes when utilizing Superpipelines:
- Deconstruction: Tasks are decomposed into a precise specification, implementation plan, and itemized task list before execution.
- Structural Review: Dedicated reviewer agents validate every task against the specification before commitment.
- State Persistence: Pipeline state persists to scope-aware temporary directories, allowing for crash recovery and session resumption.
- Escalation Guards: Hard-coded iteration caps and human gates prevent model rationalization and infinite loops.
Execution Workflow
Superpipelines executes tasks through a structured lifecycle:
Execution Patterns
The framework selects the optimal pattern based on task complexity:
<pattern_matrix> | Pattern | Shape | Use Case | | :--- | :--- | :--- | | 1 — Sequential | A → B → C | Ordered phases with hard data dependencies. | | 2 — Parallel Fan-Out | A → [B, C, D] → Merger | Independent branches that merge upon completion. | | 3 — Iterative Loop | Implement → Test → Fix | Test-driven repair with a hard escalation cap of 3 iterations. | | 4 — Human-Gated | Agent → Gate → Agent | High-stakes stages requiring manual approval. | | 5 — Spec-Driven Dev | Spec → Tasks → 2-Stage Review | Full SDD with worktrees per task. | | 6 — 4D Wrapper | 4D Intake → Pattern | Wraps any pattern with structured deconstruction. | </pattern_matrix>
Installation
Install the Superpipelines plugin via npm or locally:
Published on npm:
superpipelines
Or, clone and build locally:
# Clone the repository
git clone https://github.com/gustavo-meilus/superpipelines-opencode.git
cd superpipelines-opencode
# Build the plugin
npm install
npm run buildThen, add the plugin to your opencode.json:
{
"$schema": "https://opencode.ai/config.json",
"plugin": ["superpipelines"]
}Plugins specified via npm are automatically installed at startup using Bun and cached in ~/.cache/opencode/node_modules/.
You can also place plugin source files directly in:
.opencode/plugins/— Project-level plugins~/.config/opencode/plugins/— Global plugins
Model Configuration
By default, Superpipelines targets standard OpenCode Zen models (opencode/big-pickle). You can override the models used by both the plugin's native agents and any generated pipelines by adding a superpipelines block to your opencode.json:
{
"plugin": ["./superpipelines-opencode"],
"superpipelines": {
"models": {
"default": "openai/gpt-4o",
"architect": "anthropic/claude-3-5-sonnet-latest",
"reviewer": "anthropic/claude-3-5-haiku-latest"
}
}
}Slash Commands
| Command | Function |
| :--- | :--- |
| /superpipelines:new-pipeline | Initiates 4D intake and generates pipeline artifacts. |
| /superpipelines:run-pipeline | Orchestrates an existing pipeline end-to-end. |
| /superpipelines:new-step | Adds a new step to an existing named pipeline. |
| /superpipelines:update-step | Modifies an existing step within a named pipeline. |
| /superpipelines:delete-step | Removes a step from a named pipeline with gap analysis. |
| /superpipelines:audit-pipeline | Audits agents and skills against the v2 compliance matrix. |
Design Principles
- Structural Isolation: Permission boundaries are enforced at the agent definition level. Reviewers cannot rationalize their way into "fixing" code; they can only fail it.
- Scope-Aware State: Pipeline state persists to
<scope-root>/superpipelines/temp/{P}/{runId}/pipeline-state.json. Resumption resets in-progress phases while preserving completed work. - Permission Granularity: Every agent declares a
permissionMode(e.g.,acceptEdits,plan). Bypassing permissions requires explicit, documented justification. - Progressive Disclosure: High-density reference documentation resides in companion
*-references/directories and is loaded on demand to minimize context bloat.
Repository Layout
<file_structure>
superpipelines-opencode/
├── package.json # Plugin NPM package manifest
├── src/ # TypeScript source code for the OpenCode plugin
├── dist/ # Compiled plugin code (run `npm run build`)
├── .opencode/ # Plugin installation guides
├── agents/ # Core agent definitions (Architect, Auditor, Executor, Reviewers)
├── skills/ # Shared skills (State, Paths, Patterns, Worktree Safety)
│ ├── *-references/ # Deep reference libraries (On-demand loading)
├── commands/ # Slash command wrappers
└── settings.json # Global plugin configuration</file_structure>
Related Projects
- superpipelines — The companion CLI service for managing Superpipelines runs, state, and schedules outside the OpenCode plugin context. This plugin (
superpipelines-opencode) implements the OpenCode-side agent orchestration; the sibling project handles standalone execution, scheduling, and external integrations.
Contributing
Contributions are managed via issues and PRs at gustavo-meilus/superpipelines-opencode. Use /superpipelines:audit-pipeline to validate additions against the compliance matrix before submission.
License
MIT — See LICENSE.
