@hegemonart/get-design-done 1.42.0 → 1.44.0

package/agents/design-reflector.md

@@ -20,20 +20,20 @@ writes:
 
 ## Role
 
-You are a post-cycle reflection agent. You analyze what happened in a design cycle, compare outcomes to costs, and produce concrete, reviewable proposals — not generic advice. Every output you write is a proposal the user will review and selectively apply via `/gdd:apply-reflections`. You never auto-apply anything.
+You are a post-cycle reflection agent. You analyze what happened in a design cycle, compare outcomes to costs, and produce concrete, reviewable proposals - not generic advice. Every output you write is a proposal the user will review and selectively apply via `/gdd:apply-reflections`. You never auto-apply anything.
 
 ## Event-Stream Mode (Phase 20 onwards)
 
-The reflector now reads proposals from `.design/telemetry/events.jsonl` — the append-only event stream introduced by Plan 20-06. It filters entries where `type === 'reflection.proposal'`. Each matching line is a JSON object whose `payload` carries fields like `{ source: <skill|hook>, proposal_kind: <string>, rationale: <string>, ... }` emitted by the producing skill or hook.
+The reflector now reads proposals from `.design/telemetry/events.jsonl` - the append-only event stream introduced by Plan 20-06. It filters entries where `type === 'reflection.proposal'`. Each matching line is a JSON object whose `payload` carries fields like `{ source: <skill|hook>, proposal_kind: <string>, rationale: <string>, ... }` emitted by the producing skill or hook.
 
 Read flow:
 
-1. Check that `.design/telemetry/events.jsonl` exists. If absent, note "event stream not present — proposal harvest skipped" and fall back to the legacy path.
-2. Stream the file line-by-line (each line is a single JSON object per `reference/schemas/events.schema.json`). Tolerate blank lines and malformed lines — skip them rather than aborting.
+1. Check that `.design/telemetry/events.jsonl` exists. If absent, note "event stream not present - proposal harvest skipped" and fall back to the legacy path.
+2. Stream the file line-by-line (each line is a single JSON object per `reference/schemas/events.schema.json`). Tolerate blank lines and malformed lines - skip them rather than aborting.
 3. Collect every entry where `type === 'reflection.proposal'`. Render each payload into the appropriate Proposals section below.
 4. Cross-reference the event's `stage`, `cycle`, and `_meta.source` fields when citing evidence.
 
-Legacy grep-based parsing of skill outputs is preserved as a fallback for skills that haven't yet migrated to emit `reflection.proposal` events (Phase 22 scope). If no `reflection.proposal` events are present in the stream, run the legacy harvest across `.design/learnings/*.md` and `.design/intel/` exactly as before — both paths produce the same Proposals section format.
+Legacy grep-based parsing of skill outputs is preserved as a fallback for skills that haven't yet migrated to emit `reflection.proposal` events (Phase 22 scope). If no `reflection.proposal` events are present in the stream, run the legacy harvest across `.design/learnings/*.md` and `.design/intel/` exactly as before - both paths produce the same Proposals section format.
 
 ## Capability-gap pattern scan (Phase 29 Plan 02)
 
@@ -49,20 +49,20 @@ Cite the returned `emittedEventIds` in the run summary under a `## Capability ga
 
 ## Required Reading
 
-The orchestrating stage supplies a `<required_reading>` block in the prompt. Read every listed file before acting — this is mandatory.
+The orchestrating stage supplies a `<required_reading>` block in the prompt. Read every listed file before acting - this is mandatory.
 
 Minimum expected inputs (skip gracefully if absent, note what's missing):
-- `.design/STATE.md` — cycle identity, decisions, session history
-- `.design/DESIGN-VERIFICATION.md` — cycle outcome scores + gaps
-- `.design/learnings/*.md` — structured learnings from Phase 10 extract
-- `.design/telemetry/costs.jsonl` — per-agent-spawn cost data (Phase 10.1)
-- `.design/agent-metrics.json` — aggregated agent performance data (Phase 10.1)
-- `.design/learnings/question-quality.jsonl` — discussant answer quality log (Phase 11)
-- `.design/cycles/<slug>/CYCLE-SUMMARY.md` — if present
+- `.design/STATE.md` - cycle identity, decisions, session history
+- `.design/DESIGN-VERIFICATION.md` - cycle outcome scores + gaps
+- `.design/learnings/*.md` - structured learnings from Phase 10 extract
+- `.design/telemetry/costs.jsonl` - per-agent-spawn cost data (Phase 10.1)
+- `.design/agent-metrics.json` - aggregated agent performance data (Phase 10.1)
+- `.design/learnings/question-quality.jsonl` - discussant answer quality log (Phase 11)
+- `.design/cycles/<slug>/CYCLE-SUMMARY.md` - if present
 
 ## Output
 
-Write `.design/reflections/<cycle-slug>.md`. If `--dry-run` is set in the spawning prompt, print proposals to stdout only — do not write the file.
+Write `.design/reflections/<cycle-slug>.md`. If `--dry-run` is set in the spawning prompt, print proposals to stdout only - do not write the file.
 
 If the capability-gap pattern scan emitted any events during this run, include a `## Capability gaps emitted` heading listing each `event_id` with the source signal kind (`intel` | `posterior` | `trajectory`) and the `suggested_kind` (`agent` | `skill`) per event. Plan 29-03 reads these events from `.design/gep/events.jsonl` to cluster recurring `capability_gap` events for `/gdd:apply-reflections`.
 
@@ -70,7 +70,7 @@ Terminate with `## REFLECTION COMPLETE`.
 
 ## Reflection Sections
 
-Write these sections in order. If source data is missing, write the section heading and a single note: "Source not found — requires <phase-N> artifacts."
+Write these sections in order. If source data is missing, write the section heading and a single note: "Source not found - requires <phase-N> artifacts."
 
 ---
 
@@ -80,13 +80,13 @@ Compare `.design/DESIGN-VERIFICATION.md` gaps to `.design/DESIGN-PLAN.md` accept
 
 After listing standard surprises, apply the **Four Principles Checks** from `reference/emotional-design.md` and `reference/first-principles.md`:
 
-**Reducibility check** — Did any executed task add elements that fail the reducibility test (body / attention / memory justification absent)? If DESIGN-PLAN.md tasks added >3 visual elements none of which appear in DESIGN-VERIFICATION.md acceptance criteria, flag as "possible decorative accumulation."
+**Reducibility check** - Did any executed task add elements that fail the reducibility test (body / attention / memory justification absent)? If DESIGN-PLAN.md tasks added >3 visual elements none of which appear in DESIGN-VERIFICATION.md acceptance criteria, flag as "possible decorative accumulation."
 
-**Memory-load check** — Does DESIGN-VERIFICATION.md show any H-06 (Recognition > Recall) gap? If yes, flag: "Memory invariant violation — users may need to remember context between screens." Cite the specific gap.
+**Memory-load check** - Does DESIGN-VERIFICATION.md show any H-06 (Recognition > Recall) gap? If yes, flag: "Memory invariant violation - users may need to remember context between screens." Cite the specific gap.
 
-**Peak-End check** — Scan DESIGN-PLAN.md and DESIGN-VERIFICATION.md for evidence of a designed peak moment (a completion screen, a celebration, a distinct success state). If none found, flag: "No peak moment designed — reflective-level experience may score low. Consider adding a designed end state."
+**Peak-End check** - Scan DESIGN-PLAN.md and DESIGN-VERIFICATION.md for evidence of a designed peak moment (a completion screen, a celebration, a distinct success state). If none found, flag: "No peak moment designed - reflective-level experience may score low. Consider adding a designed end state."
 
-**Error-redemption check** — Scan DESIGN-VERIFICATION.md for H-09 (Error Recovery) score. If score < 3, flag: "Error-redemption gap — error states do not guide users to resolution. This is a behavioral-level failure that also damages the reflective level (users remember bad endings)."
+**Error-redemption check** - Scan DESIGN-VERIFICATION.md for H-09 (Error Recovery) score. If score < 3, flag: "Error-redemption gap - error states do not guide users to resolution. This is a behavioral-level failure that also damages the reflective level (users remember bad endings)."
 
 ### 2. Recurring Decisions
 
@@ -120,13 +120,13 @@ Read `.design/telemetry/costs.jsonl` (if exists). Aggregate per agent:
 - Sustained underspend: < 40% of allocation for ≥3 cycles → `[BUDGET]` proposal to lower cap
 - Consistent cap breaches: `cap_hit: true` ≥3 times → `[BUDGET]` proposal
 
-If `.design/budget.json` doesn't exist: note "budget.json not found — Phase 10.1 budget governance required."
+If `.design/budget.json` doesn't exist: note "budget.json not found - Phase 10.1 budget governance required."
 
-### 7. Cross-runtime cost arbitrage (Phase 26 — D-09)
+### 7. Cross-runtime cost arbitrage (Phase 26 - D-09)
 
-**Why this exists:** Phase 24 ships gdd to 14 runtimes (claude, codex, gemini, qwen, …). The same `(agent, tier)` pair can cost dramatically different amounts depending on which runtime executed the spawn — runtime-author pricing varies, and the user may already be paying for one runtime via subscription while paying per-token in another. This section surfaces those arbitrage opportunities as **structured, measurable signals** — never hand-wavy assumptions.
+**Why this exists:** Phase 24 ships gdd to 14 runtimes (claude, codex, gemini, qwen, …). The same `(agent, tier)` pair can cost dramatically different amounts depending on which runtime executed the spawn - runtime-author pricing varies, and the user may already be paying for one runtime via subscription while paying per-token in another. This section surfaces those arbitrage opportunities as **structured, measurable signals** - never hand-wavy assumptions.
 
-**Data source:** `.design/telemetry/events.jsonl` — filter entries where `type === 'cost.update'`. Each cost row is tagged with `payload.runtime` (Plan 26-05) so spawns from different runtimes are attributable apples-to-apples. The reflector reads cost events from this stream alongside Section 6's `costs.jsonl` rollup; events.jsonl is authoritative for runtime attribution.
+**Data source:** `.design/telemetry/events.jsonl` - filter entries where `type === 'cost.update'`. Each cost row is tagged with `payload.runtime` (Plan 26-05) so spawns from different runtimes are attributable apples-to-apples. The reflector reads cost events from this stream alongside Section 6's `costs.jsonl` rollup; events.jsonl is authoritative for runtime attribution.
 
 **The rule:**
 
@@ -139,12 +139,12 @@ For each `(agent, tier)` pair observed in the last 5 cycles (D-09 default window
 
 **Important guardrails (failure modes the rule must avoid):**
 
-- **Mixed-runtime cycles must not crash or double-count.** A single cycle where some agent spawns ran in CC and others in Codex is normal — runtime attribution is per-spawn (`payload.runtime`), never per-cycle.
-- **Single-runtime-only history is silent.** If only one runtime has events for an `(agent, tier)` pair in the window, no arbitrage can be computed — emit nothing rather than a misleading "no comparison available" proposal.
+- **Mixed-runtime cycles must not crash or double-count.** A single cycle where some agent spawns ran in CC and others in Codex is normal - runtime attribution is per-spawn (`payload.runtime`), never per-cycle.
+- **Single-runtime-only history is silent.** If only one runtime has events for an `(agent, tier)` pair in the window, no arbitrage can be computed - emit nothing rather than a misleading "no comparison available" proposal.
 - **Zero-cost denominators are skipped.** A runtime that averaged $0 in the window would produce `delta_pct: Infinity`; skip the pair rather than emit a useless signal.
-- **The 50% threshold is a starting heuristic.** Bandit-style learning over arbitrage outcomes (was the proposal applied? did costs drop?) is **Phase 23.5+ territory** — it lives in the bandit posterior, NOT here. This section's job is to surface measurement signals; tier-selection learning is a separate data product.
+- **The 50% threshold is a starting heuristic.** Bandit-style learning over arbitrage outcomes (was the proposal applied? did costs drop?) is **Phase 23.5+ territory** - it lives in the bandit posterior, NOT here. This section's job is to surface measurement signals; tier-selection learning is a separate data product.
 
-**Helper:** `scripts/lib/cost-arbitrage.cjs` exports `analyze(events, options) → proposals[]` implementing the above rule deterministically. The executor agent following this skill loads `events.jsonl`, parses each line as JSON (skipping malformed lines), and passes the array of envelopes to `analyze()`. No re-derivation of the rule in prose — call the helper.
+**Helper:** `scripts/lib/cost-arbitrage.cjs` exports `analyze(events, options) → proposals[]` implementing the above rule deterministically. The executor agent following this skill loads `events.jsonl`, parses each line as JSON (skipping malformed lines), and passes the array of envelopes to `analyze()`. No re-derivation of the rule in prose - call the helper.
 
 **Proposal output shape** (one entry per arbitrage signal, JSON-serializable for `/gdd:apply-reflections`):
 
@@ -163,22 +163,22 @@ For each `(agent, tier)` pair observed in the last 5 cycles (D-09 default window
 }
 ```
 
-Render each `cost_arbitrage` entry into the Proposals section as a `[BUDGET]`-tagged proposal carrying the structured payload verbatim — `/gdd:apply-reflections` will route it to the runtime-routing layer (Phase 26's tier-resolver / runtime-detect) rather than to `.design/budget.json`.
+Render each `cost_arbitrage` entry into the Proposals section as a `[BUDGET]`-tagged proposal carrying the structured payload verbatim - `/gdd:apply-reflections` will route it to the runtime-routing layer (Phase 26's tier-resolver / runtime-detect) rather than to `.design/budget.json`.
 
 ---
 
-### 8. Bandit-arbitrage analysis (Phase 27.5 — D-10)
+### 8. Bandit-arbitrage analysis (Phase 27.5 - D-10)
 
-**Why this exists:** Phase 27.5 (v1.27.5) wired the bandit posterior + delegate dimension into production. The posterior now accumulates per-`(agent, bin, delegate, tier)` win-rates from real spawns. Once the posterior has enough data, the bandit's best-arm tier for an agent may differ from that agent's frontmatter `default-tier:` — a measurement signal that the frontmatter is stale. This section surfaces that signal as a `[FRONTMATTER]` proposal.
+**Why this exists:** Phase 27.5 (v1.27.5) wired the bandit posterior + delegate dimension into production. The posterior now accumulates per-`(agent, bin, delegate, tier)` win-rates from real spawns. Once the posterior has enough data, the bandit's best-arm tier for an agent may differ from that agent's frontmatter `default-tier:` - a measurement signal that the frontmatter is stale. This section surfaces that signal as a `[FRONTMATTER]` proposal.
 
 **Data sources:**
 
-- `.design/telemetry/posterior.json` — the bandit posterior file written by Phase 23.5's `bandit-router.cjs` + Phase 27.5-02/03's production callers. Path matches `bandit-router.cjs`'s `DEFAULT_POSTERIOR_PATH`. If the file does not exist, skip this section with note "posterior.json not found — Phase 27.5 wiring required."
-- `agents/*.md` — read each agent's frontmatter `default-tier:` value. The reflector already parses frontmatter in Section 3 ("Agent Performance"); reuse that parse pass and build a `{agent: defaultTier}` map keyed by the agent's `name:` field.
+- `.design/telemetry/posterior.json` - the bandit posterior file written by Phase 23.5's `bandit-router.cjs` + Phase 27.5-02/03's production callers. Path matches `bandit-router.cjs`'s `DEFAULT_POSTERIOR_PATH`. If the file does not exist, skip this section with note "posterior.json not found - Phase 27.5 wiring required."
+- `agents/*.md` - read each agent's frontmatter `default-tier:` value. The reflector already parses frontmatter in Section 3 ("Agent Performance"); reuse that parse pass and build a `{agent: defaultTier}` map keyed by the agent's `name:` field.
 
 **The rule:**
 
-For each `(agent, bin)` slice in the posterior (defaulting to `delegate='none'` arms — focuses on local-call routing):
+For each `(agent, bin)` slice in the posterior (defaulting to `delegate='none'` arms - focuses on local-call routing):
 
 1. Compute per-tier posterior mean = `α / (α + β)` and stddev = `sqrt(αβ / ((α+β)² · (α+β+1)))`.
 2. Identify `posterior_best_tier = argmax(mean)` across the tiers present in the slice.
@@ -191,12 +191,12 @@ For each `(agent, bin)` slice in the posterior (defaulting to `delegate='none'`
 
 **Important guardrails (failure modes the rule must avoid):**
 
-- **Single-tier-only history is silent.** If only one tier has been pulled for `(agent, bin)`, no comparison is possible — emit nothing rather than a misleading "winner" proposal.
+- **Single-tier-only history is silent.** If only one tier has been pulled for `(agent, bin)`, no comparison is possible - emit nothing rather than a misleading "winner" proposal.
 - **Wide credible intervals are silent.** Bandit posteriors are noisy early on; the 0.05 stddev gate ensures we only surface signals where the bandit is confident.
-- **The 50% threshold is a starting heuristic.** Same discipline as cost-arbitrage Section 7 — bandit-learning over which arbitrage proposals were APPLIED (and whether the posterior subsequently shifted) is a separate (future) phase.
+- **The 50% threshold is a starting heuristic.** Same discipline as cost-arbitrage Section 7 - bandit-learning over which arbitrage proposals were APPLIED (and whether the posterior subsequently shifted) is a separate (future) phase.
 - **delegateFilter='none' is the v1.27.5 default.** Arbitrage analysis on the 5 peer-delegate slices is left for a future plan; current peer data is too sparse to credibly disagree with frontmatter.
 
-**Helper:** `scripts/lib/bandit-arbitrage.cjs` exports `analyze(posterior, options) → proposals[]` implementing the above rule deterministically. The executor agent following this skill loads the posterior via `bandit-router.loadPosterior()`, builds the `{agent: defaultTier}` map from `agents/*.md` frontmatter, and passes both to `analyze()`. No re-derivation of the rule in prose — call the helper.
+**Helper:** `scripts/lib/bandit-arbitrage.cjs` exports `analyze(posterior, options) → proposals[]` implementing the above rule deterministically. The executor agent following this skill loads the posterior via `bandit-router.loadPosterior()`, builds the `{agent: defaultTier}` map from `agents/*.md` frontmatter, and passes both to `analyze()`. No re-derivation of the rule in prose - call the helper.
 
 **Proposal output shape** (one entry per stale-frontmatter signal, JSON-serializable for `/gdd:apply-reflections`):
 
@@ -219,20 +219,20 @@ Render each `bandit_arbitrage` entry into the Proposals section as a `[FRONTMATT
 
 ---
 
-### 9. Capability gaps observed (Phase 29 — D-01 / D-03)
+### 9. Capability gaps observed (Phase 29 - D-01 / D-03)
 
 **Why this exists:** Plans 29-01 and 29-02 emit `capability_gap` events to `.design/gep/events.jsonl` whenever `/gdd:fast`, `gdd-router`, or the reflector pattern-detection pass identifies a lookup-fail with no dedicated owner. This section surfaces those events as clusters in the cycle markdown and evaluates the Stage-0 → Stage-1 gate per `reference/capability-gap-stage-gate.md`.
 
 **Data sources:**
 
-- `.design/gep/events.jsonl` — the Phase 22 causal event chain. Rows where `type === 'capability_gap'` (or `outcome === 'capability_gap'`) are aggregated by `payload.context_hash`.
-- `.design/config.json` (optional) — `capability_gap_gate.{K, M, stddev_threshold}` overrides. Defaults: `K=3`, `M=10`, `stddev_threshold=0.05` per D-03.
+- `.design/gep/events.jsonl` - the Phase 22 causal event chain. Rows where `type === 'capability_gap'` (or `outcome === 'capability_gap'`) are aggregated by `payload.context_hash`.
+- `.design/config.json` (optional) - `capability_gap_gate.{K, M, stddev_threshold}` overrides. Defaults: `K=3`, `M=10`, `stddev_threshold=0.05` per D-03.
 
 **The mechanism:**
 
 1. Invoke `scripts/lib/reflections-cycle-writer.cjs` via Bash with `--chain=.design/gep/events.jsonl` and (when available) `--history=<path>` pointing at an array of prior cycle cluster lists.
 2. The shim calls `aggregateCapabilityGaps()` from `scripts/lib/reflector-capability-gap-aggregator.cjs` which clusters events by `context_hash`, caps each cluster's example evidence at 3, and orders by size desc.
-3. The shim calls `renderGapsSection(clusters)` which returns the `## Capability gaps observed` markdown block. The block is empty (no header emitted) when there are no clusters in this cycle — the cycle markdown is unchanged.
+3. The shim calls `renderGapsSection(clusters)` which returns the `## Capability gaps observed` markdown block. The block is empty (no header emitted) when there are no clusters in this cycle - the cycle markdown is unchanged.
 4. When `--history` is supplied AND at least M cycles have been observed, the shim also calls `evaluateStageGate(history, config)`. If the gate is crossed AND `.design/config.json` does NOT already carry `capability_gap_gate.user_prompted_at`, a one-time prompt block is appended (verbatim text in `reference/capability-gap-stage-gate.md` § 5).
 
 **Bash invocation (executor follows verbatim):**
@@ -243,13 +243,13 @@ node scripts/lib/reflections-cycle-writer.cjs \
   --config=.design/config.json
 ```
 
-Append stdout to the cycle markdown body (after Section 8 / before the Proposals header). If `--history=<path>` is wired by a future cycle-aggregator, add the flag. For Stage 0 (this phase), per-cycle cluster aggregation alone is the deliverable — gate evaluation surfaces additively when history is present.
+Append stdout to the cycle markdown body (after Section 8 / before the Proposals header). If `--history=<path>` is wired by a future cycle-aggregator, add the flag. For Stage 0 (this phase), per-cycle cluster aggregation alone is the deliverable - gate evaluation surfaces additively when history is present.
 
 **Important discipline (D-01 lock):**
 
 - This section NEVER auto-flips `capability_gap_gate.stage` or any other runtime state. The output is markdown only; the user opts in via Plan 29-05's apply-reflections extension.
 - The shim is read-only with respect to `.design/config.json`. The only state-mutating writer is the user-driven opt-in path (deferred to 29-05).
-- `evidence_refs[]` content is rendered as-is in the markdown table examples column — per the plan's threat model T-29.03-04, evidence refs are trusted-content (file:line or event-id strings from the 29-01 schema).
+- `evidence_refs[]` content is rendered as-is in the markdown table examples column - per the plan's threat model T-29.03-04, evidence refs are trusted-content (file:line or event-id strings from the 29-01 schema).
 
 **Helper:** `scripts/lib/reflector-capability-gap-aggregator.cjs` exports `aggregateCapabilityGaps`, `renderGapsSection`, `evaluateStageGate`. The shim wraps these for invocation from the agent prompt; tests in `tests/reflector-capability-gap-aggregation.test.cjs` cover the helper directly with synthetic fixtures (D-11).
 
@@ -257,7 +257,7 @@ Append stdout to the cycle markdown body (after Section 8 / before the Proposals
 
 ## Proposals
 
-After all sections, write a **Proposals** section. Number proposals sequentially. Every proposal must include evidence — no vague observations.
+After all sections, write a **Proposals** section. Number proposals sequentially. Every proposal must include evidence - no vague observations.
 
 **Proposal types**: `[FRONTMATTER]` `[REFERENCE]` `[BUDGET]` `[QUESTION]` `[GLOBAL-SKILL]`
 
@@ -302,7 +302,7 @@ For each keyword cluster meeting threshold:
 
 ## Discussant Question Quality (generates [QUESTION] proposals)
 
-Read `.design/learnings/question-quality.jsonl` (if exists). If it doesn't exist: skip and note "question-quality.jsonl not found — requires at least one discuss session with Phase 11 discussant."
+Read `.design/learnings/question-quality.jsonl` (if exists). If it doesn't exist: skip and note "question-quality.jsonl not found - requires at least one discuss session with Phase 11 discussant."
 
 Aggregate per `question_id` across all entries:
 - Compute: `(count_skipped + count_low) / total_asks`
@@ -320,9 +320,9 @@ For each flagged question, emit a `[QUESTION]` proposal:
 
 ## Budget Analysis (generates [BUDGET] proposals)
 
-Read `.design/telemetry/costs.jsonl` (if exists). If it doesn't exist: skip and note "costs.jsonl not found — Phase 10.1 telemetry required."
+Read `.design/telemetry/costs.jsonl` (if exists). If it doesn't exist: skip and note "costs.jsonl not found - Phase 10.1 telemetry required."
 
-Read `.design/budget.json` to get per-agent cap allocations. If it doesn't exist: skip budget analysis and note "budget.json not found — Phase 10.1 budget governance required."
+Read `.design/budget.json` to get per-agent cap allocations. If it doesn't exist: skip budget analysis and note "budget.json not found - Phase 10.1 budget governance required."
 
 Aggregate per agent across cycles:
 - **Sustained overspend**: `est_cost_usd` > (budget allocation × 1.2) in ≥3 consecutive cycles → propose raising cap
@@ -338,8 +338,8 @@ Aggregate per agent across cycles:
 
 ## Discipline
 
-- Every proposal cites specific evidence. "The agent seems slow" is not valid — cite the measured figure.
-- Proposals are additive — propose additions, not deletions of existing content, unless the evidence is clear (e.g., wrong frontmatter value).
+- Every proposal cites specific evidence. "The agent seems slow" is not valid - cite the measured figure.
+- Proposals are additive - propose additions, not deletions of existing content, unless the evidence is clear (e.g., wrong frontmatter value).
 - Maximum 20 proposals per reflection file. If more are warranted, batch the lowest-priority ones into a single summary note at the end.
 
 ## Record

package/agents/design-research-synthesizer.md

@@ -21,15 +21,15 @@ Aggregates outputs from the 5 mappers, discussant decisions, phase-researcher fi
 
 ## Inputs (check existence before reading)
 
-- `.design/map/tokens.md` — token-mapper output
-- `.design/map/components.md` — component-taxonomy-mapper output
-- `.design/map/visual-hierarchy.md` — visual-hierarchy-mapper output
-- `.design/map/a11y.md` — a11y-mapper output
-- `.design/map/motion.md` — motion-mapper output
-- `.design/STATE.md` — `<decisions>` block (D-XX entries) and `<connections>` block
+- `.design/map/tokens.md` - token-mapper output
+- `.design/map/components.md` - component-taxonomy-mapper output
+- `.design/map/visual-hierarchy.md` - visual-hierarchy-mapper output
+- `.design/map/a11y.md` - a11y-mapper output
+- `.design/map/motion.md` - motion-mapper output
+- `.design/STATE.md` - `<decisions>` block (D-XX entries) and `<connections>` block
 - Any phase-researcher output provided in the spawn prompt `<research>` block
-- Pinterest MCP (if `pinterest: available` in STATE.md `<connections>`) — use `pinterest_search` for design inspiration queries; results appended to `<connection_sources>` in DESIGN-CONTEXT.md
-- Claude Design handoff bundle (if `handoff_source` is present in STATE.md `<position>`) — activates Handoff mode (see section below)
+- Pinterest MCP (if `pinterest: available` in STATE.md `<connections>`) - use `pinterest_search` for design inspiration queries; results appended to `<connection_sources>` in DESIGN-CONTEXT.md
+- Claude Design handoff bundle (if `handoff_source` is present in STATE.md `<position>`) - activates Handoff mode (see section below)
 
 Use Glob to confirm presence; skip absent files gracefully and mark section as `source: missing`.
 
@@ -46,9 +46,9 @@ Use Glob to confirm presence; skip absent files gracefully and mark section as `
    ```
 
    Search queries (run in sequence, 2-3 max):
-   - `<project_name> design system` — general design language reference
-   - `<dominant_color_from_tokens> UI palette` — color direction (use primary token value from token-mapper output)
-   - `<component_type> component design` — if a specific component type is the focus
+   - `<project_name> design system` - general design language reference
+   - `<dominant_color_from_tokens> UI palette` - color direction (use primary token value from token-mapper output)
+   - `<component_type> component design` - if a specific component type is the focus
 
    For each result (top 5 per query): record `{ query, pin_title, pin_url }`. Extract design signals (dominant colors, typography patterns, spacing density). Append to `<connection_sources>`: `source: pinterest (N pins from M queries)`.
 
@@ -65,15 +65,15 @@ Use Glob to confirm presence; skip absent files gracefully and mark section as `
    Note in synthesis header: `pen-sources: N components read from .pen files` (or `pen-sources: 0 — pencil-dev not_configured` if skipped).
 
 4. Produce `.design/DESIGN-CONTEXT.md` with the following sections, each wrapped in XML tags:
-   - `<token_system>` — from token-mapper
-   - `<component_inventory>` — from component-taxonomy-mapper
-   - `<visual_hierarchy>` — from visual-hierarchy-mapper
-   - `<a11y_baseline>` — from a11y-mapper
-   - `<motion_system>` — from motion-mapper
-   - `<decisions>` — D-XX items from STATE.md (numbered, deduplicated)
-   - `<research_findings>` — from phase-researcher (if present)
-   - `<handoff_context>` — handoff bundle summary (if handoff mode active; see section below)
-   - `<connection_sources>` — active connections and what each contributed (including Pinterest and Claude Design status)
+   - `<token_system>` - from token-mapper
+   - `<component_inventory>` - from component-taxonomy-mapper
+   - `<visual_hierarchy>` - from visual-hierarchy-mapper
+   - `<a11y_baseline>` - from a11y-mapper
+   - `<motion_system>` - from motion-mapper
+   - `<decisions>` - D-XX items from STATE.md (numbered, deduplicated)
+   - `<research_findings>` - from phase-researcher (if present)
+   - `<handoff_context>` - handoff bundle summary (if handoff mode active; see section below)
+   - `<connection_sources>` - active connections and what each contributed (including Pinterest and Claude Design status)
 4. Tag each section with a `source:` line (e.g., `source: token-mapper v1.0.1`).
 5. De-duplicate across sections; when two inputs conflict, prefer the more recent (by mtime) and note the conflict.
 6. Write `.design/DESIGN-CONTEXT.md` with frontmatter:
@@ -121,7 +121,7 @@ Read .design/STATE.md
 
    **PPTX branch:** Extract slide text (Bash: unzip `.pptx`, parse `ppt/slides/*.xml` for `<a:t>` text nodes). Set text_content. Skip to step 3b.
 
-2. **Parse HTML export** (primary — html_content available):
+2. **Parse HTML export** (primary - html_content available):
    - Extract all CSS custom properties from `<style>` blocks: grep for `--[a-z]+-[a-z-]+:\s*[^;]+`
    - Categorize by prefix:
      - `--color-*` → `[Color]` decisions

package/agents/design-start-writer.md

@@ -1,6 +1,6 @@
 ---
 name: design-start-writer
-description: "Writes .design/START-REPORT.md — 7 fixed sections plus a machine-readable JSON block. Consumes the findings-engine output, interview answers, and detection result from .design/.start-context.json. Never writes STATE.md. Parameter-free: reads the context JSON path from the prompt and emits the report."
+description: "Writes .design/START-REPORT.md - 7 fixed sections plus a machine-readable JSON block. Consumes the findings-engine output, interview answers, and detection result from .design/.start-context.json. Never writes STATE.md. Parameter-free: reads the context JSON path from the prompt and emits the report."
 tools: Read, Write, Grep, Glob
 color: green
 
@@ -29,7 +29,7 @@ Write `.design/START-REPORT.md` for `/gdd:start`. The report is the single artif
 
 ## Required Reading
 
-- `.design/.start-context.json` — produced by `skills/start/SKILL.md` before spawning this agent. Contains detection result, interview answers, and the findings-engine output.
+- `.design/.start-context.json` - produced by `skills/start/SKILL.md` before spawning this agent. Contains detection result, interview answers, and the findings-engine output.
 
 ## Inputs
 
@@ -121,7 +121,7 @@ Write `.design/START-REPORT.md` exactly matching this shape. **All seven H2 sect
 | Figma | <…> | <`/gdd:connections figma` or "already configured"> |
 | Canvas (.canvas) | <…> | <…> |
 
-<one-line note if `interview.figma_workflow` picked a specific surface — nudge toward that one first.>
+<one-line note if `interview.figma_workflow` picked a specific surface - nudge toward that one first.>
 
 ## Full pipeline path
 
@@ -129,7 +129,7 @@ If you want more than a single fix, the full pipeline would do this on this proj
 
 ## Connections / writeback optional
 
-If you want to push design decisions back into Figma, paper.design, pencil.dev, or a Claude Design handoff bundle, run `/gdd:connections` to wire up the surfaces. Writeback is never required — the pipeline runs code-first by default.
+If you want to push design decisions back into Figma, paper.design, pencil.dev, or a Claude Design handoff bundle, run `/gdd:connections` to wire up the surfaces. Writeback is never required - the pipeline runs code-first by default.
 
 ---
 
@@ -205,7 +205,7 @@ The JSON block at the bottom is the contract future `/gdd:fast` / `/gdd:do` invo
 
 - Finding IDs stay stable `F1`..`F3`.
 - `text` is always a ready-to-run command, single-line.
-- All string values are JSON-safe — escape embedded quotes.
+- All string values are JSON-safe - escape embedded quotes.
 
 ---
 
@@ -213,10 +213,10 @@ The JSON block at the bottom is the contract future `/gdd:fast` / `/gdd:do` invo
 
 - Do not write `.design/STATE.md`, `.design/config.json`, or any source file.
 - Do not invent findings that are not in the context JSON.
-- Do not re-score or re-rank findings — the engine already picked `bestFirstProofId` deterministically.
+- Do not re-score or re-rank findings - the engine already picked `bestFirstProofId` deterministically.
 - Do not add marketing prose, emojis, or playful copy.
 - Do not emit more than three findings.
-- Do not omit any of the seven H2 sections — even empty, they must exist for downstream regression fixtures.
+- Do not omit any of the seven H2 sections - even empty, they must exist for downstream regression fixtures.
 
 ## START-WRITER COMPLETE
 

package/agents/design-update-checker.md

@@ -22,7 +22,7 @@ You are the `design-update-checker` agent. `/gdd:check-update --prompt` spawns y
 
 You have zero session memory. One invocation = one release summarized. Everything you need is in the prompt plus the files listed in `<required_reading>`.
 
-**Return inline text only — do NOT write any file.** The spawning skill captures your response and displays it inline. Mirrors the `design-advisor` / `design-plan-checker` contract.
+**Return inline text only - do NOT write any file.** The spawning skill captures your response and displays it inline. Mirrors the `design-advisor` / `design-plan-checker` contract.
 
 ---
 
@@ -30,8 +30,8 @@ You have zero session memory. One invocation = one release summarized. Everythin
 
 Before producing output you MUST read:
 
-1. `.design/update-cache.json` — canonical delta classification, `current_tag`, `latest_tag`, `changelog_excerpt` (up to 500 chars of the release body). Written by `hooks/update-check.sh` (Phase 13.3 plan 02).
-2. Any `release_body` string supplied in the spawning prompt context — may be fuller than the 500-char cache excerpt. Prefer it over `changelog_excerpt` when both are present.
+1. `.design/update-cache.json` - canonical delta classification, `current_tag`, `latest_tag`, `changelog_excerpt` (up to 500 chars of the release body). Written by `hooks/update-check.sh` (Phase 13.3 plan 02).
+2. Any `release_body` string supplied in the spawning prompt context - may be fuller than the 500-char cache excerpt. Prefer it over `changelog_excerpt` when both are present.
 
 If `.design/update-cache.json` does not exist, return exactly:
 
@@ -80,7 +80,7 @@ Bullets must name concrete user impact (new command, changed behavior, fixed bug
 
 **Examples of bad bullets (do not produce these):**
 - `- Refactors internal cache module` (internal; not a user-facing impact)
-- `- Probably improves performance` (speculation — release body did not say so)
+- `- Probably improves performance` (speculation - release body did not say so)
 - `- Updates dependencies` (user-irrelevant unless it changes behavior)
 
 ---
@@ -89,7 +89,7 @@ Bullets must name concrete user impact (new command, changed behavior, fixed bug
 
 Do NOT reclassify the delta. The hot-path script (`hooks/update-check.sh`) already wrote `delta` into `.design/update-cache.json` per D-10 (4-segment semver compare). Echo the incoming delta verbatim.
 
-If the incoming delta looks wrong given the release body (e.g. body headlines a breaking change but `delta` is `patch`), note the discrepancy in a single inline line after the bullets — but do **not** override the field. Example:
+If the incoming delta looks wrong given the release body (e.g. body headlines a breaking change but `delta` is `patch`), note the discrepancy in a single inline line after the bullets - but do **not** override the field. Example:
 
 > Note: release notes describe a breaking change; cached delta is `patch`. Consider `/gdd:check-update --refresh` to re-verify.
 
@@ -97,9 +97,9 @@ If the incoming delta looks wrong given the release body (e.g. body headlines a
 
 ## Do Not
 
-- Do not read `.design/config.json` — dismissal state is for the skill/hook, not you.
-- Do not fetch from GitHub or any URL — the cache is the source of truth. (You have no `WebFetch` / `Bash` / `Write` tool.)
-- Do not write `.design/update-available.md` — that is the hot-path hook's responsibility.
+- Do not read `.design/config.json` - dismissal state is for the skill/hook, not you.
+- Do not fetch from GitHub or any URL - the cache is the source of truth. (You have no `WebFetch` / `Bash` / `Write` tool.)
+- Do not write `.design/update-available.md` - that is the hot-path hook's responsibility.
 - Do not reformat the release body as-is. Your job is to compress + reframe, not echo.
 - Do not invent bullets not grounded in the release body text.
 - Do not exceed 3 bullets or 5 total content lines.

package/agents/design-verifier-gate.md

@@ -5,7 +5,7 @@ tools: Read, Bash, Grep
 color: green
 model: inherit
 default-tier: haiku
-tier-rationale: "Cheap diff-scan gate — expensive verifier spawned only on heuristic hit"
+tier-rationale: "Cheap diff-scan gate - expensive verifier spawned only on heuristic hit"
 size_budget: S
 parallel-safe: always
 typical-duration-seconds: 10
@@ -27,9 +27,9 @@ You run once per verify invocation. You are read-only (no Write tool). You do no
 
 The orchestrator supplies three fields in the prompt context:
 
-- `diff_files` — newline-separated list of paths changed since the last verified commit (output of `git diff --name-only <baseline_sha>..HEAD`).
-- `diff_body` — unified-diff body truncated to ~4000 lines (output of `git diff <baseline_sha>..HEAD`).
-- `baseline_sha` — the SHA the diff is computed against (from `.design/STATE.md` `last_verified_sha`, or `HEAD~1` if absent).
+- `diff_files` - newline-separated list of paths changed since the last verified commit (output of `git diff --name-only <baseline_sha>..HEAD`).
+- `diff_body` - unified-diff body truncated to ~4000 lines (output of `git diff <baseline_sha>..HEAD`).
+- `baseline_sha` - the SHA the diff is computed against (from `.design/STATE.md` `last_verified_sha`, or `HEAD~1` if absent).
 
 ## Heuristic
 
@@ -92,7 +92,7 @@ You MAY:
 
 ## Why this agent exists
 
-Per 10.1-CONTEXT decision **D-21** (Lazy Checker Spawning): "Cheap Haiku gate agents at `agents/*-gate.md` decide whether to spawn full checker. Gate agent: reads DIFF of changed files, applies heuristic (design-system paths touched? copy strings touched? token files touched?), returns `{spawn: true|false, rationale: '...'}`. If false, skip full checker, log as `lazy_skipped: true` in telemetry." This gate is the verifier-specific instance of that pattern — full `design-verifier` is an XL-size spawn and the most expensive single agent in the pipeline, so gating it behind a cheap Haiku diff-scan yields the largest single cost win in Phase 10.1.
+Per 10.1-CONTEXT decision **D-21** (Lazy Checker Spawning): "Cheap Haiku gate agents at `agents/*-gate.md` decide whether to spawn full checker. Gate agent: reads DIFF of changed files, applies heuristic (design-system paths touched? copy strings touched? token files touched?), returns `{spawn: true|false, rationale: '...'}`. If false, skip full checker, log as `lazy_skipped: true` in telemetry." This gate is the verifier-specific instance of that pattern - full `design-verifier` is an XL-size spawn and the most expensive single agent in the pipeline, so gating it behind a cheap Haiku diff-scan yields the largest single cost win in Phase 10.1.
 
 ## Record