Nonprofit: Grant Reporting Packet Assembly with Claude Code: API Runtime Pattern
A production playbook for grant reporting packet assembly in nonprofit operations using Claude Code: api runtime pattern, run-scoped inputs, logs, typed results, and artifacts.
Audience: Nonprofit operations teams
The problem
Nonprofit operations teams need grant reporting packet assembly to run repeatedly against grant agreements, program metrics, receipts, narratives, and evidence files. In nonprofit operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.
Implementation path
Package the grant reporting packet assembly instructions as a skill, send grant agreements, program metrics, receipts, narratives, and evidence files 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 grant reporting packet assembly, 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=nonprofit-grant-reporting
inputs[]=@./input-pack.zip
result_schema=argo.result.v1
Run this on Argo