superpipelines
llms.txt4 starsChanged 6 months agoMITView on GitHub
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.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms-full.txtllms.txt
- cutting-a-releaseSkill
- cutting-a-releaseSkill
The file
Files
# 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. ## Key Features - **Spec-Driven Development (SDD)**: Tasks are decomposed into specifications, implementation plans, and itemized task lists. - **Write/Review Isolation**: Structural separation of implementation and verification roles. - **Scope-Aware State**: State persistence to project, local, or user scopes with full recovery. - **Multi-Pipeline Isolation**: Support for multiple named pipelines per workspace. - **Slash Command Integration**: Commands for creating, running, auditing, and mutating pipelines. ## Core Documentation - [README.md](file:///d:/Github/superpipelines/README.md): High-level overview and installation guide. - [CLAUDE.md](file:///d:/Github/superpipelines/CLAUDE.md): Architectural invariants and authoring rules. - [RELEASE-NOTES.md](file:///d:/Github/superpipelines/RELEASE-NOTES.md): Versioned feature history. - [CHANGELOG.md](file:///d:/Github/superpipelines/CHANGELOG.md): Granular record of changes. ## Workflow Skills - [using-superpipelines](file:///d:/Github/superpipelines/skills/using-superpipelines/SKILL.md): Core orchestration and routing protocols. - [creating-a-pipeline](file:///d:/Github/superpipelines/skills/creating-a-pipeline/SKILL.md): End-to-end pipeline scaffolding. - [running-a-pipeline](file:///d:/Github/superpipelines/skills/running-a-pipeline/SKILL.md): Registry-driven execution launcher. - [adding-a-pipeline-step](file:///d:/Github/superpipelines/skills/adding-a-pipeline-step/SKILL.md): Topology mutation (Add). - [updating-a-pipeline-step](file:///d:/Github/superpipelines/skills/updating-a-pipeline-step/SKILL.md): topology mutation (Update). - [deleting-a-pipeline-step](file:///d:/Github/superpipelines/skills/deleting-a-pipeline-step/SKILL.md): Topology mutation (Delete). ## Foundational Skills - [sk-4d-method](file:///d:/Github/superpipelines/skills/sk-4d-method/SKILL.md): Deconstruction intake (Define, Diagnose, Design, Deliver). - [sk-spec-driven-development](file:///d:/Github/superpipelines/skills/sk-spec-driven-development/SKILL.md): Full SDD lifecycle. - [sk-write-review-isolation](file:///d:/Github/superpipelines/skills/sk-write-review-isolation/SKILL.md): Two-stage review protocol. - [sk-pipeline-paths](file:///d:/Github/superpipelines/skills/sk-pipeline-paths/SKILL.md): Scope-aware path resolution. - [sk-pipeline-state](file:///d:/Github/superpipelines/skills/sk-pipeline-state/SKILL.md): Atomic state management. - [sk-worktree-safety](file:///d:/Github/superpipelines/skills/sk-worktree-safety/SKILL.md): Isolated integration verification. ## Engineering Standards - [systematic-debugging](file:///d:/Github/superpipelines/skills/systematic-debugging/SKILL.md): Root cause protocol. - [test-driven-development](file:///d:/Github/superpipelines/skills/test-driven-development/SKILL.md): Red-Green-Refactor cycle. - [verification-before-completion](file:///d:/Github/superpipelines/skills/verification-before-completion/SKILL.md): Evidence-before-claim protocol. - [brainstorming](file:///d:/Github/superpipelines/skills/brainstorming/SKILL.md): Exploratory design workflow.
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
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.

