Skip to content

Runtimes & Skills

SDTK does not run models itself. It targets execution runtimes — today Claude Code and Codex — and drives them through skills: markdown-defined workflows the runtime loads and executes. The runtimes execute; SDTK governs.

The division of labor

LayerOwnsExamples
Runtime (Claude Code / Codex)Model access, tool execution, session UXRunning /orchestrator, editing files, executing shell commands
Skills (installed by SDTK)Role behavior, phase workflow, output contracts/pm, /ba, /arch, /dev, /qa, /orchestrator, design & ops journeys
SDTK CLIsScaffolding, state, validation, ledgers, viewerssdtk-spec generate, sdtk-wiki atlas open, sdtk-agent run continue

Which kits install skills

Only the four phase toolkits are runtime-aware:

ToolkitInstalls skills?Notes
sdtk-specOrchestrator + role skills (/pm, /ba, /arch, /dev, /qa) + sub-skills
sdtk-opsOps journey skills (ops-discover, ops-planops-verify)
sdtk-codeGoverned coding flow support
sdtk-designDesign journey skills (brief, prototype, review, handoff)
sdtk-wikiCLI-driven; plain init only
sdtk-agentCLI-driven; plain init only — there is deliberately no /agent slash command

sdtk init --runtime <claude|codex> handles all six in the right order — see Installation.

Skill scopes

Skills can live at project scope (inside the repo, versionable, per-project) or user scope (shared across all projects on the machine):

RuntimeDefaultProject scopeUser scope
Claude Codeproject.claude/skills/~/.claude/skills/ (via --global)
CodexuserCODEX_HOME=<project>/.codex launch contract$CODEX_HOME/skills/ (default ~/.codex/skills/)

Project scope keeps skill versions pinned to the repo (good for teams); user scope installs once for every project (good for solo work). The Codex project-scope contract is explained in Codex integration.

How a session flows

  1. You open your runtime in an initialized project.
  2. Session-start guidance (CLAUDE.md / AGENTS.md, written by init) points the model at SDTK's routing rules.
  3. Unprefixed requests go to Orchestrator Intake, which classifies the intent and picks the smallest sufficient workflow — discovery for raw ideas, the phase pipeline for formal delivery, a single skill for bounded tasks.
  4. Skills write real artifacts into docs/ and shared state files; CLIs validate and track them.

Keeping skills current

After sdtk update bumps kit versions, refresh each project's runtime assets:

bash
sdtk init --runtime claude --force   # or --runtime codex

Per-kit control is available too: sdtk-spec runtime install|status|uninstall (same for ops/code).

Where to go next

SDTK — governed, auditable, resumable AI-assisted engineering.