@tekyzinc/gsd-t 5.22.10 → 5.24.10

package/scripts/statusline-command.sh

@@ -66,11 +66,20 @@ model=$(printf '%s' "$input" | jq -r '.model.id // ""')
 #       Computed as input_tokens + cache_creation_input_tokens +
 #       cache_read_input_tokens to capture the full window pressure. ---
 ctx_left=""
-if [ -n "$cwd" ]; then
+# Claude Code passes this session's transcript path directly. Prefer it: the
+# cwd-derived slug below misses whenever the session's working folder is a
+# subfolder (or contains spaces), which silently dropped the ctx field.
+transcript=$(printf '%s' "$input" | jq -r '.transcript_path // ""')
+if [ -n "$transcript" ] && [ -f "$transcript" ]; then
+  sess_dir=$(dirname "$transcript")
+elif [ -n "$cwd" ]; then
   proj_slug=$(printf '%s' "$cwd" | sed 's:/:-:g')
   sess_dir="$HOME/.claude/projects/$proj_slug"
+fi
+if [ -n "$sess_dir" ]; then
   if [ -d "$sess_dir" ]; then
-    latest_jsonl=$(ls -t "$sess_dir"/*.jsonl 2>/dev/null | head -1)
+    latest_jsonl=$transcript
+    [ -f "$latest_jsonl" ] || latest_jsonl=$(ls -t "$sess_dir"/*.jsonl 2>/dev/null | head -1)
     if [ -n "$latest_jsonl" ]; then
       # Window size by model family. Haiku = 200k; everything else = 1M.
       case "$model" in

package/templates/CLAUDE-global.md

@@ -625,7 +625,7 @@ Add `**Also available:**` with `- /gsd-t-{alt} — {desc}` lines if alternatives
 | `setup` | `status` | |
 | `design-decompose` | `design-build` | `partition` (if domains needed first) |
 
-Commands with no successor (standalone): `quick`, `debug`, `brainstorm`, `status`, `help`, `resume`, `prompt`, `log`, `health`, `pause`, `estimate`, `stories`, backlog commands.
+Commands with no successor (standalone): `quick`, `debug`, `brainstorm`, `status`, `help`, `resume`, `prompt`, `log`, `health`, `pause`, `estimate`, `estimate-rescale`, `stories`, backlog commands.
 
 Skip the hint if auto-advancing (Level 3 mid-wave) — only show when the user needs to manually invoke the next step.
 

package/templates/estimate-config.json

@@ -10,8 +10,8 @@
   "sizeScale": { "XS": 0.1, "S": 0.25, "M": 0.5, "L": 1, "XL": 2, "XXL": 4 },
   "_sizeScale": "AI-assisted T-shirt scale, person-days (written into the sheet legend by `gsd-t estimate-sheet write`). A size = solo AI minutes x project multiplier + task switching; see estimate-sheet-spec.md section 1.4.",
 
-  "projectMultiplier": { "greenfield-solo": 1, "greenfield-team": 5, "yellowfield-solo": 2, "yellowfield-team-isolated": 8, "yellowfield-team-wide": 12 },
-  "_projectMultiplier": "Solo AI minutes are multiplied by this, by project type (isolated vs wide = code-graph blast radius). Internal to the estimator; never shown on the sheet.",
+  "projectMultiplier": { "greenfield-solo": 1, "greenfield-team": 3, "yellowfield-solo": 2, "yellowfield-team-isolated": 5, "yellowfield-team-wide": 7 },
+  "_projectMultiplier": "Solo AI minutes are multiplied by this, by project type (isolated vs wide = code-graph blast radius). Internal to the estimator; never shown on the sheet. Includes team overhead — set the sheet overhead factor accordingly (David, 2026-09-28).",
 
   "totalMF": 0.7,
   "_totalMF": "Overhead multiplier applied to raw Days. Tekyz default 0.7 = QA 0.3 + PM 0.1 + Analysis 0.05 + Deployment 0.05 + Buffer 0.2. Raise Buffer/QA when confidence is low.",

package/templates/estimate-sheet-spec.md

@@ -80,20 +80,20 @@ Column widths: `[150, 120, 300, 430, 122, 90, 90, 61, 53, 76, 81, 81]`.
 
 #### 1.4 How a size is chosen — the AI-assisted model (David, 2026-09-27)
 
-Nobody hand-writes code. A size is the **team hours** a task takes with AI-assisted development, and the multipliers that produce it live in the estimator — never on the sheet. Calibration: the Hilo Delivery Runway build (45 tasks, ~26 solo hours: 13 David + 13 Claude).
+Nobody hand-writes code. A size is the **team hours** a task takes with AI-assisted development, and the multipliers that produce it live in the estimator — never on the sheet. Calibration: the Hilo Delivery Runway build (45 tasks, ~26 solo hours: 13 David + 13 Claude — solo minutes count both).
 
-1. **Estimate the task in SOLO AI-assisted minutes** — one person directing Claude, greenfield. Runway rate: roughly 5 min for a trivial change, 20 min for a typical screen element or endpoint, 1–2¼ hrs for the heaviest pieces.
+1. **Estimate the task in SOLO AI-assisted minutes** — one person directing Claude, greenfield, counting **the person's time AND Claude's time** (David, 2026-09-29). Runway rate: roughly 10 min for a trivial change, 40 min for a typical screen element or endpoint, 2–4½ hrs for the heaviest pieces.
 2. **Multiply by the project type:**
 
 | Project | Multiplier |
 |---|---|
 | Greenfield, solo | × 1 |
-| Greenfield, team | × 5 |
+| Greenfield, team | × 3 |
 | Yellow-field (existing app), solo | × 2 |
-| Yellow-field, team — isolated change | × 8 |
-| Yellow-field, team — big blast radius | × 12 |
+| Yellow-field, team — isolated change | × 5 |
+| Yellow-field, team — big blast radius | × 7 |
 
-   Blast radius comes from the code graph (`gsd-t graph blast-radius`), not a guess.
+   The multipliers include team overhead (reviews, QA, coordination) — do not also charge it through the overhead factors (David, 2026-09-28). Blast radius comes from the code graph (`gsd-t graph blast-radius`), not a guess.
 3. **Add task switching AFTER the multiplier** — it is one person's pickup time and does not grow with team size: 5–10 min for small tasks (less when related tasks run back-to-back), ~15 min medium, up to 30 min large.
 4. **Pick the nearest size** on the §1.1 legend. `gsd-t estimate-sheet size --solo-min <n> --project <type> [--switch-min <n>]` does steps 2–4 and prints the size.
 
@@ -273,7 +273,8 @@ Everything in §1–§5 is executed by `bin/gsd-t-estimate-sheet.cjs`, not re-de
 
 ```
 gsd-t estimate-sheet plan-schema                              # the plan shape
-gsd-t estimate-sheet size --solo-min <n> --project <type> [--switch-min <n>]   # §1.4: solo minutes → team hours → size (no sheet needed)
+gsd-t estimate-sheet size --solo-min <n> --project <type> [--switch-min <n>] [--xxs]   # §1.4: solo minutes → team hours → size (no sheet needed); --xxs for (Rescale) tabs
+gsd-t estimate-sheet rescale --sheet <id|url> (--list | --plan <p.json> [--dry-run] [--replace] [--suffix <name>])  # §7: re-price into (Rescale) copies; originals untouched
 gsd-t estimate-sheet read       --sheet <id|url> [--tab <name>]   # read-before-write dump
 gsd-t estimate-sheet plan-check --sheet <id|url> --plan plan.json # validate + the roster it WOULD write (the Step 4 pause)
 gsd-t estimate-sheet write      --sheet <id|url> --plan plan.json [--replace]   # T-Shirt + Team Mix + Tech Stack, then audit
@@ -309,3 +310,22 @@ The plan (judgment only):
 - `tshirt.mode` `items` writes whole rows below the header (halts if rows exist unless `--replace`); `sizes` fills `E:L` on rows that already exist (a gap-analysis sheet), matched by the `(id)` suffix in column C — never by position.
 - `teamMix.fte` is per-discipline FTE (`backend` `frontend` `qa` `pm` `ba` `devops` `techlead` `design` `mobile`). The tool splits it into people (saturate then spill), computes months and the column count, ramps by discipline, writes the remainder formula, and refuses a roster that leaves a weighted MF factor unstaffed. It writes **one grid per phase with hours** (§2.6); `teamMix.phases: { "Phase 1": { "fte": {…} } }` overrides the mix for one phase.
 - The MF list, rate and high factor are READ from the sheet; the plan never carries them. The legend VALUES are written by the tool (the AI-assisted scale, §1.4) — in `sizes` mode it HALTS if a sized row on the tab is missing from the plan, because moving the legend would silently re-price that row.
+
+---
+
+## 7. Rescale — re-price an existing estimate into copied tabs (`/gsd-t-estimate-rescale`)
+
+An estimate written on the old day scale is re-priced **without touching it**. `gsd-t estimate-sheet rescale` copies `T-Shirt Size Estimate` → **`T-Shirt Size Estimate (Rescale)`** and `Team Mix` → **`Team Mix (Rescale)`** (each placed next to its original) and re-sizes the copies only. The original tabs, the Overview tab and the estimates index are never written.
+
+| Step | Rule |
+|---|---|
+| List | `rescale --list` prints every sized item row (row, text, phase, sizes), the size-column labels, legend and MF. |
+| Plan | `{ "items": [ { "row", "functionality", "sizes": [...] } ] }` — every sized row exactly once, matched by row AND exact Functionality text (a moved row HALTS); sizes in size-column order. A missing row HALTS — its copy would silently re-price. |
+| Legend | The copy gets the AI scale plus **XXS 0.0625 d (0.5 hr)** in the row directly under XXL (HALTS if that row is not empty). XXS exists on (Rescale) tabs only. |
+| Formulas | With XXS present the copy's Days column uses an **exact** lookup — `SUMIF(legend, F{r}&" -*", values)` — because the template's `LEFT(F{r},2)&"*"` reads `XX*` as XXS + XXL. The audit expects the exact form whenever the legend carries XXS. |
+| Team Mix | `Team Mix (Rescale)` keeps the original tab's roster (derived as `teammix` does) and staffs the copy's phase rollups (midpoint of Low/High, §2.2). |
+| Formatting | The copy is re-wrapped (C/D) and top-aligned so it passes §5 on its own. |
+| Overhead | The COPY's overhead factors are zeroed by default (the multipliers already include team overhead); `"noOverhead": false` in the plan keeps them. The original tab's factors are never written. |
+| Re-run | Existing (Rescale) tabs HALT the run; `--replace` rebuilds them **in place** — the T-Shirt copy is cleared and re-copied from the original (values, formulas, formats, validation, widths) and the Team Mix copy is cleared and rewritten, so both tabs keep their identity. They are never deleted and re-created: other sheets import them by name (IMPORTRANGE), and a view that refreshes while a tab is missing caches `#REF!`. `--dry-run` prints old → new Low hours and writes nothing. |
+| Audit | §5 T-Shirt + Team Mix checks run on the (Rescale) tabs by read-back; exit 4 on any ✗. |
+| Second copy | `--suffix "AI v2"` writes `T-Shirt Size Estimate (AI v2)` + `Team Mix (AI v2)` instead, so a second re-estimate never overwrites the `(Rescale)` tabs other sheets import by name. Plain text only (no parentheses, quotes or `!`). |

package/templates/playbooks/tekyz-estimation-and-prd-playbook.md

@@ -51,8 +51,8 @@ For each finding, write a row (cols A–G; leave H–L formulas alone):
 `D` Low-Level Requirement · `E` Phase (MVP) · `F` Web Portal size · `G` Backend/API size.
 
 - Size **each column independently** (FE and BE), **AI-assisted** — nobody hand-writes code.
-  Estimate SOLO AI minutes, then `gsd-t estimate-sheet size --solo-min <n> --project <type>`
-  (greenfield solo ×1 · team ×5 · yellow-field solo ×2 · team ×8 isolated / ×12 wide, + task
+  Estimate SOLO AI minutes (human + Claude time; ~10 / 40 min / 2–4½ hr), then `gsd-t estimate-sheet size --solo-min <n> --project <type>`
+  (greenfield solo ×1 · team ×3 · yellow-field solo ×2 · team ×5 isolated / ×7 wide, + task
   switching after the multiplier) picks the size. Sizes: XS .1, S .25, M .5, L 1, XL 2, XXL 4
   (estimate-sheet-spec.md §1.4).
 - Sheet computes: `Days = F+G`, `MFactor = Days×MF`, `Total = Days+MFactor`,