task-agent-eliza-bridge

Exposes read-only loopback endpoints giving spawned CLI task agents parent Eliza runtime context.

1|Updated Aug 5, 2026
One-click install
npx skills add https://github.com/Solizardking/Solana-Robotics-Kit --skill task-agent-eliza-bridge-solizardking
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: task-agent-eliza-bridge
Source: https://github.com/Solizardking/Solana-Robotics-Kit/tree/main/eliza/packages/skills/skills/task-agent-eliza-bridge
Command: npx skills add https://github.com/Solizardking/Solana-Robotics-Kit --skill task-agent-eliza-bridge-solizardking

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? When an Eliza runtime spawns a CLI coding agent (Claude Code, Codex, Gemini, Aider), the child agent loses access to parent context like character persona, originating room, memory, and active workspace state. This Skill defines a read-only loopback bridge so the child can retrieve that context on demand without receiving API keys or full memory dumps. ## Core Features & Use Cases - Parent Context Endpoint: The child agent curls GET /api/coding-agents/<sessionId>/parent-context to fetch character, room, and model preference data. - Memory Search: GET /api/coding-agents/<sessionId>/memory?q=<query>&limit=N lets the child resolve references like "the project from yesterday" against parent memory. - Workspace State: GET /api/coding-agents/<sessionId>/active-workspaces returns the parent's active workspace state. - Use Case: A user tells Eliza "have the coding agent apply the same markup as last time." The spawned agent queries the bridge memory endpoint to resolve what "last time" refers to, then continues the task with that context. ## Quick Start Spawn a coding task agent from Eliza and have it query the loopback bridge endpoints with its session id whenever the task references unresolved parent context.

Frequently Asked Questions about task-agent-eliza-bridge

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I give a spawned coding agent access to Eliza runtime context?

Inject a parent-runtime reference into the agent's memory file, then have it curl the loopback endpoints with its session id. Available endpoints cover parent context, memory search, and active workspaces, all read-only.

What endpoints does the Eliza task agent bridge expose?

Three GET endpoints: /parent-context for character, room, and model preferences; /memory?q=<query>&limit=N for memory search; and /active-workspaces for workspace state. All are loopback-only and scoped by session id.

Can a child task agent write to parent Eliza memory?

No. The bridge is strictly read-only with GET endpoints only. It does not support parent memory writes, action delegation, or persistent child identity assumptions.

What happens when the bridge returns 410 or 503 errors?

A 410 task_no_longer_active response means the child should continue in workspace-only mode and note that parent context was unavailable. A 503 parent_context_timeout means the child should not retry indefinitely.

Should I pass the parent API key to a spawned coding agent?

No. The bridge exists specifically to avoid sharing the parent's API key or full memory dumps. Cloud state belongs to the eliza-cloud skill, while local runtime state is served through this session-scoped loopback bridge.