@hegemonart/get-design-done 1.57.2 → 1.58.0

package/dist/claude-code/.claude/skills/start/start-procedure.md

@@ -1,115 +0,0 @@
----
-name: start-procedure
-type: heuristic
-version: 1.0.0
-phase: 28.5
-tags: [start, first-run, proof-path, scan, writer-agent, handoff]
-last_updated: 2026-05-18
----
-
-# Start Skill - Full Procedure
-
-Extracted from `skills/start/SKILL.md` per Phase 28.5 D-10 (extract-then-link, never delete
-content). The skill keeps its arguments table, step headings, and non-goals; the per-step
-operational detail (interview JSON shape, scan invocation, writer spawn payload, handoff
-template) lives here so the SKILL stays under the 100-line cap.
-
-The companion file `./start-interview.md` (Phase 27 ship) holds the 5-question copy,
-defaults, and validation rules. This file documents what `/gdd:start` does WITH the answers.
-
-## Step 0 - Dismiss-only shortcut
-
-If invoked with `--dismiss-nudge`:
-
-1. `touch ~/.claude/gdd-nudge-dismissed` (Windows: equivalent). Ignore errors silently.
-2. Print exactly: `Nudge dismissed. Delete ~/.claude/gdd-nudge-dismissed to re-enable.`
-3. Exit with `## START COMPLETE` marker.
-
-Do not proceed to any other step.
-
-## Step 1 - Detect UI root
-
-Run the detector:
-
-```bash
-node "${CLAUDE_PLUGIN_ROOT}/scripts/lib/detect-ui-root.cjs" "$(pwd)"
-```
-
-Capture the JSON output. Branches:
-
-- `kind: "backend-only"` → print the frontend-only diagnostic below, write nothing, exit with `## START COMPLETE`. The diagnostic copy is:
-  > `/gdd:start` is for frontend codebases. This repo looks backend-only (detected `<framework>`). The plugin can still help with design references and component libraries imported by your clients - but there is no UI surface here to scan. Exiting without creating `.design/`.
-- `kind: null` (no package.json, no UI dir) → print a short "Nothing recognizable here - point me at a frontend repo and try again." and exit.
-- Any other `kind` → proceed with `detected.path` as the scan root.
-
-## Step 2 - Run the 5-question interview
-
-Read `./start-interview.md` for the exact question copy, defaults, and validation rules.
-
-If `--skip-interview`, skip this step and use the defaults documented in that file.
-
-Otherwise, ask the five questions in order using `AskUserQuestion`:
-
-1. Pain point (text, required, single-line cap 120 chars)
-2. Target area confirmation (detected path)
-3. Budget / latency preference (enum: fast / balanced / thorough)
-4. Framework + design-system confirmation (from detection)
-5. Figma / canvas workflow (enum: figma / canvas / neither / skip)
-
-Any early exit at Q1 → abort with a one-line pointer to `/gdd:scan`.
-
-Store the answers + detection result in `.design/.start-context.json`:
-
-```json
-{
-  "schema_version": "1.0",
-  "detected": { "kind": "...", "path": "...", "framework": "...", "design_system": "...", "confidence": 0.85 },
-  "interview": { "pain": "...", "target_area": "...", "budget": "balanced", "framework_confirmed": true, "design_system_confirmed": true, "figma_workflow": "skip" },
-  "generated_at": "<ISO-8601>"
-}
-```
-
-`.design/` is created here for the first time. `.design/STATE.md` is NOT written.
-
-## Step 3 - Scan findings
-
-Run the findings engine:
-
-```bash
-node "${CLAUDE_PLUGIN_ROOT}/scripts/lib/start-findings-engine.cjs" \
-  --root "<detected.path>" \
-  --budget "<budget>" \
-  --pain "<pain_point>"
-```
-
-Capture the JSON. The output carries at most three findings, each with stable IDs `F1`..`F3`, plus `bestFirstProofId` (may be null).
-
-Append the engine output to `.design/.start-context.json` under a `scan` key.
-
-## Step 4 - Spawn the writer
-
-Dispatch `Task` with:
-
-- `subagent_type: design-start-writer`
-- `description: "Write .design/START-REPORT.md"`
-- `prompt:` a short instruction pointing the agent at `.design/.start-context.json` and asking it to emit the report per its Output contract. Include a reminder that it must produce exactly 7 H2 sections plus the JSON block, and must not write `STATE.md`.
-
-Wait for the agent to complete. The agent writes `.design/START-REPORT.md`.
-
-## Step 5 - Print the handoff
-
-Read the final line of `.design/START-REPORT.md` to capture the suggested command.
-
-Print exactly (one line, no emoji):
-
-```
-Report written to .design/START-REPORT.md. Next: run <suggested_command> to see the first proof.
-```
-
-If `bestFirstProofId` was null, the suggested command is `/gdd:brief` (the default fallback).
-
-Emit `## START COMPLETE` and exit.
-
-## Failure handling
-
-Every error path exits with `## START COMPLETE` and a one-line pointer. Do not half-write files: if the writer agent fails, keep `.design/.start-context.json` and tell the user they can rerun. Do not delete `.design/` unless it was empty before the run.

package/dist/claude-code/.claude/skills/state/SKILL.md

@@ -1,106 +0,0 @@
----
-name: gdd-state
-description: "Query, recover, or roll back the Phase 57 SQLite state backbone. Use when you need to inspect the decisions/blockers/plans tables with a raw SELECT, rebuild a corrupt state.sqlite from the markdown STATE.md, or revert to the markdown-only source of truth by removing state.sqlite. Activates for requests involving querying the SQLite state database, recovering from SQLite corruption, or reverting the migration (demigrate)."
-argument-hint: "<query \"<sql>\" | recover | demigrate>"
-user-invocable: true
-tools: Read, Bash, Grep, Glob
----
-
-# /gdd:state
-
-The Phase 57 SQLite state backbone is opt-in (`--migrate-state`) and fully reversible.
-Markdown `.design/STATE.md` is always the human-editable SoT; SQLite is a faster query
-layer derived from it. This skill exposes three subcommands for operating on that layer.
-
-## Subcommands
-
-| Subcommand | What it does |
-|---|---|
-| `/gdd:state query "<sql>"` | Run a read-only SELECT against `.design/state.sqlite`. |
-| `/gdd:state recover` | Rotate the current sqlite to a `.bak` and rebuild from markdown. |
-| `/gdd:state demigrate` | Remove `.design/state.sqlite`; markdown becomes the SoT again. |
-
----
-
-## query
-
-Execute a read-only SELECT against the state database.
-
-The engine opens the file with `readonly:true` so all writes are rejected at the
-engine level. A first-token denylist (Set membership, no regex) additionally blocks
-DROP, DELETE, UPDATE, INSERT, ALTER, ATTACH, CREATE, PRAGMA, VACUUM, ANALYZE,
-REINDEX, and REPLACE before the connection is opened.
-
-```bash
-node -e '
-  const qs = require("./scripts/lib/state/query-surface.cjs");
-  const result = qs.query(process.argv[1], { projectRoot: process.cwd() });
-  console.log(JSON.stringify(result, null, 2));
-' "<sql>"
-```
-
-Outputs `{ rows: [...], backend: "sqlite" }` on success, or
-`{ degraded: true, message: "..." }` when SQLite is not active.
-
-Degrades gracefully (no throw) when `BACKEND==='markdown'` or when
-`.design/state.sqlite` has not been created yet (run `--migrate-state` first).
-
----
-
-## recover
-
-Rotate the current (possibly corrupt) `.design/state.sqlite` to `.bak.0`, then
-rebuild a fresh database from the markdown `.design/STATE.md` using
-`migrate-to-sqlite.cjs` in force mode. Runs `PRAGMA integrity_check` on the
-result and reports the outcome.
-
-```bash
-node -e '
-  const qs = require("./scripts/lib/state/query-surface.cjs");
-  const result = qs.recover({ projectRoot: process.cwd() });
-  console.log(JSON.stringify(result, null, 2));
-'
-```
-
-Outputs `{ recovered: true, integrity: true, message: "..." }` on success.
-
-Backup rotation keeps at most 10 files (`.bak.0` through `.bak.9`). The oldest
-backup is overwritten when the cap is reached.
-
----
-
-## demigrate
-
-Remove `.design/state.sqlite` so the markdown `STATE.md` becomes the SoT again.
-Idempotent: if the file does not exist, returns a clear no-op message without error.
-A backup is taken in `.bak.0` before removal.
-
-```bash
-node -e '
-  const qs = require("./scripts/lib/state/query-surface.cjs");
-  const result = qs.demigrate({ projectRoot: process.cwd() });
-  console.log(JSON.stringify(result, null, 2));
-'
-```
-
-Outputs `{ demigrated: true, message: "..." }` when the file was removed, or
-`{ demigrated: false, message: "..." }` when it was already absent (no-op).
-
-To re-enable SQLite after a demigrate, run `--migrate-state` again.
-
----
-
-## Key design decisions
-
-- **Markdown is always the SoT.** SQLite is opt-in via `--migrate-state` and
-  reversible via `demigrate`. The markdown file is never silently overwritten.
-- **Read-only queries only.** The `query` subcommand enforces SELECT-only via both
-  the engine (`readonly:true`) and a defense-in-depth denylist. No writes
-  are possible through this skill.
-- **Backup rotation cap.** `rotateBak` shifts `.bak.0..8` up by one index and caps
-  at `.bak.9` (10 files total). The oldest backup is overwritten automatically.
-- **Graceful degradation.** All subcommands return a clear `{ degraded, message }`
-  object (no throw) when `better-sqlite3` is not installed or when
-  `GDD_STATE_BACKEND=markdown` is set.
-
-## STATE COMPLETE

package/dist/claude-code/.claude/skills/stats/SKILL.md

@@ -1,51 +0,0 @@
----
-name: gdd-stats
-description: "Cycle stats - decisions made, tasks completed, commits, timeline, git metrics."
-tools: Read, Bash
-disable-model-invocation: true
----
-
-# /gdd:stats
-
-**Role:** Print cycle metrics.
-
-## Step 1 - Read state
-
-Read `.design/STATE.md`. Extract:
-- `cycle:` and `started_at` (or per-cycle start date if present in CYCLES.md)
-- D-XX count under `<decisions>`
-
-## Step 2 - Collect git metrics
-
-Let `<since>` = cycle start date (fallback to STATE.md `started_at`).
-
-```bash
-git log --oneline --since="<since>" | wc -l          # commits
-git diff --stat HEAD~N HEAD                          # files changed since cycle start
-```
-
-If git unavailable, print `git: unavailable` and skip git metrics.
-
-## Step 3 - Count todos
-
-Read `.design/TODO.md` if present:
-- pending: count `- [ ]`
-- in-progress: count `- [-]`
-- done: count `- [x]`
-- group pending by P0/P1/P2/P3 section
-
-## Step 4 - Output
-
-```
-━━━ Cycle stats ━━━
-Cycle: cycle-1   Started: 2026-04-18
-Decisions made: 12 (D-01..D-12)
-Tasks completed: 8 / 10
-Git commits:     23
-Files changed:   47
-Open todos:      3 (P0: 1, P1: 2, P2: 0, P3: 0)
-Agents spawned:  — (no task log)
-━━━━━━━━━━━━━━━━━━
-```
-
-## STATS COMPLETE

package/dist/claude-code/.claude/skills/style/SKILL.md

@@ -1,71 +0,0 @@
----
-name: gdd-style
-description: "Generate a component handoff doc at `.design/DESIGN-STYLE-<ComponentName>.md` by dispatching the `design-doc-writer` agent in one of two modes: post-pipeline (uses `DESIGN-SUMMARY.md`) or pre-pipeline fallback (uses `DESIGN.md` + source). Use when the user wants a single-component spec covering tokens, states, and AI-slop detection. Invoke with a ComponentName, or with no argument to list available components."
-argument-hint: "[ComponentName]"
-user-invocable: true
----
-
-# gdd-style - Component Handoff Doc Generator
-
-Generates a per-component style spec at `.design/DESIGN-STYLE-[ComponentName].md`. This is a **standalone command**, not a pipeline stage.
-
-For the full mode-detection logic, source-resolution fallback chain (10 paths), agent-spawn payload, and STYL-05 section spec, see `./style-doc-procedure.md`. For the cross-skill output discipline (artifact prefix, completion marker, MUST-NOT-write list), see `../../reference/shared-preamble.md#output-contract-reminders`. For the raw-hex audit signal used in Token Semantic Health Score, see `../../reference/shared-preamble.md#token-first-reasoning`.
-
-Output artifact naming: `.design/DESIGN-STYLE-[ComponentName].md` - Title-cased component name, one file per invocation.
-
----
-
-## Scope
-
-This command is **additive and non-destructive**:
-
-- It is NOT a pipeline stage - no `.design/STATE.md` read or write contract.
-- Output lives in the `DESIGN-STYLE-*.md` namespace - distinct from the pipeline namespace (`DESIGN.md`, `DESIGN-CONTEXT.md`, `DESIGN-PLAN.md`, `DESIGN-SUMMARY.md`, `DESIGN-VERIFICATION.md`).
-- It does not modify any pipeline artifact.
-- It does not invoke the pipeline router.
-- One doc per invocation - no batch mode in v3.
-
-This separation is a pre-roadmap decision recorded in `.planning/STATE.md`: utility commands use distinct prefixes (`DESIGN-STYLE-[Component].md`); the pipeline owns the `DESIGN-*.md` namespace without qualifiers.
-
----
-
-## Workflow
-
-1. **Argument check** - if `$ARGUMENTS` is empty, enter list mode (see `./style-doc-procedure.md#component-source-resolution`); display available components from `src/components/` + `.design/tasks/`, then exit.
-2. **Mode detect** - `DESIGN-SUMMARY.md` exists → post-pipeline; else `DESIGN.md` exists → pre-pipeline; else abort with a "run /get-design-done scan first" message. Full decision tree at `./style-doc-procedure.md#mode-detection`.
-3. **Source resolve** - search the 10-path fallback chain for a file matching the ComponentName. On zero matches: abort. On multiple matches: prompt the user to disambiguate.
-4. **Agent spawn** - dispatch `design-doc-writer` with the mode-specific `<required_reading>` block and the STYL-05 section list. The full Task payload + STYL-05 spec live in `./style-doc-procedure.md#agent-spawn-payload`.
-5. **Confirm + report** - after the agent emits `## DOC COMPLETE`, verify the output path exists and report success.
-
----
-
-## Constraints
-
-This command MUST NOT (per `../../reference/shared-preamble.md#output-contract-reminders`):
-
-- Write to `DESIGN.md`, `DESIGN-SUMMARY.md`, `DESIGN-VERIFICATION.md`, `DESIGN-CONTEXT.md`, or `.design/STATE.md`
-- Invoke the pipeline router (this command is a leaf invocation, not a pipeline stage)
-- Require Figma or Refero MCPs - v3 uses only local source files and `.design/` artifacts (MCP enrichment is reserved for a future version)
-- Produce more than one output file per invocation - no batch mode in v3
-
----
-
-## Examples
-
-**Example 1: Named component**
-
-```
-/get-design-done style Button
-```
-
-Resolves `src/components/Button.tsx`, detects post-pipeline mode (DESIGN-SUMMARY.md exists), spawns `design-doc-writer` with `pipeline_complete: true`, writes `.design/DESIGN-STYLE-Button.md`.
-
-**Example 2: No argument (list mode)**
-
-```
-/get-design-done style
-```
-
-Globs component files and prompts the user to specify a ComponentName. Exits without generating any file. See `./style-doc-procedure.md#component-source-resolution` for the full glob path list.
-
-## STYLE COMPLETE

package/dist/claude-code/.claude/skills/style/style-doc-procedure.md

@@ -1,150 +0,0 @@
----
-name: style-doc-procedure
-type: meta-rules
-version: 1.0.0
-phase: 28.5
-tags: [style, handoff, component-spec, doc-writer, procedure, extracted]
-last_updated: 2026-05-18
----
-
-Source: extracted from `skills/style/SKILL.md` (Phase 28.5 rework - D-10 extract-then-link).
-The skill's essential routing + mode-detection stays in `../skills/style/SKILL.md`; this file
-holds the agent-spawn payload, source-resolution paths, and the per-section spec the
-`design-doc-writer` agent produces. See `./shared-preamble.md#output-contract-reminders` for
-the cross-skill output discipline.
-
-# Style Doc Procedure
-
-Detailed procedure for the `gdd-style` standalone command - companion to
-`../skills/style/SKILL.md`. Read this file when executing the agent-spawn step (Step 4 in the
-skill) or when wiring the source-resolution fallback chain. The SKILL.md keeps the essential
-mode detection + decision tree; this file holds the deep methodology.
-
----
-
-## Mode Detection
-
-```
-If .design/DESIGN-SUMMARY.md exists:
-  mode = post-pipeline   (STYL-03)
-  pipeline_complete = true
-
-Elif .design/DESIGN.md exists:
-  mode = pre-pipeline    (STYL-04)
-  pipeline_complete = false
-
-Else:
-  Abort: "No .design/ artifacts found. Run /get-design-done scan first to initialize."
-```
-
-The mode controls which files are supplied to the agent in `<required_reading>`.
-
----
-
-## Component Source Resolution
-
-Search for a source file matching the provided ComponentName (case-insensitive):
-
-1. `src/components/[ComponentName].tsx`
-2. `src/components/[ComponentName].jsx`
-3. `src/components/[ComponentName].vue`
-4. `src/components/[ComponentName].svelte`
-5. `src/**/[ComponentName]/index.tsx`
-6. `src/**/[ComponentName]/index.jsx`
-7. `components/[ComponentName].tsx`
-8. `components/[ComponentName].jsx`
-9. `components/[ComponentName].vue`
-10. `components/[ComponentName].svelte`
-
-**If multiple matches found:** Present the list to the user and prompt them to specify the exact path. Do not proceed until a single file is selected.
-
-**If zero matches found:** Abort with: "Component [ComponentName] not found in expected paths. Verify the name matches a file in src/components/ or components/."
-
-When `$ARGUMENTS` is empty, the skill enters **list mode** - glob the same source roots, also list task names from `.design/tasks/*.md` (if directory exists), display the list, and prompt the user to specify a ComponentName. Exit without generating any file.
-
----
-
-## Agent Spawn Payload
-
-Once mode and source path are resolved, spawn the `design-doc-writer` agent:
-
-```
-Task("design-doc-writer", """
-<required_reading>
-[If pipeline_complete=true:]
-@.design/STATE.md
-@.design/DESIGN-SUMMARY.md
-@.design/DESIGN-CONTEXT.md
-@<component_source_path>
-[Else (pipeline_complete=false):]
-@.design/DESIGN.md
-@<component_source_path>
-@reference/anti-patterns.md
-@reference/audit-scoring.md
-</required_reading>
-
-Generate a handoff spec for component <ComponentName>.
-
-Context:
-  component_name: <ComponentName>
-  component_source_path: <resolved absolute path>
-  pipeline_complete: <true|false>
-  output_path: .design/DESIGN-STYLE-<ComponentName>.md
-
-Produce the doc per STYL-05 sections:
-  - Spacing Tokens (used by component)
-  - Color Tokens (used by component)
-  - Typography Scale (used by component)
-  - Component States (default, hover, focus, active, disabled, etc.)
-  - Token Semantic Health Score (raw-hex-ratio formula — see ./shared-preamble.md#token-first-reasoning)
-  - AI-Slop Detection (using ./anti-patterns.md BAN/SLOP patterns)
-  [If pipeline_complete=true:]
-  - Decisions Applied (D-XX from DESIGN-SUMMARY.md that mention this component)
-
-Emit ## DOC COMPLETE when the output file is written.
-""")
-```
-
-After the agent emits `## DOC COMPLETE`, confirm the file exists at `output_path` and report success to the user.
-
----
-
-## STYL-05 Section Spec
-
-Each generated `.design/DESIGN-STYLE-[ComponentName].md` SHOULD contain (in this order):
-
-1. **Spacing Tokens** - every spacing token the component uses (paddings, gaps, margins). Cross-reference `./composition.md` for the 4 px / 8 px modular scale discipline.
-2. **Color Tokens** - every color token the component uses (background, foreground, border, focus ring, state-overlays). Cross-reference `./palette-catalog.md` for naming convention and `./shared-preamble.md#token-first-reasoning` for the raw-hex audit threshold.
-3. **Typography Scale** - type ramps the component reaches into (label, body, code, etc.) with size + line-height + weight. Cross-reference `./typography.md`.
-4. **Component States** - default, hover, focus, active, disabled, loading, error. Each row: token diff vs default.
-5. **Token Semantic Health Score** - raw-hex ratio = `raw_hex_count / total_color_uses`. Healthy < 5 %.
-6. **AI-Slop Detection** - apply `./anti-patterns.md` `BAN-*` and `SLOP-*` patterns to the component source. List violations.
-7. **Decisions Applied** (post-pipeline only) - D-XX entries from `DESIGN-SUMMARY.md` that name or describe this component.
-
----
-
-## Examples
-
-**Example 1: Named component**
-
-```
-/get-design-done style Button
-```
-
-- Resolves component: `src/components/Button.tsx`
-- Detects mode: DESIGN-SUMMARY.md exists → post-pipeline
-- Spawns `design-doc-writer` with `pipeline_complete: true`
-- Output: `.design/DESIGN-STYLE-Button.md`
-
-**Example 2: No argument (list mode)**
-
-```
-/get-design-done style
-```
-
-- Globs component files from `src/components/`
-- Displays available components and exits without generating any file.
-
----
-
-*Imported by: `../skills/style/SKILL.md`. Maintained as part of Phase 28.5 (Bucket 2 rework).*

package/dist/claude-code/.claude/skills/synthesize/SKILL.md

@@ -1,94 +0,0 @@
----
-name: synthesize
-description: "Streaming synthesizer - collapses N parallel-agent markdown outputs into one compact merged summary via a single Haiku 4.5 call. Invoked inline by orchestrators (skills/map/, skills/discover/, skills/plan/) after parallel spawns return. Not user-invocable."
-tools: Read, Task
-user-invocable: false
-disable-model-invocation: true
----
-
-@reference/shared-preamble.md
-
-# synthesize
-
-## Role
-
-Reusable streaming synthesizer. You receive N markdown strings (parallel-agent outputs) plus a directive, emit one compact merged output in the format the directive specifies. Inline-invoked - no Task() spawn overhead; thin Haiku 4.5 merge call wrapped in a skill.
-
-You are not an orchestrator, not an auditor, not a second-pass reviewer. You preserve every distinct signal from the inputs, consolidate duplicates with source tags, and return a single merged artifact. The invoking orchestrator writes the result to disk; you do not touch the filesystem.
-
-## When to use
-
-**Use synthesize when:**
-- Parallel-mapper / parallel-researcher produced N overlapping outputs and main-context doesn't need them verbatim.
-- The downstream consumer wants one cross-cutting summary (e.g., `.design/DESIGN-PATTERNS.md` merged from 5 per-concern mappers).
-- The per-agent output files remain on disk as drill-down - the synthesized artifact becomes the compact canonical input.
-
-**Do NOT use synthesize when:**
-- A single-agent flow produced the output (nothing to merge).
-- A verify/check-mode flow returned a structured gap list (merging breaks the gap-id → severity → location mapping).
-- A downstream consumer needs every byte verbatim for grep (e.g., decision-wiring checker that matches exact D-XX anchors).
-
-## Input Contract
-
-The invoking orchestrator passes three fields:
-
-- `outputs: string[]` - N labeled strings, each pre-labeled with `=== from <agent-name> ===\n<content>` so the merge call can trace per-signal provenance.
-- `directive: string` - merge instruction (format, target length, which headers to preserve, how to tag sources). Default when empty: `"produce a single merged summary preserving all distinct signals, grouped by natural section headers"`.
-- `output_shape: "markdown" | "json"` - controls the output format. Defaults to `"markdown"`.
-
-## Implementation
-
-Single Haiku 4.5 call with this exact merge-prompt template:
-
-```
-You have received {N} outputs from parallel agents. Each output is labeled with its source.
-
-Directive: {directive}
-
-Outputs:
-{each labeled with === from <agent-name> === and its full content}
-
-Produce the merged result in the format specified by the directive.
-Preserve every distinct signal — do NOT drop content. Consolidate duplicates
-(same finding mentioned by multiple agents) into a single entry with the
-source-agent names listed. Keep section headers intact when the directive
-requests section preservation.
-
-Emit ONLY the merged output — no preamble, no meta-commentary.
-```
-
-Tier is hard-coded to `haiku` per D-14. Orchestrators should **not** re-route this to Sonnet - the merge is structure-preserving, not generative, and Haiku handles it without quality loss.
-
-## Output Contract
-
-- **Markdown shape (`output_shape: "markdown"`)** → emit the merged markdown inline, then `## SYNTHESIS COMPLETE` on its own final line. No code fence wrapping the merged output.
-- **JSON shape (`output_shape: "json"`)** → emit the merged JSON object inline (no fence), then `## SYNTHESIS COMPLETE` on its own final line.
-
-The orchestrator is responsible for:
-- Stripping the `## SYNTHESIS COMPLETE` marker before writing to the target file.
-- Persisting the merged artifact to disk (e.g., `.design/DESIGN-PATTERNS.md`).
-- Keeping per-agent files on disk as drill-down evidence.
-
-## Cost and Tier
-
-Hard-coded to Haiku 4.5 per D-14. `budget.json.tier_overrides.synthesize` can override. Typical cost per invocation: $0.002–$0.02 - dominated by input tokens (5 × ~1500-line mapper outputs ≈ 7.5k input tokens, merge output ≈ 1k output tokens).
-
-## Failure Modes
-
-- **Empty `outputs: []`** → emit an empty string followed immediately by `## SYNTHESIS COMPLETE`. Do NOT error - the orchestrator handles the empty case (e.g., `--only <name>` in map skipped the parallel dispatch).
-- **Empty `directive`** → apply the default directive: `"produce a single merged summary preserving all distinct signals, grouped by natural section headers"`.
-- **Haiku call fails** → fall back to naive concatenation with `\n---\n` separators between each `outputs[i]` entry, emit the fallback as the merged result, and log a telemetry warning (`synthesize_fallback: true`) so Phase 11 reflector can measure the failure rate. Always emit `## SYNTHESIS COMPLETE` after the fallback body.
-- **`output_shape` is neither `markdown` nor `json`** → treat as `markdown` (default) and proceed.
-
-## Non-Goals
-
-- Does **NOT** spawn Task() agents. Synthesize is a thin skill, not an orchestrator.
-- Does **NOT** write files. The invoking orchestrator owns the target path.
-- Does **NOT** validate directive semantics. If the directive is nonsensical, the merge output will reflect that - garbage in, garbage out is acceptable for an internal-use skill.
-- Does **NOT** re-rank or re-score the inputs. Preservation is the contract.
-
-## Completion Marker
-
-```
-## SYNTHESIS COMPLETE
-```

package/dist/claude-code/.claude/skills/timeline/SKILL.md

@@ -1,66 +0,0 @@
----
-name: gdd-timeline
-description: "Narrative retrospective across cycles: reads EXPERIENCE.md files and git log to produce a timeline view."
-argument-hint: "[<cycle-N> | <from>-<to> | all]"
-tools: Read, Bash, Glob
-disable-model-invocation: true
----
-
-@reference/retrieval-contract.md
-@reference/cycle-handoff-preamble.md
-
-# /gdd:timeline
-
-Generates a narrative retrospective across one or more completed cycles by reading `.design/archive/cycle-N/EXPERIENCE.md` files and correlating with `git log`.
-
-## Steps
-
-1. **Parse argument**: accepted forms:
-   - `cycle-N` or `N` - single cycle
-   - `N-M` - inclusive range
-   - `all` or no argument - all archived cycles
-
-2. **Discover archives**: glob `.design/archive/cycle-*/EXPERIENCE.md`. Sort by cycle number. Filter to requested range.
-
-3. **For each cycle archive**:
-   a. Read `EXPERIENCE.md` - extract sections: Goal, Decisions made, Learnings graduated, What died, Handoff to next cycle.
-   b. Read `DESIGN-SUMMARY.md` (if present) for shipped artifacts list.
-   c. Run:
-      ```bash
-      git log --oneline --after="<cycle start date>" --before="<cycle end date>" -- .design/ 2>/dev/null | head -10
-      ```
-      to correlate with commits. Use dates from `EXPERIENCE.md` Opened/Ended headers if present.
-
-4. **Print timeline** in this shape:
-
-   ```
-   ## Timeline: Cycle 1 → Cycle 3
-
-   ---
-
-   ### Cycle 1 — <goal headline>
-
-   **Opened with**: <first meaningful action>
-   **Key decisions**: <D-XX summary>, <D-XX summary>
-   **Surprises**: <what was unexpected>
-   **What we'd do differently**: <retrospective note>
-   **Shipped**: <artifact list or "see DESIGN-SUMMARY.md">
-
-   ---
-
-   ### Cycle 2 — <goal headline>
-   ...
-   ```
-
-5. **No archives found**: print
-   ```
-   No archived cycles found in .design/archive/.
-   Complete a cycle first with /gdd:complete-cycle.
-   ```
-
-## Do Not
-
-- Do not modify any file.
-- Do not run git commands that write or stage (only `git log` for read).
-
-## TIMELINE COMPLETE