Refine project documentation and track metric files

Close gaps found in a review of the documentation:
- Track data/metrics/ and data/metric_sources.json in git so the data
  checker passes on a fresh clone (finding 23; decision logged)
- State the Alaska and Hawaii coverage gap in the README limitations and
  extend finding 12
- File findings 24-26: the data-sources doc lacks gridMET and several
  pipeline commands; wettest/driest month are computed twice; solar GHI
  is written by the extreme-temperature apply step
- Add the stale "fallback values" note to filter 2's tasks

Tidy the document system:
- Add docs/reviews/README.md with the numbering rules and a finding index
- Rename koppen-mixed-display-plan.md to koppen-mixed-display.md and fix
  its stale Puerto Rico and "stage 5" text
- Add the precipitation-month step to the README enrichment list
- Describe the Current method / Previous method pattern in plan section 5
- Add CLAUDE.md with the project guardrails and doc layout

Format filter-calculations.md so it renders on GitHub and in VS Code:
inline math uses $...$, ranges use en dashes, and implementation
references name functions instead of line numbers.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

docs/pipeline-plan.md

@@ -50,8 +50,6 @@ run after it.
 6. `summarize_county_gridmet_humidity.py` → `apply_gridmet_humidity_metric_to_climate_data.py`
 7. `apply_nsrdb_cloud_metric_to_climate_data.py`
 
-The README's enrichment list starts at step 2 and omits steps 1 and 3.
-
 ### Problems
 
 1. **Rerunning a step can destroy data.** The base build writes 12 columns,
@@ -66,7 +64,8 @@ The README's enrichment list starts at step 2 and omits steps 1 and 3.
 2. **Order is implicit.** The sequence lives in the README, in
    `scripts/county_data_sources.md`, and in each script's assumptions.
 3. **Column ownership is unclear.** GHI is finalized by the extreme-temperature
-   apply script; wettest/driest month are computed in two places.
+   apply script; wettest/driest month are computed in two places. See findings
+   25 and 26 in [reviews/00-cross-filter.md](reviews/00-cross-filter.md).
 4. **County aggregation is inconsistent.** See finding 11 in
    [reviews/00-cross-filter.md](reviews/00-cross-filter.md).
 5. **No single entry point or final check.** A new user must piece together
@@ -160,20 +159,24 @@ For each filter:
    filter's review file under `docs/reviews/`.
 2. Decide any rule or method changes with the project owner, and record them in
    `decisions.md`.
-3. Record the adopted definition in `filter-calculations.md`.
+3. Record the adopted definition in `filter-calculations.md`. Until the new
+   values are applied, keep the old definition below it under "Current
+   method".
 4. Implement the calculation, writing `data/metrics/<metric>.csv`.
 5. Add a single-column apply step for the current CSV.
 6. Update the rules in `check_climate_data.py`.
 7. Add or update unit tests.
 8. Apply to the CSV, run `check_climate_data.py`, and compare changed counties
-   against expectations.
+   against expectations. Then rename "Current method" to "Previous method" in
+   `filter-calculations.md`, as §1 does.
 9. Update the app if the value set or display changes.
 
 ## 6. Filter tracker
 
 Each filter's findings, decisions, and tasks are in its review file. Findings
 that affect more than one filter are in
-[00-cross-filter.md](reviews/00-cross-filter.md).
+[00-cross-filter.md](reviews/00-cross-filter.md), and
+[reviews/README.md](reviews/README.md) indexes every finding number.
 
 | # | Filter | Status | Review |
 | --- | --- | --- | --- |