ai-harness-workshop-demo

Use when the user says "netwatch" or asks to measure network stats (ping latency, packet loss, interface throughput) in the background. Launches a background subagent via the `task` tool that runs ~20s of measurements, then returns control immediately so the user can keep talking. Demonstrates background subagent invocation in opencode.

Private sieve subskill. Invoked by the sieve controller after each pass; not user-invocable. Reads sieve.state and draws the current grid — remaining primes vs. struck (composite) numbers.

Demonstrates cyclic skill invocation — runs the Sieve of Eratosthenes by invoking a private "strike" subskill once per prime, re-rendering a visual grid after each pass. Takes an upper limit n. Use to show one skill invoking another skill N times in a loop.

Private sieve subskill. Invoked by the sieve controller once per prime; not user-invocable. Strikes the multiples of a single prime p out of the sieve and records them in sieve.state.

Use when the user says "syscheck" or asks for a parallel system health check. Fans out THREE subagents at once via the Agent tool — one checks CPU, one network, one memory — using only safe read-only commands, then synthesizes their results into one report. Demonstrates parallel subagent fan-out in Claude Code.

Use when the user says "syscheck" or asks for a parallel system health check. Fans out THREE subagents via the `task` tool — one checks CPU, one network, one memory — using only safe read-only commands, then synthesizes their results into one report. Demonstrates parallel subagent fan-out in opencode.

Demonstrates recursive self-invocation with a depth limit. Performs a breadth-first (level-order) traversal of the decision tree in tree.json by invoking ITSELF once per level — each call expands the current frontier and recurses on the next, stopping at a maximum depth. Takes an optional max depth.

Demonstrates recursive self-invocation as a depth-first descent — a "20 questions" guesser. Walks the decision tree in tree.json by asking the user one yes/no question per node and invoking ITSELF on the chosen child, going deeper until it reaches a leaf entity and guesses it.

Demonstrates passing arguments through a chain of skills. Takes two numbers (the legs of a right triangle) and computes the hypotenuse √(a²+b²) across three private stages, each its own skill. Use to show sequential skill execution with argument passing.

Private calc stage A (sum of squares). Invoked by calc-pipeline with two numbers as its argument; not meant to be run directly by the user. Computes a²+b² and hands off to stage B.

Private calc stage B (square root). Invoked by stage A with the sum of squares as its argument; not user-invocable. Computes √s and hands off to stage C.

Private calc stage C (round & classify). Invoked by stage B with the hypotenuse as its argument; not user-invocable. Final stage: rounds, classifies, reports the full log, and ends the chain.