@gcunharodrigues/wrxn 0.1.0

package/payload/.claude/skills/synapse/references/brackets.md

@@ -0,0 +1,100 @@
+# SYNAPSE Context Brackets Reference
+
+## Overview
+
+Context brackets control how much content SYNAPSE injects per prompt based on how much context window remains. As the conversation progresses and context fills up, SYNAPSE adapts by changing which layers are active and how many tokens it injects.
+
+The bracket system is implemented in `.aiox-core/core/synapse/context/context-tracker.js`.
+
+## The 4 Brackets
+
+| Bracket | Context Remaining | Token Budget | Behavior |
+|---------|-------------------|-------------|----------|
+| **FRESH** | 60-100% | ~800 tokens | Lean injection — essentials only |
+| **MODERATE** | 40-60% | ~1500 tokens | Standard injection — all layers active |
+| **DEPLETED** | 25-40% | ~2000 tokens | Reinforcement — reinforce critical rules, memory hints enabled |
+| **CRITICAL** | <25% | ~2500 tokens | Handoff warning — recommend session handoff, document state |
+
+## How Brackets Are Calculated
+
+The context tracker estimates remaining context using:
+
+```
+contextPercent = 100 - ((promptCount * avgTokensPerPrompt) / maxContext * 100)
+```
+
+**Default values:**
+- `avgTokensPerPrompt`: 1500
+- `maxContext`: 200000 (Claude's context window)
+
+**Bracket assignment:**
+- `contextPercent >= 60` → FRESH
+- `contextPercent >= 40` → MODERATE
+- `contextPercent >= 25` → DEPLETED
+- `contextPercent < 25` → CRITICAL
+
+Invalid or NaN input defaults to CRITICAL (fail-safe).
+
+## Layer Activation per Bracket
+
+| Bracket | Active Layers | Memory Hints | Handoff Warning |
+|---------|---------------|-------------|-----------------|
+| **FRESH** | L0, L1, L2, L7 | No | No |
+| **MODERATE** | L0-L7 (all) | No | No |
+| **DEPLETED** | L0-L7 (all) | Yes | No |
+| **CRITICAL** | L0-L7 (all) | Yes | Yes |
+
+**Key behavior:**
+- **FRESH**: Only core layers (Constitution, Global, Agent, Star-Commands) — saves tokens early
+- **MODERATE**: Full layer stack activated — normal operation
+- **DEPLETED**: Memory hints from MIS enabled (when pro available) to reinforce context
+- **CRITICAL**: Handoff warning injected, recommending session continuation in new window
+
+## Bracket-Specific Rules
+
+The `.synapse/context` domain file contains rules that vary by bracket:
+
+### FRESH Rules
+- Minimize injected rules to essentials only
+- Avoid redundant context — agent has full conversation history
+- Full layer stack available but lean injection
+
+### MODERATE Rules
+- All layers active at normal priority
+- Monitor token usage — consider summarizing long outputs
+- Prefer concise code examples over verbose explanations
+
+### DEPLETED Rules
+- Reinforce critical rules and constraints
+- Prefer concise responses to save tokens
+- Skip optional layers (L6 keyword domains) to conserve
+- Summarize progress before each action
+
+### CRITICAL Rules
+- Recommend session handoff
+- Summarize current state for new session continuation
+- Only inject L0 Constitution and L1 Global rules — skip other layers
+- Document incomplete work in story file
+
+## Token Budget Enforcement
+
+The output formatter (`.aiox-core/core/synapse/output/formatter.js`) enforces token budgets:
+
+1. Each bracket has a max token budget (800 / 1500 / 2000 / 2500)
+2. Sections are rendered in priority order (CONSTITUTION first, SUMMARY last)
+3. When budget is exceeded, sections are truncated from the end (lowest priority first)
+
+**Truncation order** (last removed first):
+```
+SUMMARY → KEYWORD → SQUAD → TASK → WORKFLOW → AGENT → CONSTITUTION
+```
+
+Constitution (L0) is never truncated.
+
+## Source Files
+
+| File | Purpose |
+|------|---------|
+| `.aiox-core/core/synapse/context/context-tracker.js` | Bracket calculation, token budgets, layer configs |
+| `.synapse/context` | Bracket-specific context rules (L1) |
+| `.aiox-core/core/synapse/output/formatter.js` | Token budget enforcement + truncation |

package/payload/.claude/skills/synapse/references/commands.md

@@ -0,0 +1,118 @@
+# SYNAPSE Commands Reference
+
+## Overview
+
+SYNAPSE provides three categories of commands:
+1. **Mode star-commands** — Switch response behavior (`*brief`, `*dev`, etc.)
+2. **`*synapse` sub-commands** — Query and manage engine state
+3. **CRUD operations** — Create, modify, and manage domains and rules
+
+## Mode Star-Commands (L7)
+
+These commands switch the response mode for the current session. They are detected by L7 (Star-Command processor) and inject mode-specific rules.
+
+| Command | Behavior |
+|---------|----------|
+| `*brief` | Bullet points only, max 5 items, no code blocks unless requested, skip preamble |
+| `*dev` | Code over explanation, minimal changes, follow existing patterns, skip docs unless needed |
+| `*review` | Check code quality and patterns, identify bugs/security issues, suggest improvements with rationale |
+| `*plan` | Outline approach before implementation, list files to modify, identify risks, estimate complexity |
+| `*discuss` | Explore trade-offs and alternatives, ask clarifying questions, present pros/cons, recommend with reasoning |
+| `*debug` | Analyze error messages and stack traces, check common failure patterns, suggest targeted fixes |
+| `*explain` | Explain in teaching detail, use analogies, show examples with code, build from basics to advanced |
+
+**Usage:** Type the command anywhere in your prompt. The mode persists for that response.
+
+**Source:** `.synapse/commands` (KEY=VALUE format, `COMMANDS_RULE_{MODE}_{INDEX}`)
+
+## `*synapse` Sub-Commands
+
+These commands query or control the SYNAPSE engine state.
+
+| Command | What it does |
+|---------|-------------|
+| `*synapse help` | Show available synapse commands and their descriptions |
+| `*synapse status` | Display current state: active domains, layers, session info |
+| `*synapse debug` | Show detailed debug info: manifest parse results, domain load times, rule counts |
+| `*synapse domains` | List all registered domains with their state and trigger conditions |
+| `*synapse session` | Show current session context: active agent, workflow, bracket level |
+| `*synapse reload` | Force reload of manifest and all domain files from disk |
+
+**Note:** These are read-only operations handled by the L7 star-command processor in the hook. They do not modify any files.
+
+## CRUD Operations
+
+These commands modify domain files and the manifest. They are implemented as Claude Code slash commands in `.claude/commands/synapse/`.
+
+### Router
+
+All CRUD operations go through the manager: `.claude/commands/synapse/manager.md`
+
+The manager parses the sub-command and dispatches to the appropriate task file.
+
+### Available Operations
+
+| Command | Task File | Purpose |
+|---------|-----------|---------|
+| `*synapse create` | `tasks/create-domain.md` | Create new domain file + manifest entry |
+| `*synapse add` | `tasks/add-rule.md` | Add a new rule to an existing domain |
+| `*synapse edit` | `tasks/edit-rule.md` | Edit or remove a rule by index |
+| `*synapse toggle` | `tasks/toggle-domain.md` | Toggle domain STATE between active/inactive |
+| `*synapse command` | `tasks/create-command.md` | Create a new star-command definition |
+| `*synapse suggest` | `tasks/suggest-domain.md` | Suggest the best domain for a given rule |
+
+### Usage Examples
+
+**Create a new domain:**
+```
+*synapse create
+```
+Prompts for: domain name, layer, description, initial rules.
+
+**Add a rule to an existing domain:**
+```
+*synapse add global "Always prefer functional patterns over imperative"
+```
+
+**Toggle a domain off:**
+```
+*synapse toggle agent-dev
+```
+
+**Edit a specific rule:**
+```
+*synapse edit global 3
+```
+Opens rule at index 3 in `global` domain for editing.
+
+**Create a new star-command:**
+```
+*synapse command
+```
+Prompts for: command name, behavior rules.
+
+**Get domain suggestion for a rule:**
+```
+*synapse suggest "Use TypeScript strict mode"
+```
+Analyzes the rule content and suggests the best-fit domain.
+
+## Command Categories Summary
+
+```
+Automatic per-event     -> HOOK   (synapse-engine.js, UserPromptSubmit)
+User guidance/learning  -> SKILL  (synapse/SKILL.md + references)
+User-invoked CRUD       -> COMMAND (synapse/manager.md + 6 tasks)
+Read-state star-cmds    -> HOOK L7 (*synapse status, *synapse debug, *brief, *dev)
+Write-file star-cmds    -> COMMAND (*synapse create, *synapse add, *synapse toggle)
+```
+
+## Source Files
+
+| File | Purpose |
+|------|---------|
+| `.synapse/commands` | Star-command rule definitions (L7) |
+| `.claude/commands/synapse/manager.md` | CRUD command router |
+| `.claude/commands/synapse/tasks/*.md` | Individual CRUD task workflows |
+| `.claude/commands/synapse/templates/` | Domain and manifest templates |
+| `.claude/commands/synapse/utils/manifest-parser-reference.md` | Parser format reference |

package/payload/.claude/skills/synapse/references/domains.md

@@ -0,0 +1,126 @@
+# SYNAPSE Domains Reference
+
+## What is a Domain?
+
+A domain is a text file containing KEY=VALUE rules that SYNAPSE injects into prompts. Each domain maps to a specific layer (L0-L7) and is registered in the manifest file (`.synapse/manifest`).
+
+Domains live in `.synapse/` and use a simple KEY=VALUE format with comments.
+
+## Domain Types by Layer
+
+| Layer | Type | Trigger | Example Files |
+|-------|------|---------|---------------|
+| L0 | Constitution | Always active (`ALWAYS_ON=true`, `NON_NEGOTIABLE=true`) | `constitution` |
+| L1 | Global | Always active (`ALWAYS_ON=true`) | `global`, `context` |
+| L2 | Agent-scoped | Active agent matches `AGENT_TRIGGER` | `agent-dev`, `agent-qa`, `agent-architect` |
+| L3 | Workflow-scoped | Active workflow matches `WORKFLOW_TRIGGER` | `workflow-sdc`, `workflow-qa-loop` |
+| L4 | Task context | Active task detected in session | (injected dynamically) |
+| L5 | Squad discovery | Squad is active in session | (squad domains) |
+| L6 | Keyword (RECALL) | User prompt contains keyword from `RECALL` field | (keyword-triggered domains) |
+| L7 | Star-commands | User types `*command` in prompt | `commands` |
+
+## KEY=VALUE Format
+
+### Syntax Rules
+
+```
+# Comments start with #
+# Empty lines are ignored
+
+# Keys use SCREAMING_SNAKE_CASE with domain prefix
+DOMAINPREFIX_RULE_0=First rule text
+DOMAINPREFIX_RULE_1=Second rule text
+
+# Grouped comments describe rule sections
+# [section-name] COMMAND:
+#   0. First behavior
+#   1. Second behavior
+```
+
+### Key Naming Convention
+
+```
+{DOMAIN_KEY}_RULE_{INDEX}={RULE_TEXT}
+```
+
+- `DOMAIN_KEY`: Unique prefix matching manifest registration (e.g., `CONSTITUTION`, `GLOBAL`, `AGENT_DEV`)
+- `RULE`: Literal word `RULE` (or `STATE`, `ALWAYS_ON`, etc. for manifest keys)
+- `INDEX`: Zero-based integer or descriptive suffix
+- `RULE_TEXT`: Plain text rule content
+
+### Example: Agent Domain
+
+```
+# SYNAPSE Agent Domain: @dev (L2)
+# Agent-scoped rules for developer agent
+# Source: .aiox-core/development/agents/dev.md
+
+AGENT_DEV_RULE_0=Follow story tasks sequentially — read task, implement, test, mark [x]
+AGENT_DEV_RULE_1=ONLY update Dev Agent Record sections in story files
+AGENT_DEV_RULE_2=Run CodeRabbit pre-commit review before marking story complete
+```
+
+### Example: Workflow Domain
+
+```
+# SYNAPSE Workflow Domain: Story Development (L3)
+
+WORKFLOW_SDC_RULE_0=Follow SDC phases: Create → Validate → Implement → QA Gate
+WORKFLOW_SDC_RULE_1=Update story checkboxes as tasks complete
+```
+
+## Manifest Registration
+
+Every domain must be registered in `.synapse/manifest`. The manifest uses the same KEY=VALUE format:
+
+### Required Manifest Keys
+
+| Key | Purpose | Example |
+|-----|---------|---------|
+| `{PREFIX}_STATE` | Domain active state (`active` or `inactive`) | `AGENT_DEV_STATE=active` |
+
+### Optional Manifest Keys
+
+| Key | Purpose | Example |
+|-----|---------|---------|
+| `{PREFIX}_ALWAYS_ON` | Domain always loaded (L0, L1) | `CONSTITUTION_ALWAYS_ON=true` |
+| `{PREFIX}_NON_NEGOTIABLE` | Cannot be overridden (L0 only) | `CONSTITUTION_NON_NEGOTIABLE=true` |
+| `{PREFIX}_AGENT_TRIGGER` | Activate when agent matches (L2) | `AGENT_DEV_AGENT_TRIGGER=dev` |
+| `{PREFIX}_WORKFLOW_TRIGGER` | Activate when workflow matches (L3) | `WORKFLOW_SDC_WORKFLOW_TRIGGER=sdc` |
+| `{PREFIX}_RECALL` | Keywords that trigger domain (L6) | `MYLIB_RECALL=react,hooks` |
+| `{PREFIX}_EXCLUDE` | Agents/contexts to exclude from | `MYLIB_EXCLUDE=qa` |
+
+### Current Manifest Domains
+
+The manifest at `.synapse/manifest` registers:
+- 1 Constitution domain (L0, NON_NEGOTIABLE, ALWAYS_ON)
+- 2 Global domains (L1, ALWAYS_ON): `global`, `context`
+- 1 Commands domain (L7): `commands`
+- 12 Agent domains (L2): one per core agent (`agent-dev`, `agent-qa`, etc.)
+- 4 Workflow domains (L3): `sdc`, `qa-loop`, `spec`, `brownfield` (triggers; keys `WORKFLOW_SDC`, `WORKFLOW_QA_LOOP`, `WORKFLOW_SPEC`, `WORKFLOW_BROWNFIELD`)
+
+## Creating Custom Domains
+
+Use the CRUD command to create a new domain:
+
+```
+*synapse create
+```
+
+This will:
+1. Ask for domain name, layer, and description
+2. Create the domain file in `.synapse/`
+3. Add the manifest entry to `.synapse/manifest`
+4. Validate the format is parseable by domain-loader
+
+For the domain file template, see: `.claude/commands/synapse/templates/domain-template`
+
+For the manifest entry template, see: `.claude/commands/synapse/templates/manifest-entry-template`
+
+## Source Files
+
+| File | Purpose |
+|------|---------|
+| `.synapse/manifest` | Central domain registry |
+| `.synapse/*` | Domain content files |
+| `.aiox-core/core/synapse/domain/domain-loader.js` | Domain parser (SYN-1) |

package/payload/.claude/skills/synapse/references/layers.md

@@ -0,0 +1,186 @@
+# SYNAPSE 8-Layer Architecture Reference
+
+## Overview
+
+SYNAPSE processes rules through an 8-layer pipeline executed sequentially on every prompt. Each layer has a specific purpose, trigger condition, and priority level. The engine orchestrator (`.aiox-core/core/synapse/engine.js`) chains all layers and the output formatter produces the final `<synapse-rules>` XML block.
+
+## Layer Pipeline
+
+```
+L0 Constitution → L1 Global → L2 Agent → L3 Workflow → L4 Task → L5 Squad → L6 Keyword → L7 Star-Command
+```
+
+Layers execute in order. Each layer's output is collected and passed to the formatter.
+
+## Layer Details
+
+### L0: Constitution (NON-NEGOTIABLE)
+
+| Property | Value |
+|----------|-------|
+| **Purpose** | Enforce inviolable framework principles (6 articles) |
+| **Trigger** | Always active (`ALWAYS_ON=true`, `NON_NEGOTIABLE=true`) |
+| **Priority** | Highest — cannot be overridden by any other layer |
+| **Domain file** | `.synapse/constitution` |
+| **Source** | Auto-generated from `.aiox-core/constitution.md` via `generate-constitution.js` |
+| **Implementation** | `.aiox-core/core/synapse/layers/l0-constitution.js` |
+
+**Articles:** CLI First, Agent Authority, Story-Driven Development, No Invention, Quality First, Absolute Imports.
+
+### L1: Global + Context
+
+| Property | Value |
+|----------|-------|
+| **Purpose** | Universal rules applied to all prompts + bracket-specific behavior |
+| **Trigger** | Always active (`ALWAYS_ON=true`) |
+| **Priority** | High — applies to every prompt regardless of context |
+| **Domain files** | `.synapse/global`, `.synapse/context` |
+| **Implementation** | `.aiox-core/core/synapse/layers/l1-global.js` |
+
+**Content:** Coding standards, import rules, TypeScript rules, error handling patterns, bracket-specific context rules.
+
+### L2: Agent-Scoped
+
+| Property | Value |
+|----------|-------|
+| **Purpose** | Inject agent-specific rules when an agent is active |
+| **Trigger** | `AGENT_TRIGGER` matches active agent ID from session |
+| **Priority** | Medium-high — only active when agent is activated |
+| **Domain files** | `.synapse/agent-dev`, `.synapse/agent-qa`, `.synapse/agent-architect`, etc. (12 total) |
+| **Implementation** | `.aiox-core/core/synapse/layers/l2-agent.js` |
+
+**Agents covered:** dev, qa, architect, pm, po, sm, devops, analyst, data-engineer, ux (ux-design-expert), aiox-master, squad-creator.
+
+### L3: Workflow-Scoped
+
+| Property | Value |
+|----------|-------|
+| **Purpose** | Inject workflow-specific rules when a workflow is active |
+| **Trigger** | `WORKFLOW_TRIGGER` matches active workflow from session |
+| **Priority** | Medium — active during specific development workflows |
+| **Domain files** | `.synapse/workflow-sdc`, `.synapse/workflow-qa-loop`, `.synapse/workflow-spec`, `.synapse/workflow-brownfield` |
+| **Implementation** | `.aiox-core/core/synapse/layers/l3-workflow.js` |
+
+### L4: Task Context
+
+| Property | Value |
+|----------|-------|
+| **Purpose** | Inject context about the currently active task |
+| **Trigger** | Active task detected in session state |
+| **Priority** | Medium — active during task execution |
+| **Domain files** | Dynamic (injected from session context) |
+| **Implementation** | `.aiox-core/core/synapse/layers/l4-task.js` |
+
+### L5: Squad Discovery
+
+| Property | Value |
+|----------|-------|
+| **Purpose** | Discover and inject rules from active squad domains |
+| **Trigger** | Squad is active in session |
+| **Priority** | Medium-low — only when working with squads |
+| **Domain files** | Squad-specific domains (discovered at runtime) |
+| **Implementation** | `.aiox-core/core/synapse/layers/l5-squad.js` |
+
+### L6: Keyword (RECALL)
+
+| Property | Value |
+|----------|-------|
+| **Purpose** | Activate domains when user prompt contains matching keywords |
+| **Trigger** | User prompt contains keyword listed in domain's `RECALL` field |
+| **Priority** | Low — optional, skipped in DEPLETED bracket to conserve tokens |
+| **Domain files** | Any domain with `RECALL` key in manifest |
+| **Implementation** | `.aiox-core/core/synapse/layers/l6-keyword.js` |
+
+### L7: Star-Command
+
+| Property | Value |
+|----------|-------|
+| **Purpose** | Detect and inject mode-switching commands (`*brief`, `*dev`, `*synapse status`, etc.) |
+| **Trigger** | User types `*command` in prompt |
+| **Priority** | Highest for explicit commands — user intent is paramount |
+| **Domain file** | `.synapse/commands` |
+| **Implementation** | `.aiox-core/core/synapse/layers/l7-star-command.js` |
+
+## Pipeline Execution Flow
+
+```
+1. Hook receives UserPromptSubmit event (stdin JSON)
+2. Engine calculates context bracket (prompt count → percent → bracket)
+3. Engine determines active layers for current bracket
+4. For each active layer (L0 → L7):
+   a. Layer processor loads relevant domain(s)
+   b. Rules are filtered/resolved
+   c. Layer output is collected
+5. Memory bridge consulted (if pro available, DEPLETED/CRITICAL brackets)
+6. Formatter assembles <synapse-rules> XML within token budget
+7. Output written to stdout (appended to user prompt)
+```
+
+## Conflict Resolution
+
+When rules from different layers conflict:
+
+1. **NON_NEGOTIABLE wins** — L0 Constitution rules cannot be overridden
+2. **Higher layer number = more specific** — L7 Star-Command overrides L1 Global for the current prompt
+3. **Agent > Global** — L2 agent-scoped rules take precedence over L1 global rules
+4. **Workflow > Agent** — L3 workflow rules can augment L2 agent rules
+5. **Explicit > Implicit** — Star-commands (explicit user intent) override automatic rules
+
+## Output Format
+
+The formatter produces XML output:
+
+```xml
+<synapse-rules>
+[CONTEXT BRACKET: MODERATE] 40-60% context remaining — all layers active
+[CONSTITUTION] (NON-NEGOTIABLE) CLI First | Agent Authority | Story-Driven | No Invention | Quality First | Absolute Imports
+[ACTIVE AGENT: @dev] Follow story tasks, update Dev Agent Record only, CodeRabbit pre-commit
+[ACTIVE WORKFLOW: sdc] Follow SDC phases, update checkboxes
+[TASK CONTEXT] Current task details
+[SQUAD: mmos] Squad-specific rules
+[STAR-COMMANDS] *dev: Code over explanation, minimal changes
+[DEVMODE STATUS] Pipeline metrics (if DEVMODE=true)
+[LOADED DOMAINS SUMMARY] constitution, global, context, agent-dev, workflow-sdc, commands
+</synapse-rules>
+```
+
+**Section ordering** (highest priority first):
+1. CONTEXT_BRACKET
+2. CONSTITUTION
+3. AGENT
+4. WORKFLOW
+5. TASK
+6. SQUAD
+7. KEYWORD
+8. MEMORY_HINTS
+9. STAR_COMMANDS
+10. DEVMODE
+11. SUMMARY
+
+## Performance Targets
+
+| Metric | Target | Hard Limit |
+|--------|--------|------------|
+| Total pipeline | <70ms | <100ms |
+| Individual layer | <15ms | <20ms (L0/L7: <5ms) |
+| Startup (.synapse/ discovery) | <5ms | <10ms |
+| Session I/O | <10ms | <15ms |
+
+**Timeout behavior:** If any layer exceeds its time limit, it is skipped with a warning. The pipeline never blocks the prompt.
+
+## Source Files
+
+| File | Purpose |
+|------|---------|
+| `.aiox-core/core/synapse/engine.js` | SynapseEngine orchestrator |
+| `.aiox-core/core/synapse/layers/l0-constitution.js` | L0 processor |
+| `.aiox-core/core/synapse/layers/l1-global.js` | L1 processor |
+| `.aiox-core/core/synapse/layers/l2-agent.js` | L2 processor |
+| `.aiox-core/core/synapse/layers/l3-workflow.js` | L3 processor |
+| `.aiox-core/core/synapse/layers/l4-task.js` | L4 processor |
+| `.aiox-core/core/synapse/layers/l5-squad.js` | L5 processor |
+| `.aiox-core/core/synapse/layers/l6-keyword.js` | L6 processor |
+| `.aiox-core/core/synapse/layers/l7-star-command.js` | L7 processor |
+| `.aiox-core/core/synapse/layers/layer-processor.js` | Abstract base class |
+| `.aiox-core/core/synapse/output/formatter.js` | XML formatter + token budget |
+| `.claude/hooks/synapse-engine.js` | Hook entry point |

package/payload/.claude/skills/synapse/references/manifest.md

@@ -0,0 +1,142 @@
+# SYNAPSE Manifest Reference
+
+## Overview
+
+The manifest (`.synapse/manifest`) is the central registry for all SYNAPSE domains. It uses a KEY=VALUE format and determines which domains are loaded, when they activate, and how they behave.
+
+The manifest is parsed by `domain-loader.js` (`.aiox-core/core/synapse/domain/domain-loader.js`) on every prompt.
+
+## File Format
+
+```
+# Comments start with #
+# Empty lines are ignored
+
+# Debug mode toggle
+DEVMODE=false
+
+# Domain registration: {PREFIX}_{KEY}={VALUE}
+CONSTITUTION_STATE=active
+CONSTITUTION_ALWAYS_ON=true
+CONSTITUTION_NON_NEGOTIABLE=true
+```
+
+## Valid Keys
+
+Every domain is identified by a unique prefix (e.g., `CONSTITUTION`, `GLOBAL`, `AGENT_DEV`). The following keys are valid for each prefix:
+
+### Required Keys
+
+| Key | Type | Description |
+|-----|------|-------------|
+| `{PREFIX}_STATE` | `active` \| `inactive` | Whether the domain is loaded. Required for every domain. |
+
+### Optional Keys
+
+| Key | Type | Description | Used By |
+|-----|------|-------------|---------|
+| `{PREFIX}_ALWAYS_ON` | `true` \| `false` | Domain always loaded regardless of context | L0, L1 |
+| `{PREFIX}_NON_NEGOTIABLE` | `true` \| `false` | Rules cannot be overridden by other layers | L0 only |
+| `{PREFIX}_AGENT_TRIGGER` | agent ID string | Activate when this agent is active | L2 |
+| `{PREFIX}_WORKFLOW_TRIGGER` | workflow ID string | Activate when this workflow is active | L3 |
+| `{PREFIX}_RECALL` | comma-separated keywords | Activate when user prompt contains keyword | L6 |
+| `{PREFIX}_EXCLUDE` | comma-separated values | Contexts/agents to exclude domain from | Any |
+
+### Global Key
+
+| Key | Type | Description |
+|-----|------|-------------|
+| `DEVMODE` | `true` \| `false` | Enable debug metrics in output |
+
+## Complete Manifest Example
+
+Below is the current manifest structure (from `.synapse/manifest`):
+
+```
+# Debug mode
+DEVMODE=false
+
+# Layer 0: Constitution (NON-NEGOTIABLE)
+CONSTITUTION_STATE=active
+CONSTITUTION_ALWAYS_ON=true
+CONSTITUTION_NON_NEGOTIABLE=true
+
+# Layer 1: Global (ALWAYS_ON)
+GLOBAL_STATE=active
+GLOBAL_ALWAYS_ON=true
+
+# Layer 1: Context brackets (ALWAYS_ON)
+CONTEXT_STATE=active
+CONTEXT_ALWAYS_ON=true
+
+# Layer 7: Star-commands
+COMMANDS_STATE=active
+
+# Layer 2: Agent-scoped domains
+AGENT_DEV_STATE=active
+AGENT_DEV_AGENT_TRIGGER=dev
+AGENT_QA_STATE=active
+AGENT_QA_AGENT_TRIGGER=qa
+AGENT_ARCHITECT_STATE=active
+AGENT_ARCHITECT_AGENT_TRIGGER=architect
+# ... (12 agent domains total)
+
+# Layer 3: Workflow domains
+WORKFLOW_SDC_STATE=active
+WORKFLOW_SDC_WORKFLOW_TRIGGER=sdc
+WORKFLOW_EPIC_CREATE_STATE=active
+WORKFLOW_EPIC_CREATE_WORKFLOW_TRIGGER=epic_creation
+WORKFLOW_ARCH_REVIEW_STATE=active
+WORKFLOW_ARCH_REVIEW_WORKFLOW_TRIGGER=architecture_review
+```
+
+## Domain-to-File Mapping
+
+The domain-loader resolves domain prefixes to files in `.synapse/`:
+
+| Prefix | File | Layer |
+|--------|------|-------|
+| `CONSTITUTION` | `.synapse/constitution` | L0 |
+| `GLOBAL` | `.synapse/global` | L1 |
+| `CONTEXT` | `.synapse/context` | L1 |
+| `COMMANDS` | `.synapse/commands` | L7 |
+| `AGENT_DEV` | `.synapse/agent-dev` | L2 |
+| `AGENT_QA` | `.synapse/agent-qa` | L2 |
+| `WORKFLOW_SDC` | `.synapse/workflow-sdc` | L3 |
+
+**Naming convention:** The prefix is derived from the filename by:
+1. Converting to SCREAMING_SNAKE_CASE
+2. Removing hyphens and replacing with underscores
+
+## Troubleshooting
+
+### Domain Not Loading
+
+1. Check `{PREFIX}_STATE=active` in manifest
+2. Verify the domain file exists in `.synapse/`
+3. For L2 domains: verify `AGENT_TRIGGER` matches the active agent ID
+4. For L3 domains: verify `WORKFLOW_TRIGGER` matches the active workflow
+5. Run `*synapse debug` to see manifest parse results
+
+### Invalid Format Errors
+
+- Keys must use SCREAMING_SNAKE_CASE
+- Values cannot contain newlines
+- No spaces around `=` sign
+- Comments must start with `#` at the beginning of the line
+
+### Adding a New Domain
+
+Use `*synapse create` or manually:
+1. Create the domain file in `.synapse/` with KEY=VALUE rules
+2. Add the registration keys to `.synapse/manifest`
+3. Run `*synapse reload` to reload from disk
+
+## Source Files
+
+| File | Purpose |
+|------|---------|
+| `.synapse/manifest` | The manifest file itself |
+| `.aiox-core/core/synapse/domain/domain-loader.js` | Manifest parser + domain file loader |
+| `.claude/commands/synapse/utils/manifest-parser-reference.md` | Detailed parser format spec |
+| `.claude/commands/synapse/templates/manifest-entry-template` | Template for new manifest entries |

package/payload/.claude/skills/tdd/SKILL.md

@@ -0,0 +1,22 @@
+---
+name: tdd
+description: Test-driven build loop — red, green, refactor. Use when building a feature or fixing a bug; write a failing test first, make it pass, then refactor with the suite green.
+---
+
+# TDD — the kernel build loop
+
+The canonical build stage of the WRXN pipeline (grill → research → prototype → PRD → issues →
+verticality review → **tdd** → code review → security review → QA-walk → operator accepts).
+
+## The loop
+
+1. **Red** — write one failing test that pins the next slice of behavior at the highest seam
+   (public interface, not internals). Run it; watch it fail for the right reason.
+2. **Green** — write the minimum code to pass. Nothing speculative.
+3. **Refactor** — clean up with the suite green. Behavior unchanged.
+
+## Rules
+
+- Tests and typecheck pass on **every commit** (Constitution Art. III). A red commit is not done.
+- Test external behavior, not implementation — internals stay refactorable.
+- One slice = one tracer bullet: independently buildable and walkable (Constitution Art. II).