AI Agents
Stategraph is built to be driven by AI agents (Claude Code, agents using skills.sh, or any tool that loads SKILL.md files), not just humans. The integration surface is a set of skill files in github.com/stategraph/skills that teach the agent the Stategraph workflows, the safe defaults, and the canonical command form.
Available skills
Five skills, one of which is a router that dispatches to the others.
| Skill | Purpose |
|---|---|
stategraph |
Router. Detects Stategraph tasks and dispatches to one of the four workflow skills below. |
stategraph-query |
Read-only MQL queries, state summaries, inventory, blast radius, and gap analysis. |
stategraph-change |
stategraph tf plan, stategraph tf apply, state deletion, transaction lifecycle. |
stategraph-import |
Import .tfstate or HCL into Stategraph. Wire a Terraform repo to Stategraph. |
stategraph-refactor |
Interactive address-rewrite workflow. Restructure a repo while preserving state addresses. |
The router pattern means users typically only need the top-level stategraph skill installed. When the agent detects a Stategraph task, the router selects the right workflow skill and hands off via the agent's Skill tool.
Installing all five together also makes each workflow directly addressable: /stategraph-query, /stategraph-change, /stategraph-import, /stategraph-refactor.
Install
With the skills CLI:
npx skills add stategraph/skills
Or install a specific skill:
npx skills add stategraph/skills -s stategraph-query
Manual install (Claude Code)
Clone into ~/.claude/skills/ so each skill lands at ~/.claude/skills/<name>/SKILL.md:
git clone https://github.com/stategraph/skills /tmp/stategraph-skills
cp -r /tmp/stategraph-skills/skills/* ~/.claude/skills/
rm -rf /tmp/stategraph-skills
Requirements
- The Stategraph CLI on your
PATH. See CLI installation. - A configured tenant.
stategraph infoshould succeed.
Usage
Once installed, ask the agent anything Stategraph-related and the router picks the workflow:
- "What S3 buckets do we have?" runs
stategraph-query - "Plan these changes." runs
stategraph-change - "Import this terraform.tfstate." runs
stategraph-import - "Refactor this repo into child modules without losing state." runs
stategraph-refactor
You can also invoke a workflow directly with /stategraph-query, /stategraph-change, /stategraph-import, or /stategraph-refactor.
Safety model
Two layers, one in the skill files and one in Stategraph itself.
Skill-level: read-only vs mutating. The stategraph-query skill is read-only by design. It runs MQL queries and inventory summaries. It never calls tf plan, tf apply, imports, or refactors. The other three workflow skills are mutating, with each scoped to its own workflow.
Stategraph-level: plan and apply are gated independently. Issue an agent an API token scoped to plan only, and the worst case from a confused model is a wrong plan you throw away. There is no path from a confused model to a destroyed database. For autonomous overnight runs, plan-only is the right default. For agents that have already passed a review boundary (a CI runner on a green PR, for example), issue plan and apply.
See Authentication for token scoping.
See also
- github.com/stategraph/skills: the repo, with each skill's
SKILL.mdin full - Refactor CLI workflow: the underlying CLI the refactor skill drives
stategraph info: the orientation command agents call first- Authentication: scoping API tokens