@tekyzinc/gsd-t 2.50.12 → 2.53.10

package/commands/gsd-t-setup.md

@@ -175,6 +175,82 @@ See `.gsd-t/progress.md` for current milestone/phase state.
 - **Include if relevant**: Where Things Live, Testing, Code Patterns, Environment Variables
 - **Omit if empty**: Deployed URLs (if not deployed), Architecture (if trivial), Workflow Preferences (if no overrides)
 
+## Step 5.5: Quality North Star Configuration
+
+After generating the CLAUDE.md content (Step 5) and before presenting it to the user, offer a Quality North Star section if one is not already present.
+
+**Skip this step if the existing or generated CLAUDE.md already contains `## Quality North Star`.**
+
+Ask the user:
+```
+Would you like to define a Quality North Star for this project?
+This is a 1–3 sentence quality identity that subagents read at execute time to calibrate
+their judgment. It does not add procedural rules — it shapes what "excellent" means here.
+
+Options:
+  [1] library  — "Published npm library: intuitive API, well-documented, backward-compatible, type-safe, zero-dep."
+  [2] web-app  — "User-facing app: accessible, performant, visually consistent. UX is the product."
+  [3] cli      — "Developer CLI: fast, predictable, clear output. Error messages explain what went wrong and how to fix it."
+  [4] custom   — Write your own 1–3 sentences
+  [5] skip     — No Quality North Star (can add later via /user:gsd-t-setup)
+```
+
+If the user picks 1–3, use the corresponding preset text from the table below.
+If the user picks 4, ask: "Describe what 'excellent' means for this project in 1–3 sentences."
+If the user picks 5, skip the section entirely.
+
+| Preset ID | Text |
+|-----------|------|
+| `library` | `This is a published npm library. Every public API must be intuitive, well-documented, and backward-compatible. Type safety and zero-dependency design are non-negotiable.` |
+| `web-app` | `This is a user-facing web application. Every feature must be accessible, performant, and visually consistent. The user experience is the product.` |
+| `cli` | `This is a developer CLI tool. Every command must be fast, predictable, and produce clear output. Error messages must explain what went wrong and how to fix it.` |
+
+Insert the chosen section into the generated CLAUDE.md content before `## GSD-T Workflow`:
+
+```markdown
+## Quality North Star
+
+{selected preset text or custom text}
+```
+
+If the project already has a `CLAUDE.md` with `## Quality North Star`, the generated file preserves the existing section. Do not overwrite user-customized personas.
+
+## Step 5.6: Design Brief Generation (UI Projects)
+
+After the Quality North Star step, check for UI/frontend signals in this project. If detected, offer to generate a design brief.
+
+**Skip this step if `.gsd-t/contracts/design-brief.md` already exists** — user-customized briefs are authoritative. Log: "Design brief: skipped — existing brief preserved."
+
+### Detection — check for ANY of the following
+
+| Signal | How to check |
+|--------|-------------|
+| React, Vue, Svelte, Next.js | in `package.json` dependencies |
+| Flutter | `pubspec.yaml` exists |
+| CSS/SCSS files | `.css`, `.scss`, `.sass` files in project |
+| Component files | `.jsx`, `.tsx`, `.svelte`, `.vue` files in project |
+| Tailwind config | `tailwind.config.js` or `tailwind.config.ts` exists |
+
+If NO signals detected → skip this step entirely. Do not mention it to the user.
+
+If signals detected, ask the user:
+```
+UI/frontend signals detected ({list signals found}).
+Would you like to generate a design brief at .gsd-t/contracts/design-brief.md?
+This gives subagents a consistent visual language reference (colors, typography, spacing, patterns).
+
+  [1] Yes — generate now (sources: Tailwind config if exists, then project defaults)
+  [2] No — skip for now (can generate later by re-running /user:gsd-t-setup)
+```
+
+If user picks 1: generate `.gsd-t/contracts/design-brief.md` using the format defined in `.gsd-t/contracts/design-brief-contract.md` (or the standard format):
+- Extract color palette from `tailwind.config.js/ts` → `theme.colors` if available; else use web defaults
+- Extract fonts from `theme.fontFamily` if available; else use system fonts
+- Read `## Quality North Star` from `CLAUDE.md` for Tone & Voice (skip if absent)
+- Fill remaining fields with sensible defaults and `{placeholder}` markers for user to complete
+
+Log in `.gsd-t/progress.md` Decision Log (if `.gsd-t/` exists): `- {date}: Design brief generated at .gsd-t/contracts/design-brief.md`
+
 ## Step 6: Present and Confirm
 
 Show the generated CLAUDE.md content to the user with a summary:

package/commands/gsd-t-status.md

@@ -1,166 +1,192 @@
-# GSD-T: Status — Cross-Domain Progress View
-
-You are checking the current state of the project across all domains.
-
-## Launch via Subagent
-
-To keep the main conversation context lean, run status via a Task subagent.
-
-**If you are the orchestrating agent** (you received the slash command directly):
-Spawn a fresh subagent using the Task tool:
-```
-subagent_type: general-purpose
-model: haiku
-prompt: "You are running gsd-t-status. Working directory: {current project root}
-Read .gsd-t/progress.md and execute the full status report workflow."
-```
-Wait for the subagent to complete. Relay its output to the user. **Do not read files yourself.**
-
-**If you are the spawned subagent** (your prompt says "running gsd-t-status"):
-Continue below.
-
-## Read These Files
-
-1. `.gsd-t/progress.md`
-2. `.gsd-t/domains/*/tasks.md` — all domain task lists
-3. `.gsd-t/contracts/integration-points.md` — dependency graph
-
-## Report Format
-
-Present a concise status to the user:
-
-```
-📊 GSD-T Status: {milestone name}
-Phase: {PARTITIONED | DISCUSSED | PLANNED | EXECUTING | INTEGRATED | VERIFIED}
-
-Domains:
-  {domain-1}: {completed}/{total} tasks {✅ done | 🔄 in progress | ⏳ blocked}
-  {domain-2}: {completed}/{total} tasks {✅ done | 🔄 in progress | ⏳ blocked}
-  {domain-3}: {completed}/{total} tasks {✅ done | 🔄 in progress | ⏳ blocked}
-
-Backlog: {N} items
-  1. {title} ({type})
-  2. {title} ({type})
-  3. {title} ({type})
-
-Next checkpoint: {description} — waiting on {domain} Task {N}
-Next action: {what should happen next}
-
-Recent decisions:
-  - {latest decision from Decision Log}
-```
-
-### Backlog Section
-
-If `.gsd-t/backlog.md` exists, read and parse it. Show total count and top 3 items (position, title, type). If no backlog file exists, skip the Backlog section entirely. If the backlog file exists but is empty (no entries), show `Backlog: No items`.
-
-If there are blockers or issues, highlight them.
-If the user provides $ARGUMENTS, focus the status on that specific domain or aspect.
-
-## Token Usage Breakdown
-
-If `.gsd-t/token-log.md` exists, read it and append a token breakdown to the status report.
-
-Parse each row in the table. Handle both old format (9 columns) and extended format (12 columns with Domain, Task, Ctx%). Rows with missing or empty Domain column are assigned domain "(untagged)".
-
-### Token Usage by Domain
-Group rows by Domain. For each domain, sum Tokens and collect all Ctx% values (ignoring "N/A" and empty). Display:
-
-```
-## Token Usage by Domain
-| Domain         | Tokens | Subagents | Peak Ctx% |
-|----------------|--------|-----------|-----------|
-| auth           | 12,400 | 4         | 14%       |
-| notifications  | 45,200 | 3         | 52% ⚠️    |
-| (untagged)     | 8,100  | 6         | N/A       |
-```
-
-Flag any domain where Peak Ctx% >= 70 with `⚠️` suffix.
-
-### Token Usage by Phase/Command
-Group rows by Command. For each command, sum Tokens and count subagent rows. Display:
-
-```
-## Token Usage by Command
-| Command       | Tokens | Subagents |
-|---------------|--------|-----------|
-| gsd-t-execute | 86,200 | 14        |
-| gsd-t-wave    | 12,400 | 9         |
-| gsd-t-plan    | 3,400  | 1         |
-```
-
-If token-log.md does not exist or is empty, skip this section entirely (no error).
-
-## Process Health
-
-If `.gsd-t/metrics/rollup.jsonl` exists, read the latest entry and append to the status report:
-
-```
-Process Health:
-  ELO: {elo_after} ({elo_delta > 0 ? '↑' : '↓'} {elo_delta})
-  Quality: {first_pass_rate * 100}% first-pass rate | {total_fix_cycles} fix cycles
-```
-
-If `.gsd-t/metrics/task-metrics.jsonl` exists but no rollup.jsonl, compute first_pass_rate directly from task-metrics for the current milestone and display:
-
-```
-Process Health:
-  Quality: {rate}% first-pass rate (current milestone, no rollup yet)
-```
-
-If neither file exists, skip this section entirely.
-
-## Graph Status
-
-If `.gsd-t/graph/meta.json` exists, read it and append to the status report:
-```
-Graph: {entityCount} entities indexed — last indexed {lastIndexed timestamp}
-```
-If the graph does not exist, skip this section.
-
-## Version Check
-
-After displaying the project status, check for GSD-T updates:
-
-1. Read `~/.claude/.gsd-t-version` to get the installed version
-2. Read `~/.claude/.gsd-t-update-check` (JSON with `latest` and `timestamp` fields) to get the latest known version
-3. If the file doesn't exist or is unreadable, run `gsd-t status` (CLI) in the background to trigger a cache refresh, and skip the notice
-4. If `latest` is newer than the installed version, append to the report:
-
-```
-⬆️  GSD-T update available: {installed} → {latest}
-   Run: npm update -g @tekyzinc/gsd-t && gsd-t update-all
-```
-
-5. If versions match, skip — don't show anything
-
-## Global ELO & Cross-Project Rankings
-
-After the Process Health section, check for global metrics:
-
-1. Run via Bash:
-   ```bash
-   node -e "const g = require('./bin/global-sync-manager.js'); const name = (() => { try { return require('./package.json').name; } catch { return require('path').basename(process.cwd()); } })(); const elo = g.getGlobalELO(name); const ranks = g.getProjectRankings(); console.log(JSON.stringify({ elo, ranks, name }));" 2>/dev/null
-   ```
-
-2. If the result returns `elo: null` or the command fails: display "No global metrics yet" and skip.
-
-3. If global ELO data exists, display:
-   ```
-   Global ELO: {elo} (rank #{position} of {total} projects)
-   ```
-   Where position is the 1-based index of the current project in the rankings array.
-
-4. If 2+ projects have global rollup data, display the top 5 rankings:
-   ```
-   ## Cross-Project Rankings (Top 5)
-   | Rank | Project          | ELO    | Latest Milestone |
-   |------|------------------|--------|------------------|
-   | 1    | {project}        | {elo}  | {milestone}      |
-   ```
-
-$ARGUMENTS
-
-## Auto-Clear
-
-All work is committed to project files. Execute `/clear` to free the context window for the next command.
+# GSD-T: Status — Cross-Domain Progress View
+
+You are checking the current state of the project across all domains.
+
+## Launch via Subagent
+
+To keep the main conversation context lean, run status via a Task subagent.
+
+**If you are the orchestrating agent** (you received the slash command directly):
+Spawn a fresh subagent using the Task tool:
+```
+subagent_type: general-purpose
+model: haiku
+prompt: "You are running gsd-t-status. Working directory: {current project root}
+Read .gsd-t/progress.md and execute the full status report workflow."
+```
+Wait for the subagent to complete. Relay its output to the user. **Do not read files yourself.**
+
+**If you are the spawned subagent** (your prompt says "running gsd-t-status"):
+Continue below.
+
+## Read These Files
+
+1. `.gsd-t/progress.md`
+2. `.gsd-t/domains/*/tasks.md` — all domain task lists
+3. `.gsd-t/contracts/integration-points.md` — dependency graph
+
+## Report Format
+
+Present a concise status to the user:
+
+```
+📊 GSD-T Status: {milestone name}
+Phase: {PARTITIONED | DISCUSSED | PLANNED | EXECUTING | INTEGRATED | VERIFIED}
+
+Domains:
+  {domain-1}: {completed}/{total} tasks {✅ done | 🔄 in progress | ⏳ blocked}
+  {domain-2}: {completed}/{total} tasks {✅ done | 🔄 in progress | ⏳ blocked}
+  {domain-3}: {completed}/{total} tasks {✅ done | 🔄 in progress | ⏳ blocked}
+
+Backlog: {N} items
+  1. {title} ({type})
+  2. {title} ({type})
+  3. {title} ({type})
+
+Next checkpoint: {description} — waiting on {domain} Task {N}
+Next action: {what should happen next}
+
+Recent decisions:
+  - {latest decision from Decision Log}
+```
+
+### Backlog Section
+
+If `.gsd-t/backlog.md` exists, read and parse it. Show total count and top 3 items (position, title, type). If no backlog file exists, skip the Backlog section entirely. If the backlog file exists but is empty (no entries), show `Backlog: No items`.
+
+If there are blockers or issues, highlight them.
+If the user provides $ARGUMENTS, focus the status on that specific domain or aspect.
+
+## Token Usage Breakdown
+
+If `.gsd-t/token-log.md` exists, read it and append a token breakdown to the status report.
+
+Parse each row in the table. Handle both old format (9 columns) and extended format (12 columns with Domain, Task, Ctx%). Rows with missing or empty Domain column are assigned domain "(untagged)".
+
+### Token Usage by Domain
+Group rows by Domain. For each domain, sum Tokens and collect all Ctx% values (ignoring "N/A" and empty). Display:
+
+```
+## Token Usage by Domain
+| Domain         | Tokens | Subagents | Peak Ctx% |
+|----------------|--------|-----------|-----------|
+| auth           | 12,400 | 4         | 14%       |
+| notifications  | 45,200 | 3         | 52% ⚠️    |
+| (untagged)     | 8,100  | 6         | N/A       |
+```
+
+Flag any domain where Peak Ctx% >= 70 with `⚠️` suffix.
+
+### Token Usage by Phase/Command
+Group rows by Command. For each command, sum Tokens and count subagent rows. Display:
+
+```
+## Token Usage by Command
+| Command       | Tokens | Subagents |
+|---------------|--------|-----------|
+| gsd-t-execute | 86,200 | 14        |
+| gsd-t-wave    | 12,400 | 9         |
+| gsd-t-plan    | 3,400  | 1         |
+```
+
+If token-log.md does not exist or is empty, skip this section entirely (no error).
+
+## Process Health
+
+If `.gsd-t/metrics/rollup.jsonl` exists, read the latest entry and append to the status report:
+
+```
+Process Health:
+  ELO: {elo_after} ({elo_delta > 0 ? '↑' : '↓'} {elo_delta})
+  Quality: {first_pass_rate * 100}% first-pass rate | {total_fix_cycles} fix cycles
+```
+
+If `.gsd-t/metrics/task-metrics.jsonl` exists but no rollup.jsonl, compute first_pass_rate directly from task-metrics for the current milestone and display:
+
+```
+Process Health:
+  Quality: {rate}% first-pass rate (current milestone, no rollup yet)
+```
+
+If neither file exists, skip this section entirely.
+
+## Graph Status
+
+If `.gsd-t/graph/meta.json` exists, read it and append to the status report:
+```
+Graph: {entityCount} entities indexed — last indexed {lastIndexed timestamp}
+```
+If the graph does not exist, skip this section.
+
+## Harness Health (M31 — if available)
+
+If `bin/component-registry.js` exists, check for flagged components:
+
+Run via Bash:
+`node -e "const cr = require('./bin/component-registry.js'); const flagged = cr.getFlaggedComponents('.'); if(flagged.length) { flagged.forEach(c => console.log('⚠️  FLAGGED: ' + c.name + ' — ' + c.reason)); } else { console.log('No flagged components'); }" 2>/dev/null`
+
+If flagged components exist, display them in the report:
+```
+Flagged Components:
+  ⚠️  {component-name} — {reason}
+```
+
+If `bin/qa-calibrator.js` exists and `.gsd-t/metrics/qa-miss-log.jsonl` exists, display QA miss-rate summary:
+
+Run via Bash:
+`node -e "const qc = require('./bin/qa-calibrator.js'); const s = qc.getMissRateSummary('.'); if(s) process.stdout.write(JSON.stringify(s));" 2>/dev/null`
+
+If data returned, display:
+```
+QA Calibration:
+  Miss rate: {miss_rate}% | Weak spots: {weak_spot_count} | Top category: {top_category}
+```
+
+If neither file exists, skip this section entirely.
+
+## Version Check
+
+After displaying the project status, check for GSD-T updates:
+
+1. Read `~/.claude/.gsd-t-version` to get the installed version
+2. Read `~/.claude/.gsd-t-update-check` (JSON with `latest` and `timestamp` fields) to get the latest known version
+3. If the file doesn't exist or is unreadable, run `gsd-t status` (CLI) in the background to trigger a cache refresh, and skip the notice
+4. If `latest` is newer than the installed version, append to the report:
+
+```
+⬆️  GSD-T update available: {installed} → {latest}
+   Run: npm update -g @tekyzinc/gsd-t && gsd-t update-all
+```
+
+5. If versions match, skip — don't show anything
+
+## Global ELO & Cross-Project Rankings
+
+After the Process Health section, check for global metrics:
+
+1. Run via Bash:
+   ```bash
+   node -e "const g = require('./bin/global-sync-manager.js'); const name = (() => { try { return require('./package.json').name; } catch { return require('path').basename(process.cwd()); } })(); const elo = g.getGlobalELO(name); const ranks = g.getProjectRankings(); console.log(JSON.stringify({ elo, ranks, name }));" 2>/dev/null
+   ```
+
+2. If the result returns `elo: null` or the command fails: display "No global metrics yet" and skip.
+
+3. If global ELO data exists, display:
+   ```
+   Global ELO: {elo} (rank #{position} of {total} projects)
+   ```
+   Where position is the 1-based index of the current project in the rankings array.
+
+4. If 2+ projects have global rollup data, display the top 5 rankings:
+   ```
+   ## Cross-Project Rankings (Top 5)
+   | Rank | Project          | ELO    | Latest Milestone |
+   |------|------------------|--------|------------------|
+   | 1    | {project}        | {elo}  | {milestone}      |
+   ```
+
+$ARGUMENTS
+
+## Auto-Clear
+
+All work is committed to project files. Execute `/clear` to free the context window for the next command.