@event4u/agent-config 6.1.0 → 7.0.0

package/dist/agent-src/skills/adr-create/SKILL.md

@@ -145,17 +145,17 @@ the area's contract from the README in
 
 ### 5. Regenerate the index
 
-- **Flat surface** — `python3 scripts/adr/regenerate_index.py
+- **Flat surface** — `./scripts-run src/scripts/adr/regenerate_index
   --dir docs/decisions/` writes `INDEX.md` from `ADR-*.md`.
-- **Per-area surface** — `python3 scripts/audit_adr_coverage.py
+- **Per-area surface** — `./scripts-run src/scripts/audit_adr_coverage
   --regen-area-readme <area>` rewrites `docs/adrs/<area>/README.md`.
-  Coverage gate: run `python3 scripts/audit_adr_coverage.py` (no
+  Coverage gate: run `./scripts-run src/scripts/audit_adr_coverage` (no
   args) — exit 0 only when every canonical area has ≥ 1 ADR.
 
 ### 6. Validate
 
-- Flat: `python3 scripts/adr/regenerate_index.py --check` exits 0.
-- Per-area: `python3 scripts/audit_adr_coverage.py --check` exits 0.
+- Flat: `./scripts-run src/scripts/adr/regenerate_index --check` exits 0.
+- Per-area: `./scripts-run src/scripts/audit_adr_coverage --check` exits 0.
 - Project's CI / quality pipeline passes locally.
 
 ## Output format

package/dist/agent-src/skills/agent-security-review/evals/triggers.json

@@ -1,5 +1,6 @@
 {
     "skill": "agent-security-review",
+    "last_eval": "2026-06-16",
     "description": "5 should-trigger + 5 should-not-trigger queries. Should-trigger covers DE + EN phrasings for adversarial review of an agent's CONFIG/behaviour (rules, skills, MCP, hooks, permissions). Should-not-trigger covers the near-miss neighbours (code threat-model, code security-audit, the static config-audit command, privacy review, dependency CVE scan) whose vocabulary overlaps.",
     "queries": [
         {

package/dist/agent-src/skills/agents-md-thin-root/SKILL.md

@@ -97,7 +97,7 @@ Each answer must fit on one line. The block exists so the root never silently de
 
 ## Procedure — apply Thin-Root to AGENTS.md
 
-1. **Measure baseline.** `wc -c AGENTS.md` and `python3 scripts/measure_augment_budget.py`. Record current char-count and the gap to 2,200 / 2,500.
+1. **Measure baseline.** `wc -c AGENTS.md` and `./scripts-run src/scripts/measure_augment_budget`. Record current char-count and the gap to 2,200 / 2,500.
 2. **Inventory sections.** List every `## ` heading and its char-count. Mark each as `keep-inline` (Iron-Law-adjacent, ≤ 200 chars, no good outboard target) or `outboard-candidate` (longer-form prose, table-only sections, narrative).
 3. **Identify outboard targets.** For each `outboard-candidate`, name the destination — `packages/core/.agent-src.uncondensed/contexts/`, `docs/contracts/`, an existing rule body, an existing skill body. Never invent a new top-level directory.
 4. **Move content; insert pointer.** Cut the section into the target file. Replace it in AGENTS.md with a single substantive pointer per anatomy above. Verify the *why*-clause length.

package/dist/agent-src/skills/ai-council/SKILL.md

@@ -577,7 +577,7 @@ usually lower).
 If `pricing.is_stale(table)` returns true, ask before proceeding:
 
 > Price table is stale (last_updated: YYYY-MM-DD)
-> 1. Refresh now (`python3 scripts/update_prices.py`)
+> 1. Refresh now (`./scripts-run src/scripts/update_prices`)
 > 2. Continue with the stale table
 > 3. Cancel
 

package/dist/agent-src/skills/analysis-autonomous-mode/SKILL.md

@@ -85,7 +85,7 @@ Route to the primary skill. Monitor findings for signals to chain additional ski
 
 Merge all specialist findings into ONE prioritized output:
 
-1. Confirmed root → (with evidence)
+1. Confirmed root causes (with evidence)
 2. Contributing factors
 3. Risks not yet proven but worth checking
 4. Concrete fixes (ordered by priority)
@@ -95,19 +95,11 @@ Never dump isolated observations without synthesis.
 
 ## Procedure: Autonomous investigation loop
 
-When running a broad investigation, repeat until confident:
+Constraint: **attack the biggest unknown first** (not breadth-first). Repeat until confident:
 
-```
-1. Assess current understanding
-2. Identify biggest unknown
-3. Choose specialist skill to fill that gap
-4. Execute analysis
-5. Evaluate result — did it answer the question?
-6. Update mental model
-7. Decide: narrow down or broaden scope?
-8. If confident → synthesize and present
-   If not → loop back to step 2
-```
+1. Route the right specialist skill at the largest gap in your understanding.
+2. Inspect the result against the question; narrow or broaden scope.
+3. Once confident, synthesize and present — otherwise return to step 1.
 
 ## Adaptation rules
 
@@ -162,6 +154,10 @@ When specialist findings conflict:
 
 ## Output format
 
+1. Produce one report covering the five subsections below; no narration outside the report.
+2. Every finding must cite file paths or stack/version evidence; mark unverified items as *Contributing Risks*, not *Confirmed Findings*.
+3. Close with a *Recommended Fix Order*; prioritize by production impact → exploitability → user-facing breakage → effort vs value.
+
 ### Investigation Summary
 - What was analyzed, which skills were used, why
 

package/dist/agent-src/skills/blade-ui/SKILL.md

@@ -102,11 +102,18 @@ not the initial apply — it also emits:
   pre-existing entries on replay. Omit the envelope on apply passes; the
   engine's `_apply_a11y_gate` only fires when a baseline is present.
 - `state.ui_review.preview` — `{render_ok: bool, screenshot_path?,
-  dom_dump_path?, error?, skipped?}`. `render_ok: false` with `error`
-  populated triggers the `preview_render_failed` halt; `render_ok: true`
-  with `screenshot_path` threads the screenshot into the delivery
-  report's `artifacts` list. Browser tooling (Playwright/Cypress/…) is
-  a consumer-project dependency — this package does not ship one.
+  dom_dump_path?, error?, skipped?, skip_reason?}`. **Render evidence is
+  required, not optional** on a review/polish pass: you MUST drive the
+  headless browser (Playwright + axe-core) against the rendered output and
+  write `render_ok`. Omitting it now triggers the `preview_render_required`
+  halt — a render-capable stack can no longer claim success without
+  rendering. `render_ok: false` with `error` populated triggers the
+  `preview_render_failed` halt; `render_ok: true` with `screenshot_path`
+  threads the screenshot into the delivery report's `artifacts` list. The
+  only no-render path is an **explicit, reasoned skip**: set `skipped: true`
+  plus a `skip_reason` (e.g. no Playwright runner in this env). Browser
+  tooling (Playwright/Cypress/…) is a consumer-project dependency — this
+  package does not ship one.
 
 Polish dispatch: when the dispatcher skips `review` because a previous
 review pass already returned `SUCCESS`, this skill MUST itself

package/dist/agent-src/skills/blameless-post-mortem/SKILL.md

@@ -0,0 +1,199 @@
+---
+model_tier: high
+name: blameless-post-mortem
+description: "Use after an incident or outage is resolved — blame-free facilitation, root cause, corrective actions, memory write-back — even for a near-miss. Consumes the incident-commander skeleton."
+source: package
+domain: quality
+personas:
+  - senior-engineer
+  - critical-challenger
+workspaces:
+  - engineering
+packs:
+  - analysis-workbench
+lifecycle: active
+trust:
+  level: professional
+  confidence: medium
+  human_review_required: false
+install:
+  default: false
+  removable: true
+requires_skills:
+  - root-cause-frameworks
+---
+
+# blameless-post-mortem
+
+> Facilitate a blame-free post-mortem after an incident or near-miss.
+> Consumes the `incident-commander` skeleton, derives or fills the root
+> cause, writes the corrective-action plan, and drafts an
+> `incident-learnings` memory candidate. Systems and processes are
+> examined — never individuals.
+
+## When to use
+
+- An incident or outage is resolved and the team needs a structured
+  write-up.
+- A near-miss happened and a post-mortem is being drafted (near-miss
+  mode — same flow, different severity framing).
+- The `incident-commander` hands off a post-mortem skeleton (empty
+  root cause is accepted — do not block on it).
+- German triggers: "Post-mortem", "Nachbesprechung", "was ist
+  schiefgelaufen?", "Vorfallsanalyse".
+
+Do NOT use when:
+
+- The incident is still active — route to
+  [`incident-commander`](../incident-commander/SKILL.md) first.
+- The goal is root-cause analysis only, no write-up needed — route
+  to [`root-cause-frameworks`](../root-cause-frameworks/SKILL.md).
+- The concern is a future risk, not a past event — route to
+  [`risk-officer`](../risk-officer/SKILL.md).
+
+## Procedure
+
+### 1. Consume the incident-commander skeleton
+
+Read the incoming skeleton. Per
+[`docs/contracts/analysis-memory-loop.md § 5`](../../docs/contracts/analysis-memory-loop.md):
+
+- Accept any skeleton, complete or not.
+- Extract: `SEV`, `State`, `Started`, `Timeline`, `Mitigation`,
+  `Root cause` (may be `unknown` or TBD).
+- Do NOT stall or reject on an empty root cause.
+
+If no skeleton is provided, reconstruct from the user's description:
+severity, timeline, impact, mitigation state.
+
+### 2. Derive the root cause (if unresolved)
+
+If root cause is `unknown` or TBD, invoke
+[`root-cause-frameworks`](../root-cause-frameworks/SKILL.md). That
+skill returns ranked candidates with confidence levels — do NOT force
+a verdict. If root cause remains unresolved after the analysis pass,
+mark the post-mortem `status: draft` and continue. A draft post-mortem
+can still produce memory candidates (note the open question in the
+candidate summary).
+
+### 3. Write the blame-free report
+
+Sections in order — no individuals named, systems and processes only:
+
+1. **Summary** — one paragraph, blame-free, what happened and the
+   business impact.
+2. **Timeline** — reference the skeleton timeline; do NOT rebuild it.
+3. **Impact** — users affected, duration, data, revenue, SLA.
+4. **Detection** — how the incident was discovered (monitoring, user
+   report, alert, manual).
+5. **Root cause** — the confirmed or highest-confidence candidate;
+   state confidence level if draft.
+6. **Contributing factors** — conditions that made the root cause
+   possible (tooling gaps, process gaps, system state).
+7. **What went well** — at least one item; omitting this is a smell.
+8. **What went wrong** — process, tooling, signals, communication
+   gaps. No individual blame.
+
+**Near-miss mode:** same sections; set `SEV: near-miss`. Add two
+extra questions after "what went wrong":
+
+- *"What would have made this worse?"*
+- *"Which control caught it — luck or a designed control?"*
+
+### 4. Corrective actions (folded-in phase)
+
+For each identified gap, propose a corrective action. Reuse
+`risk-officer` mitigation framing: owner role, size, residual-risk
+note. Four action types:
+
+| Type | Purpose |
+|---|---|
+| **Immediate** | Stop recurrence now (config fix, kill switch, revert) |
+| **Preventive** | Remove the root cause (architectural or process change) |
+| **Detection** | Catch it sooner next time (alert, dashboard, runbook) |
+| **Process** | Address human/coordination gaps (oncall rotation, docs) |
+
+Each action MUST have:
+
+- **Owner role** (eng, ops, PO, support — never "the team")
+- **Closure criterion** — specific, testable condition marking the
+  action done
+- **Regression signal** — a test, monitor, or alert that proves the
+  fix held
+
+An action without a closure criterion is a wish, not a plan.
+
+### 5. Memory write-back
+
+Per [`docs/contracts/analysis-memory-loop.md § 2`](../../docs/contracts/analysis-memory-loop.md):
+
+1. Run the dedup pre-check — call `find_duplicate(...)` from
+   `scripts.memory_lookup` over the same key-space (incident type,
+   affected paths, decision area).
+2. **Match found** — propose a `frequency` / `supersedes` update to
+   the existing entry; do NOT create a new candidate.
+3. **No match** — draft a REDACTED `incident-learnings` candidate to
+   `/memory propose`:
+   - `type: incident-learnings`
+   - `summary`: one-line pattern (no customer names, no secrets, no
+     project-rooted paths)
+   - `evidence_paths`: ≥ 2 file paths (for admission gate)
+   - `decision_surface`: ≥ 3 decisions this pattern changes (if
+     possible)
+   - `last_validated`: today
+   - `review_after_days`: 90
+   - `applicable_scope`: `project`
+
+4. NEVER auto-promote. The human drives promotion via `/memory
+   promote`. If the candidate fails the admission gate
+   (`check_memory_proposal.py`), surface the gap to the user.
+
+If `retrieve()` returns stale entries in `skipped`, surface them
+explicitly — never silently use stale data.
+
+## Output
+
+The post-mortem produces, in order:
+
+1. **Post-mortem document** — sections 1–8 from step 3; status
+   `final` or `draft` if root cause is unresolved.
+2. **Corrective-action table** — each action with type, owner,
+   closure criterion, regression signal.
+3. **Memory candidate** — the drafted `incident-learnings` JSONL
+   snippet for `/memory propose` (or the frequency-update proposal if
+   a duplicate was found).
+
+## Do NOT
+
+- Do NOT blame individuals — name systems, processes, signals, tooling.
+- Do NOT auto-promote to curated memory — the gate is human-driven.
+- Do NOT skip the dedup pre-check before drafting a memory candidate.
+- Do NOT ship raw PII, customer names, secrets, or project-rooted
+  paths in the memory candidate (redact per the contract).
+- Do NOT reject or stall on an incomplete skeleton — mark `draft` and
+  continue.
+- Do NOT rebuild the timeline from scratch — reference the skeleton's
+  timeline.
+
+## Gotchas
+
+- **Incomplete skeleton** → `status: draft`, not a rejection. Draft
+  post-mortems still produce memory candidates with the open question
+  noted.
+- **Near-miss** → a mode within this skill, not a separate flow.
+  Severity is `near-miss`; the extra two questions apply.
+- **Corrective actions without closure criteria** are non-actionable.
+  Always require a specific, testable done condition.
+- **Stale memory entries** surface in `skipped`, not `results`. Never
+  silently reuse stale data.
+
+## See also
+
+- [`incident-commander`](../incident-commander/SKILL.md) — produces the
+  skeleton this skill consumes; run first during live incidents.
+- [`root-cause-frameworks`](../root-cause-frameworks/SKILL.md) — RCA
+  engine invoked in step 2 when root cause is unresolved.
+- [`risk-officer`](../risk-officer/SKILL.md) — mitigation framing
+  reused for corrective actions (owner, size, residual-risk).
+- [`docs/contracts/analysis-memory-loop.md`](../../docs/contracts/analysis-memory-loop.md)
+  — produce → propose → promote → retrieve contract this skill binds to.

package/dist/agent-src/skills/brand/ATTRIBUTION.md

@@ -0,0 +1,38 @@
+# Attribution — brand corpus + grounding engine
+
+This skill is a second instance of the ADR-061 corpus-grounding layer.
+
+## Grounding engine
+
+The retrieval/decision engine is the shared
+[`corpus-grounding`](../corpus-grounding/SKILL.md) skill — it is **not** forked
+or vendored here. Its provenance and license obligations are recorded once in
+[`design-intelligence/ATTRIBUTION.md`](../design-intelligence/ATTRIBUTION.md)
+(MIT engine port). This skill ships only a manifest + CSVs that plug into it.
+
+## Corpus (`data/*.csv`)
+
+The brand corpus is **original-authored** from public, non-proprietary brand
+frameworks and conventions:
+
+- the 12 brand archetypes (Jung; Mark & Pearson, *The Hero and the Outlaw*) —
+  a public framework, not a vendored dataset;
+- conventional colour-psychology-by-industry associations;
+- well-known messaging frameworks (positioning statement, value-proposition
+  canvas, message house, golden circle, StoryBrand, jobs-to-be-done, etc.) —
+  named methods in the public domain, described in our own words;
+- voice/tone, naming-pattern, logo-style, and archetype→typography rows
+  authored for this package.
+
+No third-party CSV or skill content was copied into these files, so no
+third-party license obligation attaches to the corpus. The framework *names*
+above are referenced as public concepts, not as a source we adapted file
+content from.
+
+## Provenance discipline
+
+The manifest carries `owner: package-maintainer`, `refresh_cadence: quarterly`,
+and `upstream: null` (no upstream repo — original-authored). Refresh re-reviews
+the archetype↔type rows whenever the font-pairings Reference
+(`font-pairings-reference.csv`) refreshes, and revisits colour/cultural caveats
+on the quarterly cadence.

package/dist/agent-src/skills/brand/SKILL.md

@@ -0,0 +1,115 @@
+---
+model_tier: inherit
+name: brand
+description: "Grounded brand decisions from a curated corpus — archetype, voice, naming, colour psychology, logo-style fit, messaging frameworks, archetype→type mapping. Use to ground brand strategy and identity."
+domain: engineering
+personas:
+  - brand-strategist
+workspaces:
+  - engineering
+packs:
+  - brand
+trust:
+  level: professional
+install:
+  removable: true
+execution:
+  type: manual
+---
+
+# brand
+
+> The grounded source for brand decisions — a **second instance of the
+> ADR-061 corpus-grounding layer** ([`corpus-grounding`](../corpus-grounding/SKILL.md)),
+> after [`design-intelligence`](../design-intelligence/SKILL.md). Branding is
+> the layer that *constrains* UI: the corpus grounds brand **strategy** and
+> **identity** decisions (archetype, voice, naming, colour, logo style,
+> messaging, archetype→type filter) as a **constraint set** the human confirms —
+> never the final brand. No forked engine; this plugs into the shared one via a
+> manifest.
+
+Corpus: 7 tabular CSVs under [`data/`](data/) — 12 brand `archetype`s, a
+`voice`-and-tone matrix, `naming` patterns, `color` psychology by industry,
+`logo`-style ↔ industry fit, `messaging` frameworks, and
+`typography`-principles (archetype → pairing-filter Grounding, the layer that
+upgrades [`typography-system`](../typography-system/SKILL.md) stage-2).
+Provenance: [`ATTRIBUTION.md`](ATTRIBUTION.md); manifest:
+[`data/manifest.json`](data/manifest.json).
+
+## When to use
+
+- A brand decision needs grounding: which archetype fits, what voice/tone,
+  how to name, which colour direction, which logo style, which messaging
+  framework, or which type pairing-filter an archetype implies.
+- Before [`brand-strategy`](../brand-strategy/SKILL.md) /
+  [`brand-identity`](../brand-identity/SKILL.md) commit to a direction — those
+  skills consult this corpus first.
+- When `typography-system` needs the brand-aware (archetype → pairing-filter)
+  upgrade — query the `typography` domain here.
+
+## Procedure: consult the brand corpus
+
+1. **Ground or search** (paths resolve skill-relative; works from any cwd):
+
+   ```bash
+   python3 <skills-root>/corpus-grounding/scripts/ground.py search \
+     --manifest <skills-root>/brand/data/manifest.json \
+     "<brand brief: sector + intent + audience>" \
+     [--domain archetype|voice|naming|color|logo|messaging|typography] \
+     [--filter "Archetype Fit=Ruler"] [--json]
+   ```
+
+   `<skills-root>` is `~/.claude/skills/` for Claude Code installs,
+   `src/skills/` inside this repo.
+2. **Read `confidence` + every `evidence_gap` line before trusting any row** —
+   surface them; the human signs off on what the corpus could NOT support.
+3. **Propose grounded options** (archetype + voice + colour + logo + messaging),
+   each cited per corpus row, with alternatives — the human confirms.
+4. The confirmed selections become the **brand token + voice constraint set**
+   that `brand-to-tokens`, `brand-consistency`, and pack-ai-image's brand-asset
+   generation consume.
+
+## Output format
+
+1. Grounded brand candidates per domain (archetype, voice, naming, colour,
+   logo style, messaging, type filter) — each selection cited per corpus row.
+2. The grounded output's `confidence` label + every `evidence_gap` line,
+   verbatim.
+3. Alternatives per domain so the human can swap before confirming.
+
+## Do NOT
+
+- Do NOT let the corpus author final brand copy or names — it supplies
+  constraint sets and patterns; final strings are agent-written and
+  human-confirmed.
+- Do NOT fork the engine — plug in via the manifest (ADR-061 §2).
+- Do NOT override the consumer's existing brand tokens / voice profile with
+  corpus rows — consumer brand is the source of truth; the corpus fills gaps
+  (see [`brand-source-of-truth`](../../rules/brand-source-of-truth.md)).
+- Do NOT hide low confidence — the user signs off on the gaps too.
+
+## Gotchas
+
+- Corpus grounds **pre-action selection** — not mid-task reference and not
+  output validation ([`brand-consistency`](../../rules/brand-consistency.md)
+  owns validation).
+- Keep queries brand-shaped ("luxury law firm rebrand", "playful kids snack
+  brand") — generic words land on the default `archetype` domain.
+- An empty result is a legitimate outcome — surface the evidence gap and
+  proceed on priors; never widen filters to force a hit.
+- BM25 drops tokens ≤2 chars — pad short queries ("B2B", "AI") with companions.
+
+## See also
+
+- [`corpus-grounding`](../corpus-grounding/SKILL.md) — the shared engine + manifest contract.
+- [`brand-strategy`](../brand-strategy/SKILL.md) / [`brand-identity`](../brand-identity/SKILL.md) — the workflow skills that consult this corpus.
+- [`design-intelligence`](../design-intelligence/SKILL.md) — sibling corpus instance (style); brand constrains style.
+- [`typography-system`](../typography-system/SKILL.md) — consumes the `typography` (archetype→filter) domain for its brand-aware stage-2.
+
+## Policies
+
+- Provenance: [`ATTRIBUTION.md`](ATTRIBUTION.md) — original-authored corpus
+  from public brand frameworks; shared engine attributed in
+  [`design-intelligence/ATTRIBUTION.md`](../design-intelligence/ATTRIBUTION.md).
+- Refresh: quarterly per the manifest; re-review archetype↔type rows when the
+  font-pairings Reference refreshes.

package/dist/agent-src/skills/brand/data/archetypes.csv

@@ -0,0 +1,13 @@
+Archetype,Core Desire,Goal,Voice Traits,Messaging Angle,Visual Cues,Color Direction,Typography Filter,Best For,Avoid When
+Innocent,Safety and simple happiness,Be good and be happy,"Optimistic, honest, plain, warm","Purity, simplicity, doing it right","Clean layouts, open space, soft edges","Light pastels, white, sky blue","Rounded humanist sans","Wellness, organics, family, baby","Cynical or edgy markets that read the optimism as naive"
+Sage,Truth and understanding,Use intelligence to understand the world,"Authoritative, measured, evidence-led, calm","Expertise, insight, clarity","Structured grids, editorial restraint","Deep blue, navy, muted neutrals","Transitional or old-style serif with a neutral sans","Research, education, consultancy, journalism","Impulse retail where analysis reads as cold"
+Explorer,Freedom and discovery,"Experience a more authentic, fuller life","Adventurous, rugged, candid, independent","Discovery, autonomy, the open road","Wide landscapes, motion, texture","Earthy tones, forest green, ochre","Condensed sans or slab","Outdoor, travel, adventure, automotive","Formal corporate services that need polish over grit"
+Outlaw,Liberation and rule-breaking,Overturn what is not working,"Bold, disruptive, irreverent, raw","Rebellion, change, challenging the default","High contrast, raw composition","Black, red, charcoal","Heavy grotesque or brutalist display","Challenger brands, streetwear, counterculture","Trust-critical sectors like finance or healthcare"
+Magician,Transformation,Make dreams come true,"Visionary, evocative, confident","Transformation, wonder, the impossible made real","Gradients, depth, controlled light","Violet, indigo, iridescent accents","Elegant geometric sans with a display face","Tech, beauty, immersive experiences","Utilitarian, low-cost positioning"
+Hero,Mastery and courage,Prove worth through bold action,"Bold, direct, motivating","Triumph, performance, rising to the challenge","Dynamic angles, strong contrast","Bold primary, red, black","Strong grotesque, italic display accent","Sports, performance gear, defense","Gentle or nurturing categories"
+Lover,Intimacy and belonging,Be in a relationship and feel connection,"Sensual, warm, expressive","Desire, closeness, indulgence","Rich texture, soft directional light","Deep red, rose, warm neutrals","High-contrast serif with a script accent","Beauty, fashion, hospitality, fragrance","Technical B2B utility where warmth reads as fluff"
+Jester,Enjoyment and play,Have a great time and lighten the world,"Playful, witty, irreverent","Fun, spontaneity, not taking it too seriously","Bright, bouncy, expressive shapes","Bright multi-hue, yellow, orange","Rounded display or quirky sans","Snacks, entertainment, kids, gaming","Sectors that require gravitas and authority"
+Everyman,Belonging and connection,Connect with others as equals,"Friendly, plain-spoken, inclusive","Relatability, fairness, everyday value","Approachable, candid imagery","Denim blue, warm neutral, earthy tones","Humanist sans, neutral weights","Mass retail, community, FMCG","Luxury or exclusive positioning"
+Caregiver,Protection and service,Care for and protect others,"Warm, reassuring, supportive","Care, safety, being looked after","Soft forms, human imagery, gentle light","Soft blue, teal, warm white","Humanist sans or a soft serif","Healthcare, childcare, nonprofit","Edgy or aggressively competitive positioning"
+Ruler,"Control, order and prosperity",Create order and lasting prosperity,"Authoritative, polished, assured","Leadership, excellence, the standard others follow","Refined symmetry, premium materials","Deep navy, gold, black","Classic serif (Didone or old-style) with a refined sans","Luxury, finance, law, institutions","Playful or budget mass-market positioning"
+Creator,Self-expression and lasting value,Realize a vision and craft something enduring,"Expressive, imaginative, precise","Craft, originality, the made thing","Bold composition, generous grid","Expressive accent on neutral or monochrome ground","Distinctive display with a clean grotesque workhorse","Design tools, studios, makers, agencies","Sectors where trust comes from conformity, not originality"

package/dist/agent-src/skills/brand/data/color-psychology.csv

@@ -0,0 +1,14 @@
+Industry,Primary Hue Direction,Emotional Association,Secondary/Accent,Avoid Hue,Contrast Note,Cultural Caveat,Archetype Fit
+Finance/Banking,Deep blue - signals trust and stability,trust; stability; authority; confidence,Gold or dark teal as accent,Bright orange - reads as frivolous or discount brand,Navy on white passes AA; mid-blue on grey often fails - verify ratio,Red = luck in China so avoid framing red as a warning only,Ruler
+Healthcare,Clean blue or teal - clinical confidence without coldness,care; cleanliness; calm; hope,White or soft green,Red for non-emergency UI - raises false alarm signals,Pastel teal on white can fail AA at small sizes - darken text tones,Green = illness in some Middle Eastern contexts - prefer blue,Caregiver
+Technology/SaaS,Blue to indigo spectrum - innovative yet dependable,innovation; intelligence; clarity; speed,Electric blue or violet accent,Muddy brown - evokes outdated legacy software,High-contrast dark mode is common - ensure 4.5:1 on both light and dark backgrounds,Purple = mourning in some Latin American cultures - use sparingly,Magician
+Food and Beverage,Warm red-orange - stimulates appetite and energy,appetite; warmth; energy; playfulness,Yellow or earthy brown,Cool grey-blue - suppresses appetite and feels clinical,Saturated warm tones on white are typically safe - watch yellow text legibility,White plates in photography read as sterile in some South Asian feast contexts,Jester
+Beauty/Cosmetics,Dusty rose to nude blush - softness and sensuality,elegance; softness; femininity; desire,Gold or matte black for premium tier,Harsh neon green - clashes with skin-tone imagery,Low-contrast nude palettes fail AA on white - always pair with dark text overlay,Pink = masculine in some historical European contexts - research target market,Lover
+Luxury,Black anchored by deep navy or charcoal - exclusivity,prestige; exclusivity; sophistication; desire,Gold or champagne as sole accent,Bright primary red - reads mass-market or sale-driven,Black backgrounds with gold text often miss 3:1 - test; consider off-white on black,Gold = vulgarity in some Northern European minimalist cultures,Ruler
+Children/Education,Bright primary hues - yellow; red; blue with high chroma,joy; curiosity; safety; playfulness,Complementary secondary primaries,Black as dominant - feels heavy and scary for young audiences,High chroma on white generally passes AA but verify yellow text on white,Red = danger signal universally; balance with friendlier primaries,Innocent
+Eco/Sustainability,Natural mid-green grounded with earthy brown or beige,nature; honesty; renewal; responsibility,Warm tan or sky blue accent,Neon or synthetic-feeling fluorescents - undermine authenticity,Mid-green on white passes AA at normal weights - avoid light sage for body text,Green = environment globally but also envy; pair with earth tones to anchor meaning,Explorer
+Fitness/Sports,Bold red-orange or electric blue - energy and motion,energy; power; determination; vitality,Black or white for contrast,Pastel lavender - reads too gentle for performance context,High-saturation colours on dark backgrounds need 4.5:1; test contrast on product imagery,Red = aggression risk in some East Asian performance contexts - balance with neutral,Hero
+Legal/Professional Services,Charcoal navy or deep green - authority without aggression,authority; reliability; tradition; gravitas,Muted gold or warm grey,Bright playful yellows - undermine gravitas and formal trust signals,Dark navy on dark grey fails AA - always use white or near-white for text,Black = formality in West but mourning in East Asia - soften with navy for global brands,Ruler
+Travel/Hospitality,Sky blue to teal - freedom and escape,freedom; adventure; relaxation; wonder,Warm sand or coral accent,Industrial grey - negates escapism and wanderlust,Teal on white passes AA at bold sizes; mid-weight teal on white needs darkening,Blue = sadness in some European idioms; balance with warm accent to ensure positivity,Explorer
+Fashion,Variable - season-driven but often neutral black or seasonal accent hue,desirability; individuality; status; creativity,Seasonal accent per collection,Dated neon from prior decades unless intentional retro signal,Editorial black-on-white is high contrast and safe; low-contrast grey-on-grey is decorative only,White = purity in West but mourning in parts of East and South Asia - verify market,Creator
+Nonprofit/Charity,Warm green or hopeful blue - optimism and humanity,compassion; hope; community; trust,Warm orange or yellow for calls to action,Cold corporate navy alone - can feel institutional and distant,Ensure CTA orange or yellow meets 3:1 against adjacent background for UI elements,Red = blood or danger in fundraising imagery - use carefully; prefer orange for urgency,Caregiver

package/dist/agent-src/skills/brand/data/logo-style-fit.csv

@@ -0,0 +1,13 @@
+Logo Style,Description,Industry Fit,Construction,Scalability Note,Vector Requirement,Avoid When,Archetype Fit
+Wordmark/Logotype,A logo consisting entirely of a stylized company name set in a custom or chosen typeface.,Tech startups; fashion; media; SaaS,Custom letterforms on a baseline grid; tight tracking; optical kerning adjustments,Readable down to ~16px if typeface is clean; collapses to favicon initial at very small sizes,Must be SVG <path> outlines so any renderer can scale without font-dependency or raster blur,Brand name is long or hard to pronounce; international markets require localized scripts,Ruler
+Lettermark/Monogram,"One to three initials treated as a standalone graphic mark, often with custom ligatures.",Law firms; finance; luxury; consulting,Two or three letterforms composed on a shared grid; ligatures optically balanced,Excellent at small sizes - single glyph reads instantly as favicon or app icon,True vector required; raster versions pixelate at retina densities and lose ligature crispness,Company name is already short and memorable enough to stand alone as a wordmark,Ruler
+Brandmark/Pictorial symbol,"A recognizable real-world object or icon used as the sole brand identifier, no text.",Consumer tech; sports; retail; food and beverage,Simplified silhouette reduced to essential contours; built on a geometric skeleton,Scales from billboard to 16px favicon cleanly when unnecessary detail is removed at design time,SVG <path> is mandatory; any bitmap detail renders as mud at small icon sizes,Brand is unknown - pictorial marks require years of recognition before standing alone,Explorer
+Abstract mark,A non-representational geometric form that conveys brand values through shape and color.,B2B technology; consulting; financial services; biotech,Constructed from geometric primitives on a strict grid; proportions derived from golden ratio or modular scale,Highly scalable as it contains no fine detail; works as app icon with no modification,Vector <path> essential; abstract marks are precision objects and raster blurs their mathematical edges,Brand needs immediate intuitive communication of a product category to new audiences,Magician
+Combination mark,A wordmark and symbol presented together as a single lockup with defined clear-space rules.,Most industry sectors - the most versatile logo format,Symbol placed left of or above the wordmark; aligned on a shared baseline; proportional size ratio defined in brand guide,Can separate into symbol-only or wordmark-only responsive variants for small placements,Each element must be a separate SVG layer so the lockup can be split for responsive use without raster degradation,Space is extremely constrained and only one mark variant will ever be used,Everyman
+Emblem/Badge,"The name and a symbol are enclosed inside a containing shape such as a shield, circle, or crest.",Breweries; universities; sports teams; heritage brands; automotive,Outer shape contains arranged type arcs and central device; letterpress-era inspired construction,Loses fine interior detail below 48px; a simplified badge variant is typically required for favicon use,Vector is critical - the interior complexity of badge elements becomes unrecognizable in raster at small sizes,Digital-first products that appear primarily as small icons or in dense UI environments,Caregiver
+Mascot,"A character - illustrated figure or creature - that acts as brand spokesperson and logo element.",Food and beverage; sports; children's brands; gaming; insurance,Character illustration with defined poses; color palette limited for reproduction consistency; brand guide covers expression library,Cannot scale to favicon; a separate abstract or initial-based icon is always required alongside it,Vector illustration preferred for scalability; raster mascots are acceptable only if minimum-size usage is strictly avoided,B2B enterprise; legal; medical; financial sectors where authority and trust must read instantly,Jester
+Geometric/Modular mark,A mark constructed from repeated or interlocking geometric modules - squares; circles; triangles.,Architecture; engineering; data; fintech; design agencies,Grid-based modules locked to precise intervals; negative space between modules is part of the design intent,Scales cleanly because the building blocks are simple; modules may merge into a solid shape at very small sizes,SVG paths must encode each module as a closed shape so module colors and spacing remain editable and renderer-agnostic,Brands that need warmth or organic character; hospitality or wellness sectors,Creator
+Negative-space mark,"A mark where a hidden secondary image is revealed in the space between or within primary shapes.",Design-forward brands; food; retail; clever challenger brands,Two overlapping or adjacent positive shapes engineered so the gap forms a recognizable third image,Can be fragile at small sizes if the negative-space detail disappears; test at 24px before approving,Vector mandatory - raster anti-aliasing destroys the sharp edge contrast on which the illusion depends,Audiences who will encounter the mark only at small digital sizes and never in print or large-format,Outlaw
+Gradient/3D mark,"A mark that uses color gradients, shadows, or dimensional rendering to suggest depth or light.",Consumer apps; entertainment; gaming; lifestyle tech,Gradient mesh or linear/radial gradient applied over a vector base form; highlight and shadow layers stacked,Degrades to flat color at small sizes; a flat fallback variant is required in brand guidelines,Base shape must be SVG <path>; gradient appearance is a style layer - the structural mark must work without it,Embossing; foil stamping; or single-color print contexts where gradients cannot reproduce,Lover
+Dynamic/Responsive mark,A mark system with defined variants that adapt layout or complexity to available space or context.,Large digital platforms; media networks; enterprise software suites,Core symbol plus rules for 3-4 variants ranging from full lockup to icon-only; grid defines reduction breakpoints,Purpose-built for small sizes - the icon variant is the small-size solution by design,Each variant must be a separate SVG file with <path> elements; automated raster export from each variant covers all densities,Small organizations without resources to maintain a multi-variant system consistently,Sage
+Typographic/Custom-type mark,"A logotype where the letterforms are uniquely drawn or heavily modified to be a proprietary typeface.",Premium consumer brands; fashion houses; editorial media; cultural institutions,Letters drawn from scratch or derived from an existing typeface then heavily modified; each glyph refined for optical balance,Works at most sizes if letterforms are open and not overly decorative; condensed custom cuts can collapse at favicon scale,Outlines must be expanded to SVG <path> curves so the mark is independent of any font file and renders identically everywhere,Brands requiring frequent name updates or localization into non-Latin scripts,Creator