Skip to content

Astromesh Leia

Leia, a lemon beagle in an astronaut helmet

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 Leia, the author’s lemon beagle: a scent hound, bred to follow a trail until it finds what it was sent for — which is the job here too.

  • Prompts, not a program. Leia is ten slash commands, five subagents, six templates and eight 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 0.74.1: per-role models, the real orchestration patterns, spec.chain, spec.output_schema, every tool type that loads (including integration, api, mcp and a2a), prefetch, prompts.context, OKF knowledge bundles, guardrails, permissions, spec.skills and A2A publishing, and the version each one needs.
  • A guide to the ecosystem. schemas/ecosystem.md lists the current version of every component and when to point at each library: astromesh-a2a for agents in other frameworks, astromesh-okf to check a bundle, astromesh-rag and astromesh-context for your own code.
  • 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.

SubagentModelDoes
leia-interpreterSonnetTurns a sentence into an intent (create, deploy, status, test, diagnose…) and entities (business, channel, name, tenant, vertical), then routes
leia-architectOpusReads the bundled schemas and the closest template, checks ollama list, picks a pattern, and writes the manifest
leia-operatorSonnetCalls the Nexus API with curl and the cluster with kubectl
leia-testerSonnetProxies a chat to the agent, or runs five scenarios and scores them
leia-doctorSonnetWalks a fixed checklist, stops at the first failure, and gives a root cause and the fix
LeiaNexusAstromesh core knowledge
0.11.x0.26 – 0.28.x0.29 – 0.74.x
0.10.x0.26 – 0.28.x0.29 – 0.74.x
0.9.x0.26.x0.29 – 0.71.x
0.8.x0.26.x0.29 – 0.70.x
0.7.x0.3.x0.29 – 0.70.x
0.6.x0.3.x0.29 – 0.68.x
0.5.x0.3.x0.29 – 0.38.x
0.4.x0.3.x0.29 – 0.36.x
0.2.x0.3.x0.18 – 0.28.9

From 0.8.0 the operator, tester, doctor, bootstrap and logs send the API key in X-API-Key, and the bundled schemas/nexus-api.md describes Nexus 0.26.11: /run, /run/stream, invocations, usage, versions, subscriptions and the /admin plane. The tester reads the 0.70 response (blocked/guardrail, propuestas, usage.by_model): an expected block passes, an unexpected one fails and names the rule. Nexus 0.26.11 does not forward blocked/guardrail (0.26.12 does), so against 0.26.11 the tester infers the block from the answer.

Leia 0.10 adds the A2A server of Nexus 0.27–0.28.2 to nexus-api.md: card, SendMessage (blocking or returnImmediately), streaming, GetTask, CancelTask, SubscribeToTask, ListTasks and the run usage part. Publishing needs Nexus 0.27+, spec.skills core 0.73+ and type: a2a tools core 0.74+; the rest works against any 0.26.x.

Leia 0.7.x and earlier target Nexus 0.3.x; against 0.26.x design with them and publish the YAML with Cortex or the Nexus API:

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

VersionSynced toAdded
0.11.2Nexus 0.28.2, core 0.74.1Herald 0.14.0 in schemas/ecosystem.md: a binding with an agent can also send attachments to media_callback_url; a new row in the request table.
0.11.1Nexus 0.28.2, core 0.74.1Herald 0.13.0 in schemas/ecosystem.md: new conversations per day, hour and channel.
0.11.0Nexus 0.28.2, core 0.74.1A request-to-component table at the top of schemas/ecosystem.md (Spanish and English); Cortex 0.29, Forge 0.29.1, Glyph, Orbit vs. Prisma and Nebula/Centinela with their status; Spanish verbs mapped to every intent; the context eval’s level 2 marked as not run.
0.10.0Nexus 0.28.2, core 0.74.1type: a2a tools (card_url, auth by env var name, policy) and the warning that the Nexus pool has no tenant env vars; spec.skills, spec.a2a.publicar and origen (an agent’s turn never confirms a write); sub-agent usage counted in the parent’s cost_limit and billed; the Nexus A2A server in nexus-api.md; an A2A check in the operator, doctor and tester; schemas/ecosystem.md.
0.9.0Nexus 0.26.13, core 0.71.0Schemas and the architect at core 0.71: permissions (fnmatch over registered tool names, denied wins), semantic/episodic memory scoped to the session, real swarm handoff with max_handoffs, enforced timeout_seconds (120 s recommended); /leia logs marks invocations blocked by a guardrail.
0.8.0Nexus 0.26.11, core 0.70.0Operations use X-API-Key (Bearer gave 401); nexus-api.md rewritten for 0.26.11; the tester understands blocked/guardrail, propuestas and by_model; kind: Eval, OKF bundle and RAGPipeline schemas; /leia deploy --node for standalone nodes.
0.7.0core 0.70.0Guardrails are enforced in core 0.70, so the architect emits them again: the real rule types per side, message, and the cautions (no input PII redaction when tools need IDs or phones, cost_limit ≈ 4000 for the whole run, US-format PII patterns). Templates carry input max_length and cost_limit, and output PII redaction where it fits.
0.6.0core 0.68.0The whole manifest again: integration, api and mcp tools with confirm/mode, prefetch, prompts.context and context_window, max_result_tokens, pipeline stages, Glyph, and spec.knowledge with OKF bundles. It also says what 0.68 accepts but never applies: spec.guardrails, permissions.allowed_actions, semantic and episodic memory, a swarm handoff, orchestration.timeout_seconds
0.5.0core 0.38.1spec.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
0.4.0core 0.36.0Only 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
0.3.0core 0.29.0Per-role models (default + roles), litellm, the roles each pattern asks for
0.2.1core 0.28.9Moonshot / Kimi through openai_compat
0.2.0core 0.28.5, Nexus 0.3.0Fixed templates that the runtime silently ignored (flat memory, limit instead of max_chars) and invalid patterns; dual auth
Built by FAiNANSU