Astromesh Leia

Astromesh Leia is a Claude Code plugin. You describe the agent you need, in English or Spanish, and Leia designs a complete astromesh/v1 manifest with a real system prompt, shows it to you, and can deploy it, test it and diagnose it on a Nexus hub. It is named after a lemon beagle.

v0.5.0 targets an older Nexus

Leia’s operations (deploy, status, logs, test, bootstrap, doctor) were written for Nexus 0.3.x, when Nexus was a Kubernetes operator. Against the current managed Nexus (0.26.x) they do not work as written: Leia sends the API key as Authorization: Bearer, and Nexus only reads API keys from X-API-Key, so its API calls are refused. Its tenant checks also use resources that no longer exist. Agent design, templates and the schema knowledge work regardless of Nexus. See Compatibility.

What Leia is

• Prompts, not a program. Leia is ten slash commands, five subagents, six templates and four reference schemas, all Markdown and YAML. Claude Code runs them; the actual work happens through curl, kubectl and ollama on your machine.
• An agent designer. Its architect subagent knows the agent schema up to astromesh core 0.38.1: per-role models, the real orchestration patterns, spec.chain, spec.output_schema, which tool types load, and the mistakes that make a runtime ignore a section without saying so.
• A deploy-and-test loop for a Nexus hub: publish, poll, chat with the agent, run scored test scenarios, and walk a diagnostic checklist when something fails.

It is not a hosted service, a GUI or an agent framework. The agents it builds run on Nexus and the Astromesh runtime.

How it works

flowchart LR
  you["You<br/>/leia …"] --> interp["leia-interpreter<br/>intent + entities"]
  interp --> arch["leia-architect<br/>YAML + system prompt"]
  interp --> op["leia-operator<br/>curl · kubectl"]
  interp --> test["leia-tester<br/>chat · scenarios"]
  interp --> doc["leia-doctor<br/>checklist"]
  arch -- "preview → yes" --> op
  op --> nexus["Nexus API"]
  test --> nexus
  doc --> nexus
  arch -. reads .-> kb["schemas/ · templates/"]

Subagent	Model	Does
leia-interpreter	Sonnet	Turns a sentence into an intent (create, deploy, status, test, diagnose…) and entities (business, channel, name, tenant, vertical), then routes
leia-architect	Opus	Reads the bundled schemas and the closest template, checks ollama list, picks a pattern, and writes the manifest
leia-operator	Sonnet	Calls the Nexus API with curl and the cluster with kubectl
leia-tester	Sonnet	Proxies a chat to the agent, or runs five scenarios and scores them
leia-doctor	Sonnet	Walks a fixed checklist, stops at the first failure, and gives a root cause and the fix

Compatibility

Part	Nexus 0.3.x (operator)	Nexus 0.26.x (managed hub)
/leia create (design, preview, write YAML)	Works	Works
/leia templates	Works	Works
/leia config	Works	Works
Publishing (create → deploy, /leia deploy)	Works	Refused (401): key sent as Bearer
/leia status, logs, test	Works	Refused (401); status also reads tenant CRDs
/leia bootstrap local, teardown	Works	Installs the old operator: Nexus’s hack/bootstrap.sh still does
/leia bootstrap remote	Works	Auth check fails (401)
leia-doctor checks 3–8	Works	Use kubectl resources that no longer exist

Until Leia is synced with the managed hub, design with Leia and publish the YAML with Cortex or the Nexus API:

curl -X POST "$NEXUS_URL/api/v1/agents" \
  -H "X-API-Key: $NEXUS_API_KEY" -H "Content-Type: application/yaml" \
  --data-binary @agents/my-agent.yaml

Leia	Nexus	Astromesh core knowledge
0.5.x	0.3.x	0.29 – 0.38.x
0.4.x	0.3.x	0.29 – 0.36.x
0.2.x	0.3.x	0.18 – 0.28.9

What each release taught it

Leia’s value is what the architect knows, so each release is a knowledge sync with a core version.

Version	Synced to	Added
0.5.0	core 0.38.1	spec.chain and spec.output_schema: when to offer them, that every agent in on_complete must be deployed first, and that an older runtime ignores both silently. The doctor checks chain declarations
0.4.0	core 0.36.0	Only builtin, agent and client tools load from YAML; which model keys each source reads; the streaming contract and usage.by_model; RAG pipeline and workflow endpoints
0.3.0	core 0.29.0	Per-role models (default + roles), litellm, the roles each pattern asks for
0.2.1	core 0.28.9	Moonshot / Kimi through openai_compat
0.2.0	core 0.28.5, Nexus 0.3.0	Fixed templates that the runtime silently ignored (flat memory, limit instead of max_chars) and invalid patterns; dual auth

Note

The architect’s knowledge stops at core 0.38.1. It does not know the integration, api and mcp tool types, prefetch or Glyph, which arrived later; for those, author in Cortex.

Next steps

• Quick Start — install the plugin and design your first agent
• Command Reference — every command, step by step
• Templates & Agents — the templates, the subagents and the bundled schemas