review

<!-- evaluator-ignore: content/broken-references, content/allowed-tools-auto-approve --> # Review Setup Full qualitative review of the user's agent setup. Claude reads every file and evaluates quality, redundancy, coherence, and optimization opportunities. ## Hard Rules 1. **Never give a verdict without reading the files.** Lint counts are input data, not the verdict. A component with warnings can still be healthy. 2. **Read before you judge.** Read every file's actual content before assessing. 3. **Don't manufacture problems.** If the setup is good, say so. 4. **Always end with the evidence-based summary.** 5. **Record the exact start time** (note the timestamp from your first tool call in Step 2) and compute the exact duration at the end. ## Step 1: Ask Output Preference Before doing anything else, ask the user: > Where should i present the results? > 1. **Terminal** - print the report here in the conversation > 2. **File** - write a markdown report to a file (you'll choose the path) Wait for their answer before proceeding. ## Step 2: Run Lint for Context Determine the setup path. If the user doesn't specify one, use the current working directory. ```bash uvx --from harness-eval harness-eval harness-lint <setup-path> --format json ``` If `uvx` is not available, fall back to `pip install harness-eval` and use `harness-eval` directly. Read the JSON output. This gives you per-component diagnostics, token budget, trigger overlaps, and dependency findings. Do NOT p...