Agent Webhook Handler with Claude Code: API Runtime Pattern
A production playbook for agent webhook handler in cross-industry operations using Claude Code: api runtime pattern, run-scoped inputs, logs, typed results, and artifacts.
Audience: Backend teams wiring agent runs into products
The problem
Backend teams wiring agent runs into products need agent webhook handler to run repeatedly against run states, webhook payloads, retries, and signatures. In cross-industry operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.
Implementation path
Package the agent webhook handler instructions as a skill, send run states, webhook payloads, retries, and signatures as run-scoped inputs, execute with Claude Code, poll terminal status, and consume argo.result.v1 instead of parsing a transcript.
Tradeoffs and failure modes
The API boundary forces the workflow to define inputs, terminal states, and result shape before customers depend on it. For agent webhook handler, the practical test is whether a second run can be debugged, retried, and consumed by a product without reading the raw agent transcript.
Run request
POST /api/skills/<skill_id>/run
provider=claude-code
workflow=agent-webhook-handler
inputs[]=@./input-pack.zip
result_schema=argo.result.v1
Run this on Argo