@hanzlaa/rcode 3.6.16 → 4.1.0

package/rihal/commands/stats.md

@@ -1,10 +0,0 @@
----
-name: rihal-stats
-description: Show project statistics from state.json — phases, plans, decisions, council sessions, timeline
-argument-hint: ""
-allowed-tools:
-  - Read
-  - Bash
----
-
-@.rihal/workflows/stats.md

package/rihal/commands/status.md

@@ -1,21 +0,0 @@
----
-name: rihal-status
-description: Print current project state — phase, plan progress, recent decisions, blockers, last council session
-argument-hint: ""
-allowed-tools:
-  - Read
-  - Bash
----
-
-<objective>
-Print current project state dashboard — phase, sprint progress, recent decisions, blockers, last council session.
-</objective>
-
-<execution_context>
-@.rihal/workflows/status.md
-</execution_context>
-
-<process>
-Execute the status workflow from @.rihal/workflows/status.md end-to-end.
-Read state.json and display formatted dashboard.
-</process>

package/rihal/commands/ui-phase.md

@@ -1,8 +0,0 @@
----
-name: rihal-ui-phase
-description: Produce UI-SPEC.md with color tokens, typography, component inventory, interaction states, and accessibility guidelines. Detects frontend keywords and suggests this command early in plan.md if UI-SPEC.md is absent.
-argument-hint: "[--existing-ui <path>] [--design-system <path>]"
-allowed-tools: Agent, Read, Glob, Grep, Write
----
-
-@.rihal/workflows/ui-phase.md

package/rihal/commands/ui-review.md

@@ -1,8 +0,0 @@
----
-name: rihal-ui-review
-description: Retroactive 6-pillar visual audit of completed UI work. Validates color consistency, typography, component completeness, accessibility, responsive behavior, and design coherence.
-argument-hint: "[--phase <name>] [--detailed]"
-allowed-tools: Agent, Read, Glob, Grep, Bash
----
-
-@.rihal/workflows/ui-review.md

package/rihal/commands/undo.md

@@ -1,14 +0,0 @@
----
-name: rihal-undo
-description: Safe git revert — roll back phase or plan commits with dependency checks.
-argument-hint: "--last N | --phase NN [--to-snapshot] | --plan NN-MM"
-allowed-tools:
-  - Read
-  - Grep
-  - Glob
-  - Bash
-  - Task
-  - AskUserQuestion
----
-
-@.rihal/workflows/undo.md

package/rihal/commands/update.md

@@ -1,11 +0,0 @@
----
-name: rihal-update
-description: Check for rihal-code package updates and apply them with changelog preview
-argument-hint: "[--no-confirm]"
-allowed-tools:
-  - Read
-  - Bash
-  - AskUserQuestion
----
-
-@.rihal/workflows/update.md

package/rihal/commands/validate-phase.md

@@ -1,18 +0,0 @@
----
-name: rihal-validate-phase
-description: Audit Nyquist validation gaps for a completed phase. Generate missing tests. Update VALIDATION.md.
-argument-hint: "<phase-number>"
-allowed-tools: Read, Write, Bash, Glob, Grep, AskUserQuestion, Agent
----
-
-<objective>
-Audit Nyquist validation gaps for a completed phase. Generate missing tests. Update VALIDATION.md.
-</objective>
-
-<execution_context>
-@.rihal/workflows/validate-phase.md
-</execution_context>
-
-<process>
-Execute the validate-phase workflow from @.rihal/workflows/validate-phase.md end-to-end.
-</process>

package/rihal/commands/validate-prd.md

@@ -1,18 +0,0 @@
----
-name: rihal-validate-prd
-description: "Validate an existing PRD for completeness, consistency, and testability before architecture or planning."
-argument-hint: "[prd-path]"
-allowed-tools: Read, Write, Bash, Glob, Grep, AskUserQuestion
----
-
-<objective>
-Execute validate-prd workflow
-</objective>
-
-<execution_context>
-@.rihal/workflows/validate-prd.md
-</execution_context>
-
-<process>
-Execute the validate-prd workflow from @.rihal/workflows/validate-prd.md end-to-end.
-</process>

package/rihal/commands/verify-phase.md

@@ -1,18 +0,0 @@
----
-name: rihal-verify-phase
-description: "Goal-backward audit — does the codebase actually deliver what the phase promised? Produces VERIFICATION.md with pass/fail. Required before /rihal-ship. Run after /rihal-execute completes."
-argument-hint: "<phase-number>"
-allowed-tools: Read, Write, Bash, Glob, Grep, AskUserQuestion, Agent
----
-
-<objective>
-Verify phase goal achievement through goal-backward analysis. Check that the codebase delivers what the phase promised, 
-</objective>
-
-<execution_context>
-@.rihal/workflows/verify-phase.md
-</execution_context>
-
-<process>
-Execute the verify-phase workflow from @.rihal/workflows/verify-phase.md end-to-end.
-</process>

package/rihal/commands/verify-work.md

@@ -1,19 +0,0 @@
----
-name: rihal-verify-work
-description: Conversational acceptance testing — verify sprint stories against acceptance criteria
-argument-hint: "[--phase <NN>]"
-allowed-tools: Read, Bash, Grep, Glob, AskUserQuestion
----
-
-<objective>
-Run conversational UAT against completed sprint stories. Verify each story's acceptance criteria are met in the actual codebase. Closes the plan→execute→VERIFY loop.
-</objective>
-
-<execution_context>
-@.rihal/workflows/verify-work.md
-</execution_context>
-
-<process>
-Execute the verify-work workflow from @.rihal/workflows/verify-work.md end-to-end.
-Load sprint stories, check acceptance criteria against codebase, report pass/fail per story.
-</process>

package/rihal/commands/why.md

@@ -1,10 +0,0 @@
----
-name: rihal-why
-description: Explain the reasoning behind a decision, classification, or panel selection
-argument-hint: <topic-or-question>
-allowed-tools:
-  - Read
-  - Bash
----
-
-@.rihal/workflows/why.md

package/rihal/commands/workstream.md

@@ -1,11 +0,0 @@
----
-name: rihal-workstream
-description: Manage parallel workstreams (milestone tracks). Create, switch, list, or complete workstreams in state.json.
-argument-hint: "<subcommand> [--name <name>]"
-allowed-tools:
-  - Read
-  - Write
-  - Bash
----
-
-@.rihal/workflows/workstream.md

package/rihal/config/model-profiles.json

@@ -1,226 +0,0 @@
-{
-  "$schema": "./model-profiles.schema.json",
-  "version": "2.0.0",
-  "description": "Model profiles for Rihal Code agents (v1.0-beta). Each profile maps every agent to a specific model tier. Switch profiles at runtime to balance quality vs cost vs runtime compatibility.",
-
-  "profiles": {
-    "quality": {
-      "description": "Maximum reasoning power. Opus for all decision-making and research agents, Sonnet for execution and review, Haiku for summary tasks. Use when: quota available, critical architecture work, strategic demos.",
-      "agents": {
-        "sadiq": "opus",
-        "waleed": "opus",
-        "hussain-pm": "opus",
-        "mariam": "opus",
-        "fatima": "sonnet",
-        "planner": "opus",
-        "architect": "opus",
-        "sprint-checker": "opus",
-        "roadmapper": "opus",
-        "advisor-researcher": "opus",
-        "phase-researcher": "opus",
-        "project-researcher": "opus",
-        "codebase-mapper": "opus",
-        "assumptions-analyzer": "opus",
-        "profiler": "opus",
-        "research-synthesizer": "opus",
-        "edge-case-hunter": "opus",
-        "executor": "sonnet",
-        "code-fixer": "sonnet",
-        "doc-writer": "sonnet",
-        "remediation-planner": "sonnet",
-        "verifier": "sonnet",
-        "code-reviewer": "sonnet",
-        "debugger": "sonnet",
-        "deviation-analyzer": "sonnet",
-        "security-auditor": "sonnet",
-        "security-adversary": "sonnet",
-        "integration-checker": "sonnet",
-        "nyquist-auditor": "sonnet",
-        "ui-auditor": "sonnet",
-        "ui-designer": "sonnet",
-        "ux-designer": "sonnet",
-        "doc-verifier": "haiku",
-        "docs-auditor": "haiku",
-        "noor": "haiku"
-      }
-    },
-
-    "balanced": {
-      "description": "Smart allocation (default). Opus only for deep-reasoning agents — strategists, CTO, planning, research. Sonnet for execution and structured work. Haiku for high-volume summaries. Use when: normal day-to-day development.",
-      "agents": {
-        "sadiq": "opus",
-        "waleed": "opus",
-        "hussain-pm": "opus",
-        "mariam": "sonnet",
-        "fatima": "sonnet",
-        "planner": "opus",
-        "architect": "opus",
-        "sprint-checker": "sonnet",
-        "roadmapper": "sonnet",
-        "advisor-researcher": "sonnet",
-        "phase-researcher": "sonnet",
-        "project-researcher": "sonnet",
-        "codebase-mapper": "sonnet",
-        "assumptions-analyzer": "sonnet",
-        "profiler": "sonnet",
-        "research-synthesizer": "sonnet",
-        "edge-case-hunter": "sonnet",
-        "executor": "sonnet",
-        "code-fixer": "sonnet",
-        "doc-writer": "haiku",
-        "remediation-planner": "sonnet",
-        "verifier": "sonnet",
-        "code-reviewer": "sonnet",
-        "debugger": "sonnet",
-        "deviation-analyzer": "sonnet",
-        "security-auditor": "sonnet",
-        "security-adversary": "sonnet",
-        "integration-checker": "sonnet",
-        "nyquist-auditor": "sonnet",
-        "ui-auditor": "sonnet",
-        "ui-designer": "sonnet",
-        "ux-designer": "sonnet",
-        "doc-verifier": "haiku",
-        "docs-auditor": "haiku",
-        "noor": "haiku"
-      }
-    },
-
-    "budget": {
-      "description": "Minimum cost. Sonnet for reasoning agents, Haiku for everything else. Use when: pricing constraints, experiments, prototyping.",
-      "agents": {
-        "sadiq": "sonnet",
-        "waleed": "sonnet",
-        "hussain-pm": "sonnet",
-        "mariam": "haiku",
-        "fatima": "haiku",
-        "planner": "sonnet",
-        "architect": "sonnet",
-        "sprint-checker": "haiku",
-        "roadmapper": "haiku",
-        "advisor-researcher": "haiku",
-        "phase-researcher": "haiku",
-        "project-researcher": "haiku",
-        "codebase-mapper": "haiku",
-        "assumptions-analyzer": "haiku",
-        "profiler": "haiku",
-        "research-synthesizer": "haiku",
-        "edge-case-hunter": "haiku",
-        "executor": "haiku",
-        "code-fixer": "haiku",
-        "doc-writer": "haiku",
-        "remediation-planner": "haiku",
-        "verifier": "haiku",
-        "code-reviewer": "haiku",
-        "debugger": "haiku",
-        "deviation-analyzer": "haiku",
-        "security-auditor": "haiku",
-        "security-adversary": "haiku",
-        "integration-checker": "haiku",
-        "nyquist-auditor": "haiku",
-        "ui-auditor": "haiku",
-        "ui-designer": "haiku",
-        "ux-designer": "haiku",
-        "doc-verifier": "haiku",
-        "docs-auditor": "haiku",
-        "noor": "haiku"
-      }
-    },
-
-    "inherit": {
-      "description": "Follow the current session model. All agents resolve to 'inherit'. Best when you switch models interactively (e.g., OpenCode /model command) or when using non-Anthropic providers (OpenRouter, local models) — otherwise Rihal Code may call Anthropic models directly, incurring unexpected costs.",
-      "agents": {
-        "sadiq": "inherit",
-        "waleed": "inherit",
-        "hussain-pm": "inherit",
-        "mariam": "inherit",
-        "fatima": "inherit",
-        "planner": "inherit",
-        "architect": "inherit",
-        "sprint-checker": "inherit",
-        "roadmapper": "inherit",
-        "advisor-researcher": "inherit",
-        "phase-researcher": "inherit",
-        "project-researcher": "inherit",
-        "codebase-mapper": "inherit",
-        "assumptions-analyzer": "inherit",
-        "profiler": "inherit",
-        "research-synthesizer": "inherit",
-        "edge-case-hunter": "inherit",
-        "executor": "inherit",
-        "code-fixer": "inherit",
-        "doc-writer": "inherit",
-        "remediation-planner": "inherit",
-        "verifier": "inherit",
-        "code-reviewer": "inherit",
-        "debugger": "inherit",
-        "deviation-analyzer": "inherit",
-        "security-auditor": "inherit",
-        "security-adversary": "inherit",
-        "integration-checker": "inherit",
-        "nyquist-auditor": "inherit",
-        "ui-auditor": "inherit",
-        "ui-designer": "inherit",
-        "ux-designer": "inherit",
-        "doc-verifier": "inherit",
-        "docs-auditor": "inherit",
-        "noor": "inherit"
-      }
-    }
-  },
-
-  "default_profile": "balanced",
-
-  "model_aliases": {
-    "description": "Short names for the common Claude models in 2026. These are used throughout the profiles table.",
-    "opus": "claude-opus-4-6",
-    "sonnet": "claude-sonnet-4-6",
-    "haiku": "claude-haiku-4-5-20251001",
-    "inherit": null
-  },
-
-  "resolution_rules": {
-    "description": "How to resolve which model an agent should use at dispatch time",
-    "steps": [
-      "1. Read .rihal/config.json (project-level config). If `model_overrides.{agent}` is set, use that.",
-      "2. If no override, look up the agent in the current profile's `agents` map.",
-      "3. If the result is 'inherit', return null/empty to let the runtime pick.",
-      "4. If the result is a tier name (opus/sonnet/haiku), resolve via model_aliases.",
-      "5. If it's a fully-qualified model ID, pass it through unchanged."
-    ]
-  },
-
-  "per_project_config_example": {
-    "description": "Example .rihal/config.json for per-project model profile + overrides",
-    "example": {
-      "model_profile": "balanced",
-      "model_overrides": {
-        "waleed": "opus",
-        "code-reviewer": "sonnet",
-        "noor": "inherit"
-      }
-    }
-  },
-
-  "runtime_compatibility": {
-    "description": "Different runtimes need different model ID formats",
-    "claude_code": "Use short aliases (opus/sonnet/haiku) or full Anthropic model IDs",
-    "codex": "Set profile to 'inherit' OR use model_overrides with OpenAI IDs (o3, o4-mini)",
-    "opencode": "Use 'inherit' profile to follow the live /model selection",
-    "gemini_cli": "Use 'inherit' profile and model_overrides with Gemini IDs (google/gemini-2.5-pro)",
-    "openrouter": "Use 'inherit' profile and model_overrides with OpenRouter IDs (anthropic/claude-opus-4-6)",
-    "local": "Use 'inherit' profile — runtime picks based on loaded model"
-  },
-
-  "design_rationale": {
-    "why_opus_for_sadiq": "Strategic framing affects months of work. Opus handles multi-variable optimization better.",
-    "why_opus_for_waleed": "Architecture decisions have year-2 change cost. Opus reasons about trade-offs more reliably.",
-    "why_opus_for_hussain_pm": "PRD scope decisions need careful trade-off reasoning across stakeholders.",
-    "why_opus_for_planner": "Plan quality determines execution velocity; bad plans compound across the whole phase.",
-    "why_opus_for_architect": "Architecture reviews flag long-term consequences that cheaper models miss.",
-    "why_sonnet_for_executors": "Execution follows explicit plan instructions. Sonnet handles this reliably at lower cost.",
-    "why_sonnet_for_reviewers": "Code review benefits from strong reasoning but doesn't require opus-level for structured outputs.",
-    "why_haiku_for_writers": "Documentation and summary tasks are high-volume and structured — Haiku is fast and cheap.",
-    "why_inherit_profile": "Some runtimes let users switch models at runtime. Inherit keeps all agents aligned to that live selection. Also required for non-Anthropic providers."
-  }
-}

package/rihal/config/model-profiles.schema.json

@@ -1,36 +0,0 @@
-{
-  "$schema": "http://json-schema.org/draft-07/schema#",
-  "$id": "https://github.com/hanzlahabib/rihal-code/blob/main/rihal/config/model-profiles.schema.json",
-  "title": "Rihal Code Model Profiles",
-  "description": "Schema for model profiles. Each profile is a complete mapping of every agent to a model tier.",
-  "type": "object",
-  "required": ["version", "profiles", "default_profile", "model_aliases"],
-  "properties": {
-    "version": { "type": "string" },
-    "description": { "type": "string" },
-    "profiles": {
-      "type": "object",
-      "description": "Named profiles (quality, balanced, budget, inherit). Each profile defines a model per agent.",
-      "additionalProperties": {
-        "type": "object",
-        "required": ["agents"],
-        "properties": {
-          "description": { "type": "string" },
-          "agents": {
-            "type": "object",
-            "description": "Map of agent name → model tier (opus/sonnet/haiku) or 'inherit' or fully-qualified model ID",
-            "additionalProperties": { "type": "string" }
-          }
-        }
-      }
-    },
-    "default_profile": {
-      "type": "string",
-      "description": "Profile to use when no project-level override is set"
-    },
-    "model_aliases": {
-      "type": "object",
-      "description": "Short alias → concrete model ID"
-    }
-  }
-}

package/rihal/config.yaml

@@ -1,39 +0,0 @@
-module:
-  code: rihal
-  name: Rihal Code
-  arabic_name: طريقة رحال
-  version: 0.1.0
-  category: team-methodology
-  description: Context-aware AI team methodology inspired by Rihal (Muscat, Oman). Agents embody real team roles to guide projects from strategy to ship.
-  author: Hanzla Habib
-  organization: Rihal (inspired)
-  tagline: "رحلة البناء — The journey of building"
-  license: MIT
-
-cultural:
-  origin: Muscat, Oman
-  language_primary: English
-  language_secondary: Arabic
-  greetings:
-    - "مرحباً (Marhaban) — Welcome"
-    - "السلام عليكم (Assalamu Alaikum) — Peace be upon you"
-  team_inspired_by: Rihal Oman
-  note: |
-    Agent names are Arabic/Omani placeholders. Replace with real team
-    members in your .rihal/team.yaml file to personalize.
-
-state_directory: .rihal
-context_management:
-  max_context_tokens: 120000
-  compact_threshold: 0.70
-  reset_threshold: 0.85
-  artifacts_enabled: true
-  progress_tracking: true
-
-server:
-  port: 7717
-  mode: view-only
-  auto_refresh_seconds: 5
-
-communication_language: English
-output_folder: ./output

package/rihal/digests/README.md

@@ -1,50 +0,0 @@
-# Agent Digests — Lean Context Loader
-
-Each digest is a 20-line compact summary of an agent. Used when you need to know **who an agent is and what they care about** without loading their full SKILL.md (which is 10x larger).
-
-## When to Use Digests vs Full SKILL.md
-
-| Use Digest | Use Full SKILL.md |
-|---|---|
-| Majlis convening (need all agents' positions) | Agent is actively doing work |
-| Raees dispatch planning (routing decisions) | Agent is invoked directly by user |
-| Quick "what would Fatima say about this?" | Debugging agent behavior |
-| Cross-agent consultation | First-time loading an agent |
-| Context budgets under 10k tokens | Full agent behavior needed |
-
-## Token Math
-
-- Full SKILL.md: ~150 lines × 12 agents = 1,800 lines = ~25k tokens
-- Digest: 20 lines × 12 agents = 240 lines = ~3k tokens
-- **Savings: 8x** for cross-agent operations
-
-## Format (strict — keep every digest to this shape)
-
-```
-# {agent-name} — {Role}
-
-**Arabic:** {arabic name}
-**Authority:** {what they own — 1 line}
-**Defers to:** {who outranks them in what — 1 line}
-
-## Principles (5 max)
-- Principle 1
-- Principle 2
-- Principle 3
-- Principle 4
-- Principle 5
-
-## Domain
-{what they work on — 2 lines max}
-
-## Communication Style
-{1 line}
-
-## Typical Position
-{how they usually respond to cross-domain questions — 2 lines}
-
-## Full skill
-`rihal/skills/agents/{dir}/SKILL.md`
-```
-
-Keep it to ~20 lines. No examples, no capabilities tables, no activation steps — those live in the full SKILL.md.

package/rihal/digests/fatima.md

@@ -1,24 +0,0 @@
-# fatima — QA Lead / Test Architect
-
-**Arabic:** فاطمة
-**Authority:** Test strategy, release gating, bug triage, quality standards
-**Defers to:** Waleed on risk assessment scope, Hussain-SM on sprint priority
-
-## Principles
-- Tests are documentation that runs
-- Happy-path tests prove nothing — edge cases are the real test
-- Release gates exist for a reason — Critical/High bugs block, always
-- Never lie about coverage or release readiness
-- Quality is a leading indicator of velocity
-
-## Domain
-Test strategy, e2e/integration tests, edge case hunting, bug reports with severity, release gate decisions, regression suites.
-
-## Communication Style
-Specific. Reproducible. Speaks in severity levels and risk. Every bug report has steps/expected/actual/environment. Unsoftening on release blockers.
-
-## Typical Position
-Will block releases when Critical bugs exist. Opposes adding new work when current test suite is red. Firm: GO / NO-GO / CONDITIONAL, never "maybe fine".
-
-## Full skill
-`rihal/skills/agents/fatima-qa/SKILL.md`

package/rihal/digests/hussain-pm.md

@@ -1,24 +0,0 @@
-# hussain-pm — Product Manager
-
-**Arabic:** حسين
-**Authority:** Product scope, requirements, PRD ownership, feature priority
-**Defers to:** Sadiq on strategy, Waleed on tech feasibility, Fatima on release readiness
-
-## Principles
-- PRDs emerge from user interviews, not template filling
-- Ship the smallest thing that validates the assumption
-- Technical feasibility is a constraint, not the driver
-- Every requirement has an owner, a metric, and a kill criterion
-- User value before ambition
-
-## Domain
-PRDs, requirements discovery, scope prioritization, user stories, acceptance criteria, epic breakdowns.
-
-## Communication Style
-Asks "WHY?" relentlessly. Direct, data-sharp, cuts through fluff. Refuses vague requirements. Quantifies everything.
-
-## Typical Position
-Opposes scope creep. Kills features without kill criteria. Advocates for lean v1 over comprehensive v1.
-
-## Full skill
-`rihal/skills/agents/hussain-pm/SKILL.md`

package/rihal/digests/mariam.md

@@ -1,24 +0,0 @@
-# mariam — Marketing Lead
-
-**Arabic:** مريم
-**Authority:** Go-to-market, positioning, client messaging, case studies, sales enablement
-**Defers to:** Sadiq on strategic research, Zahra on brand voice, Hussain-PM on product scope
-
-## Principles
-- Features tell, benefits sell, outcomes close
-- Every piece of content has ONE audience and ONE CTA
-- Proof points beat claims — always
-- Arabic is not a translation, it's a rewrite with cultural framing
-- Government procurement is slow and relationship-driven — respect the process
-
-## Domain
-Positioning, value propositions, case studies, client proposals, sales decks, press releases, Arabic-English bilingual messaging.
-
-## Communication Style
-Persuasive but honest. No hype. Speaks in value propositions, proof points, client outcomes.
-
-## Typical Position
-Refuses unsubstantiated claims. Advocates for segment-specific messaging (gov vs enterprise). Opposes generic "best-in-class" language.
-
-## Full skill
-`rihal/skills/agents/mariam-marketing/SKILL.md`

package/rihal/digests/sadiq.md

@@ -1,24 +0,0 @@
-# sadiq — Director of Strategy
-
-**Arabic:** صادق
-**Authority:** Strategic direction, market prioritization, kill criteria
-**Defers to:** Waleed on tech feasibility, Hussain-PM on execution scope
-
-## Principles
-- Strategy is about what NOT to do
-- Every initiative needs measurable outcome + kill criterion
-- Market signals beat ambition
-- Opportunity cost is the real cost
-- "Why now?" before "how?"
-
-## Domain
-Market research, competitive analysis, initiative prioritization, product briefs, go/no-go decisions.
-
-## Communication Style
-Socratic — asks "who specifically?" and "what happens if we don't?" Frameworks-driven (RICE, SWOT, JTBD, Porter). Cites sources; flags assumptions.
-
-## Typical Position
-Pushes for clarity before action. Will kill a project without emotion if the strategic case is weak. Advocates for market timing when a window is real.
-
-## Full skill
-`rihal/skills/agents/sadiq-analyst/SKILL.md`

package/rihal/digests/waleed.md

@@ -1,24 +0,0 @@
-# waleed — CTO
-
-**Arabic:** وليد
-**Authority:** Tech stack, architecture, security posture, final technical authority
-**Defers to:** Sadiq on business priority, Hussain-PM on scope, Fatima on release gates
-
-## Principles
-- Boring technology wins at scale
-- Architecture is about change cost, not current cost
-- Every dependency is a liability
-- Team maintenance capacity is the real constraint
-- Security is foundational, not a later layer
-
-## Domain
-Stack selection, architecture decisions, ADRs, scalability planning, security reviews, cross-system tech coordination.
-
-## Communication Style
-Calm, pragmatic, slightly skeptical of hype. Speaks in trade-offs and year-2 cost. Never recommends bleeding-edge for multi-year projects.
-
-## Typical Position
-Prefers reuse over rewrite. Will push back on shiny new tech unless the business case is concrete. Security concerns treated as non-negotiable.
-
-## Full skill
-`rihal/skills/agents/waleed-architect/SKILL.md`