Tama Kit

Tama Kit is a domain-neutral ChatGPT and Codex plugin for building, changing, and auditing Tama Terraform graph networks. It combines focused graph skills with a workspace-specific Tama MCP connection. The skills cover routed conversations, direct forwarded actions, shared replies, ingestion, enrichment, embeddings, indexing, batch reprocessing, the required global foundation, and Terraform-safe graph migration.

Bootstrap a local Tama runtime

Tama Kit also ships a conventional CLI for adding a local Tama runtime and a starter Terraform root to an existing Rails, Phoenix, Node, or generic application repository:

npx @upmaru/tama-kit bootstrap

After a global npm installation, the equivalent command is:

tama-kit bootstrap

Bootstrap detects the project and its default Docker Compose file, creates a private .tama.env, adds managed Tama and PostgreSQL services, and generates a tama/ Terraform root with one version-pinned module "global". It preserves an existing global-foundation address and refuses ambiguous ownership rather than creating duplicate data-bearing resources.

Generated non-sensitive files are tracked by tama/.tama-kit.json. If a tracked file has been edited since the previous bootstrap, Tama Kit stops and reports the drift instead of overwriting the user's changes.

Inspect the proposed changes without writing:

npx @upmaru/tama-kit bootstrap --dry-run

Generate and start the local services:

npx @upmaru/tama-kit bootstrap --start

The first release uses Tama's supported interactive setup flow to create root and provisioner credentials. Bootstrap does not use the test-only provisioner path and never runs terraform apply.

Installation

Codex

Tama Kit is distributed as a plugin containing the graph-builder and graph-audit skills. The plugin is downloaded from npm through the Upmaru marketplace; installing the npm package by itself does not enable the plugin in ChatGPT or Codex.

This installation path requires the Codex CLI with plugin support, Node.js 20 or newer, and an npm CLI available on your system.

Add the marketplace and install the plugin:

codex plugin marketplace add upmaru/tama-kit
codex plugin add tama-kit@upmaru

Start a new Codex session after installation so Codex can load the bundled skills. You can then invoke either skill explicitly:

$graph-builder
$graph-audit

For example:

Use $graph-builder to add a routed support-search component with plain and
artifact replies, then verify every trigger-to-terminal path.

To confirm the plugin is installed:

codex plugin list

OpenCode

OpenCode loads Agent Skills directly; it does not use the Codex plugin manifest. Install both Tama Kit skills globally with the Skills CLI:

npx skills add upmaru/tama-kit \
  --agent opencode \
  --global \
  --yes

For a project-only installation, run the same command from the project root without --global:

npx skills add upmaru/tama-kit \
  --agent opencode \
  --yes

Start a new OpenCode session after installation, then ask it to use graph-builder or graph-audit. You may install just one of the two skills by adding --skill graph-builder or --skill graph-audit. These steps install only the skills; configure your workspace-specific Tama MCP server separately when runtime inspection is needed. See the Skills CLI, OpenCode's official Agent Skills, and MCP servers documentation.

Included skills

graph-builder designs, implements, extends, migrates, and removes graph slices. It models execution edges, control edges, operational policy, terminals, and Terraform lifecycle impact before editing.

graph-audit traces existing graphs without editing them. It reports incomplete topology, missing control edges, unsafe lifecycle changes, and runtime unknowns with exact evidence.

Development

The bundled maintenance utilities and Terraform inspector are dependency-free Node.js ES modules; no Python runtime is required. The CLI remains native ESM and uses JSDoc contracts with a no-emit TypeScript check, so development does not require a compiled dist/ tree.

Memovee-derived forward-test cases live in evals/cases.json; public skill references remain domain-neutral. Validate the public-directory metadata, Template MCP scaffold, and review cases with:

npm run check
npm run typecheck
npm test
npm run validate:bootstrap
npm run validate:submission

npm run check verifies formatting, lint rules, and import ordering with Biome. Use npm run check:fix to apply its safe fixes and formatter output locally.

The public Template MCP connection is intentionally not represented by a fake local endpoint. Configure the review materials with a concrete, working example endpoint:

npm run configure:mcp -- \
  --example-url "$TAMA_KIT_EXAMPLE_MCP_URL"

The example URL must be publicly reachable and must match the committed https://{host}/mcp template. Tama deployments expose Streamable HTTP at /mcp; their OAuth discovery metadata remains owned by each deployment. The OpenAI Platform draft identifier shown as asdk_app_v_... belongs to the draft URL and is not an MCP app ID, package setting, or .app.json value.

After configuration, run the review-readiness gate and build the distributable plugin ZIP:

npm run validate:review
npm run build:submission

The archive is written to dist/tama-kit-<version>.zip. In the OpenAI Platform draft, enter the Example and Template MCP Server URLs directly and upload the final skill bundles from skills/. Portal test cases remain in evals/cases.json because they are review materials rather than plugin runtime files. Copy-ready listing URLs, selected review cases, and release notes live in submission/portal.json.

Template MCP URLs are available only to trusted OpenAI developers with an established relationship. The OpenAI review also requires a verified publisher, Apps Management write access, and a public non-test example MCP endpoint. See the official plugin packaging and submission requirements.

License

Tama Kit is licensed under the Apache License 2.0.