- Six declarative agents generated from the v1.1 stories (scaffold_from_stories.py, ADR 0001),
and a 9-step workflow export (build_workflow.py).
- Code-only intake (ADR 0008) verifies the one Discovery package in code before any agent.
- The rate card is the run input rate_card_document; no upload step (ADR 0009).
- Critic 0.1.6 after live runs on crucible-kab-dev:
- K-12 model independence checked at build time against each agent's deployed model
(ADR 0010); the critic reports it from its two inputs;
- receives in_cloud_estate for K-10; an unverified K-10 never fails the run alone;
- K-08 allows the scoring note to list findings as advisory, as ALZ-ASM-04 must;
- carries ALZ-ASM-03's and ALZ-ASM-04's rule sections, copied by the scaffold, so it can
recalculate risk, confidence and TCO.
- The scaffold refuses to regenerate unless every story file is present.
- Case azure-crucible-kab-dev-assessment with an illustrative rate card.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2.6 KiB
2.6 KiB
Individual agents: ALZ-F02 Assessment & Disposition
CP1 Assessment as six separate declarative KAB agents chained by the workflow, cp4-agents style, behind a code-only intake step (ADR 0008). Its counterpart, ../../sub-agents/ALZ-F02: Assessment & Disposition Workflow Agent/, is the sub-agent pattern (not built yet). Keep the two patterns apart: never copy app/, sub-agents or workspace code into this folder, and never merge their ADRs.
@.agents/CONTEXT.md @.agents/PLAN.md
Each agent folder has its own CLAUDE.md and .agents/CONTEXT.md. Repository-wide rules are in ../../CLAUDE.md.
Commands (from this folder)
python3 scripts/scaffold_from_stories.py # regenerate the six agent folders from the v1.1 story files
python3 scripts/build_workflow.py # after any schemas/ change; it asserts every from_steps field exists
python3 ../../scripts/check_agents.py --runtime-image cruciblecoredevacr.azurecr.io/kab/agent-runtime-adk:0.35.7 cp1-*/
(cd ../.. && python3 scripts/render_k8s.py deploy/crucible-kab-dev.yaml <agent> && kustomize build build/crucible-kab-dev/<agent>)
Rules
- Declarative agents only: no
app/, functions or hooks. Scoring, confidence and TCO are prompt rules that the critic recalculates (ADR 0001). Don't add a scoring tool or an MCP server for them. The one exception iscp1-assessment-intake-agent(ADR 0008): code only, not generated by the scaffold, and it only checks the Discovery package. Keep scoring out of it. - Existing MCP servers only. ALZ-ASM-02 and ALZ-ASM-05 use
azure-discovery,aws-discoveryandgcp-discovery. ALZ-ASM-05's guidance comes from<provider>_search_well_architectedon the same servers (Azure and GCP; none on AWS yet). Read-only tools only. - The agent folders are generated by
scripts/scaffold_from_stories.pyfrom the story files in the engineering hub workspace. Change the script and regenerate; regenerating rewrites whole folders, so review the diff. - Discovery's outputs arrive as one package, as text, through
a1(Artifacts) andp1(parse) (ADRs 0002, 0008), and the intakes0checks it before the planner runs. Never wire an agent toa1directly: its only output,artifacts, holds base64 records. - Keep
repo: cp1-agents-individualon these agents in../../deploy/. - A change to an original requirement needs an ADR in
docs/adr/, a link to it from each affected agent'sdocs/adr/README.md(inADRS_FORin the scaffold), and a step in.agents/PLAN.md. - No pattern detail on ADO tickets. Record pattern decisions here, not on the board.