Template
mathiasandClaude Opus 5
020edc5b3a
Canonical gained two inputs so the repos still to migrate can adopt without forking the script again: TARGET for multi-stage builds (cad, agentsquad) and BUILD_SECRETS for buildkit secret mounts (agentsquad). BUILD_SECRETS takes the SPEC only (`id=NAME,src=PATH`) -- the caller writes the secret to PATH itself, so no secret value ever reaches this script's argv or the CI log. Unused here; this repo's copy just stays byte-identical, which is the whole point. Written by `task ci:sync`, not by hand. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011PL5XcG68SvQqz3vGVbWbf
PROJECT_NAME
Go agent built on Google ADK with a LiteLLM adapter for local model routing.
Quick start
cp .env.example .env
# edit .env with your LITELLM_API_KEY
go mod tidy
task run
Harness & workflow
Single harness: Claude Code + hyperguild — session-based (start a session, it works, it
stops). No push-triggered dispatch. MCP connections live in .mcp.json: brain (knowledge)
and gitea (issues/PRs — the audit trail); provide BRAIN_MCP_TOKEN and GITEA_MCP_TOKEN.
Work flows: issue → hyperguild session → PR (task check gate) → report-back comment on the
issue → brain capture if the learning is durable. See AGENTS.md / CLAUDE.md for the full
context, AGENT_BOUNDARIES.md for runtime scope.
Observability
Set OTLP_ENDPOINT=http://jaeger.d-ma.be:4318 to emit traces. Each invocation produces:
invoke_agent __PROJECT_NAME__spangenerate_content <model>child span withgen_ai.request.modelattribute
Structure
cmd/__PROJECT_NAME__/ agent entrypoint
pkg/litellm/ OpenAI-compat ADK adapter + OTLP telemetry helper