LaunchKit · 2026
Back to Skills

agentmanager

This file is a concise integration contract for AI tool callers and gateway implementers.

0
465 downloads
by @nonightwatch

Setup & Installation

openclaw skills install @nonightwatch/agentmanager

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install agentmanager

Version History

v1.0.2Feb 19, 2026 - Version note by skill developer:

- Added new core modules: `src/config.ts` for validated configuration and `src/lib/safe-fetch.ts` for safe network requests. - Introduced basic tests for provider gateway and safe fetch logic (`tests/gateway-provider.test.ts`, `tests/safe-fetch.test.ts`). - Updated documentation to clarify environment variable requirements and outbound data handling.

What This Skill Does

Agent Manager is an orchestration kernel that receives plans from external AI systems, then validates, schedules, and executes the tools within those plans. It enforces token budgets, tracks per-task costs, and stores replayable telemetry for every run.

It separates plan authoring from execution infrastructure, so any external planner can submit plans without implementing its own scheduling, budget enforcement, or streaming telemetry.

When to use it

  • Running multi-step AI agent workflows with enforced cost budgets
  • Streaming real-time task execution events to a monitoring dashboard
  • Replaying a failed run to debug the exact tool call sequence
  • Injecting deterministic result overrides into a live task mid-run
  • Auditing per-task LLM costs across multiple tenants or workloads

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: execute a two-task plan where task A fetches data and task B summarizes it

AGENT
  1. 1Call GET /v1/capabilities to confirm available providers
  2. 2Submit plan via POST /v1/plan to validate structure and get recommendations
  3. 3Start the run with POST /v1/run and receive a run ID
  4. 4Stream progress with GET /v1/run/:id/stream, reading task_start and tool_call_end events
  5. 5Retrieve final results and cost breakdown from GET /v1/run/:id
OUTPUT

Completed run record with per-task cost attribution and a replayable event log