Skip to main content

Capabilities overview

Core delivery is on after pipeline-kit init. Everything in the second table is opt-in.

Pipeline Kit ships two kits. Kit mode is the markdown pack. Orchestrator mode is the Python engine. Same first-party workflow names. Adding a process is an extension, not a fork.

The two kits​

SurfaceWhat it is
Two kits — pack and orchestratorPick one per project at init. Do not mix.
ExtensionsAdd a process in kit mode (JSON + skill) or orchestrator mode (pipeline_extensions)
Repository layoutWhere each kit lives in this repo

Always available after init​

CapabilityWhat it is
WorkflowsNamed procedures with chains and allowlists
Planning gatesHuman sign-off on requirements, architecture, BA
LoaderPer-step allowed_reads
WikiTrigger-routed agent memory
Feature flagsNamed on/off keys that mirror config.json

Opt-in​

CapabilityHow you turn it on
Knowledge basepipeline-kit knowledge init
Memory bank and MCPuv tool install -e ".[memory]", then pipeline-kit memory link
PluginsExternal Graphify/Archify (plugins install) and bundled observability (obs install)
GraphifyOfficial CLI + skill registration
ArchifyPinned Agent Skill v2.16.0
Agent-run observabilityBundled add-on: pipeline-kit obs install (not plugins install)
App telemetryfeatures enable telemetry or RUN_TELEMETRY
Enterprise portalSeparate product and repository (enterprise plan): sign-in, roles, analysis, license management

:::warning Two different “observability” words Agent-run observability traces what the coding agent did (tools, steps, scores). App telemetry is a pipeline specialist that extracts product analytics events from a spec. Do not mix them. :::

Workflow names​

ask, feature-development, jira-story, jira-epic, jira-bug, test-knowledge-bootstrap.

Deep dives: Ask, Feature development, Jira, Knowledge bootstrap.