- New cp1-discovery-package-agent (ADR 0020): one package per reviewed run, every part hashed (sha256 over canonical JSON), with a manifest and a value scorecard. - Applications grouped CMDB -> tag -> resource group with a judged model fallback (ADR 0021): CMDB 0.7.0 carries ownership, dependency mapping 0.6.0 groups, report 0.9.0 shows them. - Critic 0.6.1 accepts the producers' enums; build_workflow.py refuses a consumer enum narrower than its producer's. - Code hooks, sub-agents and tests for the inventory, CMDB, dependency, planner and critic agents; the report and Well-Architected review agents; ADRs 0012-0021. - Workflow cases with value bars and run limits; run evaluation and usage collection scripts; the run context template and the field-by-field review for ADR 0016. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Individual agents, ALZ-F01 Discovery: documentation
For people who run, review or operate CP1 Discovery with the individual-agents pattern. Instructions for coding agents are in ../CLAUDE.md and ../.agents/.
| Document | For |
|---|---|
| deployment.md | Platform operators: building, pushing and deploying the agents with kustomize |
| adr/ | Product owner and reviewers: every change to the original ALZ-F01 requirements in this pattern |
| run-context-field-review.md | Product owner: ADR 0016's 51 run context fields, one by one, with a recommendation and a decision column |
| discovery-value-plan.md | Product owner: what the output must give the Engagement Lead and Assessment, the scorecard baseline, and the phases to raise it |
<agent>/docs/user-guide.md |
Engagement leads: what each step does and how to read its output |
- MCP tools and context: why each agent holds its tools, how context carries between steps, and what to watch for.