# CLAUDE.md Optimizer: the optimisation of the AIMsight detectors on the labels of `labeling/auto`, and nothing else (`README.md`). The workflow: `.claude/skills/improve/SKILL.md` (`/improve`), launched from the root of Optimizer with the agents plugin (`--plugin-dir agents`); its agents `agents:upgrader` and `agents:validator`; the benchmark `detectors/bench/`. - **The links**, out of git: `detectors/` → `~/detectors` (the session commits there); `data/` → `~/aimsight-data/data` and `labeling/` → `~/labeling` (read-only); `agents/` → `~/agents` (the plugin, loaded read-only). - **The sessions**: `sessions/_/`; Diagnostic-App reads their summary (`summary.md`). - **The workflow stays generic**: the skill describes only the workflow (range + labels → upgrader → validator → summary); what is specific to a caller (its paths, its git rules, `Caller's context`) arrives in the request. - **Check a change of the skill**: `env -u ANTHROPIC_API_KEY claude -p "/improve" --plugin-dir agents --model haiku` must say the inputs are missing and stop without touching `detectors/`; then a real session through the app's button. - `archive/`: the former batch and its scanner, stopped; do not run them again. Rules: - **The agents run on the Claude subscription, never on an API key** (`ANTHROPIC_API_KEY` removed from the launch). - Every time is UTC. - Read-only on `data/` and `labeling/`; never copy the metric identifiers (`SIM_CCID`, `ip*`); never read `.env`. - The project uses the labels of `labeling/auto` only; `labeling/manual` is the user's alone. - No rule specific to a station, a target or a date. - Commit by path, never `git add -A`. - Language: English.