Files
tom_analysis_agent/CLAUDE.md

28 lines
1.3 KiB
Markdown

# CLAUDE.md
## Direction
This agent turns a description of a solution into a reviewed target operating model. It is the Execution engine (`../orchestration_engine`) and one Workflow, `app/operating_model/workflow.py`. Read `CONTEXT.md` and `docs/adr/` before designing or restructuring anything.
Three rules are the point of the design:
- **The solution is never changed here.** What operations needs and the solution lacks is a finding, returned to whoever owns the design (ADR-0001).
- **No agent writes a number of people or a cost.** They are computed from the rate card Skill, whose prices only the service provider sets (ADR-0003).
- **Behaviour lives in Skills.** The core names no Cloud provider and no framework. The capability catalogue is in our own words and cites the frameworks it draws on.
Engine code is not edited here. A fault in it is fixed in `../orchestration_engine`.
Plans and history live in `.agents/plans/`; `IMPLEMENTATION_PLAN.md` is the plan across both repositories. The design spec is `.scratch/target-operating-model/spec.md`.
## Checks
A step is done when all three pass:
```bash
.venv/bin/python -m pytest -q
.venv/bin/ruff check . && .venv/bin/ruff format --check .
.venv/bin/mypy .
```
Set up with `pip install -e ../orchestration_engine --config-settings editable_mode=compat` and then `pip install -e '.[dev]'`.