@softspark/ai-toolkit 2.9.0 → 2.10.1

package/app/skills/plan/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: plan
-description: "Plan implementation with tasks and success criteria"
+description: "Breaks down feature requests and project goals into phased implementation plans with task lists, agent assignments, dependency graphs, and success criteria. Use when the user asks to plan a feature, create an implementation roadmap, break down a coding task, or outline project phases."
 user-invocable: true
 effort: high
 argument-hint: "[goal]"
@@ -11,71 +11,14 @@ allowed-tools: Read, Grep, Glob
 
 $ARGUMENTS
 
-Create a structured plan for a new project or feature.
+## Workflow
 
-## Usage
-
-```
-/plan [description]
-```
-
-## What This Command Does
-
-1. **Analyzes** the request
-2. **Identifies** project type and tech stack
-3. **Breaks down** into tasks
-4. **Creates** plan file with agent assignments
-
-## Plan File Output
-
-Creates a `{project-slug}.md` file in project root:
-
-```markdown
-# {Project Name} - Implementation Plan
-
-## Overview
-- **Type**: [Web App / Mobile App / API / etc.]
-- **Stack**: [Tech choices]
-- **Complexity**: [Low / Medium / High]
-
-## Requirements
-1. [Requirement 1]
-2. [Requirement 2]
-
-## Task Breakdown
-
-### Phase 1: Foundation
-- [ ] Task 1 (Agent: backend-specialist)
-- [ ] Task 2 (Agent: database-architect)
-
-### Phase 2: Core Features
-- [ ] Task 3 (Agent: frontend-specialist)
-- [ ] Task 4 (Agent: backend-specialist)
-
-### Phase 3: Polish
-- [ ] Task 5 (Agent: test-engineer)
-- [ ] Task 6 (Agent: devops-implementer)
-
-## Agent Assignment
-
-| Task | Agent | Dependencies |
-|------|-------|--------------|
-| Database | database-architect | None |
-| API | backend-specialist | Database |
-| UI | frontend-specialist | API |
-| Tests | test-engineer | All above |
-
-## File Structure
-```
-project/
-├── src/
-└── ...
-```
-
-## Success Criteria
-- [ ] Criterion 1
-- [ ] Criterion 2
-```
+1. **Analyze scope**: read the goal, scan relevant source files to understand current state
+2. **Detect project type**: match keywords to determine stack and primary agents (see table below)
+3. **Break into phases**: group tasks by dependency order (foundation, core, polish)
+4. **Assign agents**: map each task to the best-fit agent with explicit dependencies
+5. **Write plan file**: create `{project-slug}.md` in project root using [templates/plan-template.md](templates/plan-template.md)
+6. **Validate**: confirm every requirement maps to at least one task, no circular dependencies exist, and success criteria are measurable
 
 ## Project Type Detection
 
@@ -83,44 +26,29 @@ project/
 |----------|------|----------------|
 | landing, website | Static Site | frontend-specialist |
 | dashboard, admin | Web App | frontend + backend |
-| api, rest | API Only | backend-specialist |
+| api, rest, graphql | API Only | backend-specialist |
 | mobile, ios, android | Mobile | mobile-developer |
-| game, unity | Game | game-developer |
+| cli, terminal | CLI Tool | backend-specialist |
 
-## PLAN MODE RULES
+## Planning Constraints
 
-During planning:
-- Create plan documents
-- Define tasks and structure
-- NO code writing
-- NO file creation (except plan)
-
-## Common Rationalizations
-
-| Excuse | Why It's Wrong |
-|--------|----------------|
-| "We already know what to build" | Assumed requirements lead to rework — validate assumptions explicitly |
-| "Planning is wasted time, just start coding" | Unplanned work has 3-5x more rework — 30 min planning saves days |
-| "The requirements will change anyway" | Plans adapt — without one, you can't assess impact of changes |
-| "It's a small feature, no plan needed" | Small features in complex systems have hidden dependencies — map them |
-| "We'll figure it out as we go" | Discovery without structure leads to scope creep and missed edge cases |
-
-## Next Steps
-
-After plan approval:
-1. Use `/orchestrate` to execute with agents
-2. Or manually invoke specific agents
+- Create plan documents only, NO code writing, NO file creation (except the plan)
+- Each task must name affected file(s) and a single owning agent
+- Phases must have explicit dependency edges (`Phase 1 -> Phase 2`)
+- Success criteria must be verifiable (command to run, expected output, or observable behavior)
 
 ## KB Integration
 
 Before planning:
+
 ```python
 smart_query("project template: {type}")
 hybrid_search_kb("architecture {pattern}")
 ```
 
 ## Related Skills
-- Plan approved? → `/orchestrate` or `/workflow` to execute with agents
-- Need requirements first? → `/write-a-prd` for structured product requirements
-- Want to stress-test the plan? → `/grill-me` for Socratic questioning
-- Ready to break into issues? → `/prd-to-plan` → `/triage-issue`
+
+- Plan approved? -> `/orchestrate` or `/workflow` to execute with agents
+- Need requirements first? -> `/write-a-prd` for structured product requirements
+- Want to stress-test the plan? -> `/grill-me` for Socratic questioning
+- Ready to break into issues? -> `/prd-to-plan` -> `/triage-issue`

package/app/skills/predict/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: predict
-description: "Predict regressions and impact before changes land"
+description: "Analyzes code diffs and file changes to identify potential regressions, maps dependency impact across the codebase, and generates a risk-scored impact report. Use when reviewing pull requests, assessing code change risk, checking for breaking changes, or analyzing the blast radius of a diff."
 effort: medium
 disable-model-invocation: true
 argument-hint: "[change description]"
@@ -13,18 +13,66 @@ allowed-tools: Read, Grep, Glob
 
 $ARGUMENTS
 
-Triggers the Predictive Analyst to assess impact.
+Triggers the Predictive Analyst to assess the impact and regression risk of proposed changes.
 
 ## Usage
 
 ```bash
 /predict [path_or_diff]
-# Example: /predict src/auth
-# Example: /predict --diff (analyzes uncommitted changes)
+# /predict src/auth              : analyze all files under src/auth
+# /predict --diff                : analyze uncommitted changes (git diff)
+# /predict src/api/routes.ts     : analyze a single file
 ```
 
 ## Protocol
-1. **Scope**: Identify target files.
-2. **Trace**: Build dependency graph.
-3. **Assess**: Calculate risk score.
-4. **Report**: Generate Impact Prediction.
+
+### 1. Scope: Identify Target Files
+
+- If path provided: collect all files under that path
+- If `--diff`: run `git diff --name-only` to get changed files
+- List each file with its last-modified date and line count
+
+### 2. Trace: Build Dependency Graph
+
+For each target file, find dependents:
+
+```bash
+# Find files that import/require the target
+grep -rl "import.*from.*[target]" --include="*.ts" --include="*.py" --include="*.js" .
+grep -rl "require.*[target]" --include="*.js" --include="*.ts" .
+```
+
+Build a graph: `changed file, direct dependents, transitive dependents (1 level)`
+
+### 3. Assess: Calculate Risk Score
+
+Score each changed file on a 1 to 5 scale:
+
+| Factor | Weight | Scoring |
+|--------|--------|---------|
+| Dependent count | 30% | 0 deps = 1, 1 to 3 = 2, 4 to 10 = 3, 11 to 20 = 4, 21+ = 5 |
+| Test coverage | 30% | Has dedicated test = 1, partial = 3, none = 5 |
+| Change surface | 20% | < 10 lines = 1, 10 to 50 = 2, 50 to 200 = 3, 200+ = 5 |
+| Shared/core file | 20% | Leaf = 1, mid-layer = 3, core/shared = 5 |
+
+**Overall risk** = weighted average rounded to nearest integer.
+
+### 4. Report: Generate Impact Prediction
+
+Output a markdown report:
+
+```markdown
+## Impact Prediction: [scope]
+
+| File | Risk | Dependents | Test Coverage | Notes |
+|------|------|------------|---------------|-------|
+| src/auth/login.ts | 4/5 | 12 files | partial | Core auth flow |
+
+### High-Risk Changes (score >= 4)
+- [file]: [why it's high risk and what to watch]
+
+### Recommended Actions
+- [ ] Add tests for [untested file]
+- [ ] Review [high-dependent file] with extra scrutiny
+- [ ] Run integration tests covering [affected area]
+```

package/app/skills/refactor-plan/SKILL.md

@@ -110,3 +110,4 @@ What is explicitly NOT part of this refactor.
 - No file paths or code snippets in the issue (durability)
 - File immediately via `gh issue create` — don't ask for review
 - Interview thoroughly before planning
+- **Dead code cleanup is mandatory per step, not deferred** (Constitution Art. VI.1): every refactor step must leave the repo with zero orphaned references. "We'll delete the old code in a later step" is only acceptable for transitional double-write / expand-contract phases where both paths are temporarily live — and the cleanup step must be explicitly listed in the plan, not implied.

package/app/skills/teams/SKILL.md

@@ -1,21 +1,17 @@
 ---
 name: teams
-description: "Launch pre-configured Agent Teams for common workflows"
+description: "Launches pre-configured multi-agent teams for code review, debugging, feature development, security audits, and database migrations. Use when the user asks to start a multi-agent workflow, coordinate agent teams, run a team review, or needs parallel agent collaboration on a complex task."
 effort: max
 user-invocable: true
 argument-hint: "<preset> [task-description]"
 allowed-tools: Bash, Read, Write, Edit, Glob, Grep, Agent, TeamCreate, TeamDelete, SendMessage, TaskCreate, TaskList, TaskUpdate, TaskGet
 ---
 
-# /teams - Agent Teams Presets
+# /teams: Agent Teams Presets
 
 $ARGUMENTS
 
-## What This Does
-
-Launches a pre-configured Agent Teams composition for your task.
-
-Requires: `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`
+Launches a pre-configured Agent Teams composition for your task. Requires `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`.
 
 ## Available Presets
 
@@ -29,70 +25,36 @@ Requires: `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`
 | `security` | security-architect, security-auditor, backend-specialist | Security audit |
 | `migration` | database-architect, backend-specialist, devops-implementer | Database migration |
 
-## Usage Examples
+See [reference/presets.md](reference/presets.md) for detailed ownership, aggregation strategies, and output formats for each preset.
+
+## Usage
 
 ```
-/teams review           # Launch review team on current changes
-/teams debug            # Launch debug team for current issue
-/teams feature          # Launch feature team for new feature
-/teams security         # Launch security audit team
-/teams migration        # Launch migration team
+/teams review              # Launch review team on current changes
+/teams debug               # Launch debug team for current issue
+/teams feature add auth    # Launch feature team with task context
+/teams security            # Launch security audit team
 ```
 
-## Preset Definitions
-
-### review
-- **Agents**: code-reviewer (lead), security-auditor, performance-optimizer
-- **Ownership**: code-reviewer owns review summary; others own their domain reports
-- **Aggregation**: consensus — flag issues found by 2+ agents as high priority
-- **Output**: `REVIEW.md` with severity-ranked findings
-
-### debug
-- **Agents**: debugger (lead), backend-specialist, incident-responder
-- **Ownership**: debugger owns root-cause analysis; others own hypothesis testing
-- **Aggregation**: relay — debugger synthesizes findings from others
-- **Output**: `DEBUG_REPORT.md` with root cause and fix
-
-### feature
-- **Agents**: orchestrator (lead), backend-specialist, frontend-specialist, test-engineer
-- **Ownership**: orchestrator owns plan; specialists own their files; test-engineer owns tests
-- **Aggregation**: map-reduce — orchestrator integrates all outputs
-- **Output**: implemented feature + tests
-
-### fullstack
-- **Agents**: backend-specialist, frontend-specialist, database-architect, devops-implementer
-- **Ownership**: each agent owns their layer (API, UI, DB, infra)
-- **Aggregation**: relay — backend-specialist synthesizes integration
-- **Output**: full stack implementation
-
-### research
-- **Agents**: technical-researcher (lead), data-analyst, prompt-engineer
-- **Ownership**: technical-researcher owns synthesis; others own domain findings
-- **Aggregation**: consensus — areas of agreement highlighted
-- **Output**: `RESEARCH.md` with findings and recommendations
-
-### security
-- **Agents**: security-architect (lead), security-auditor, backend-specialist
-- **Ownership**: security-architect owns threat model; auditor owns findings; backend owns remediation
-- **Aggregation**: relay — security-architect integrates all
-- **Output**: `SECURITY_AUDIT.md` with CVSS-scored findings
-
-### migration
-- **Agents**: database-architect (lead), backend-specialist, devops-implementer
-- **Ownership**: database-architect owns schema; backend owns code changes; devops owns deployment
-- **Aggregation**: relay — database-architect coordinates sequence
-- **Output**: migration scripts + rollback plan + deployment runbook
-
-## Steps
-
-1. Parse `$ARGUMENTS` to extract `<preset>` and optional `[task-description]`
-2. Validate preset is one of: review, debug, feature, fullstack, research, security, migration
-3. Check `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS` is set; warn if not
-4. Display the team composition and ownership rules
-5. Ask user to confirm before launching
-6. Launch the appropriate agents using the Agent tool with the task description
-7. Apply the aggregation strategy to synthesize results
-8. Produce the defined output document
+## Workflow
+
+1. **Parse** `$ARGUMENTS`: extract `<preset>` and optional `[task-description]`
+2. **Validate** preset is one of: review, debug, feature, fullstack, research, security, migration
+3. **Check environment**: verify `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS` is set; warn if missing
+4. **Display** team composition and ownership rules from [reference/presets.md](reference/presets.md)
+5. **Confirm** with user before launching
+6. **Launch agents**: spawn each agent with its assigned scope using the Agent tool:
+   ```
+   Agent({ description: "code-reviewer: PR review lead", prompt: "[task + ownership rules]" })
+   Agent({ description: "security-auditor: security findings", prompt: "[task + domain scope]" })
+   ```
+7. **Aggregate results**: apply the preset's aggregation strategy (consensus, relay, or map-reduce)
+8. **Produce output**: write the defined output document (e.g., `REVIEW.md`, `DEBUG_REPORT.md`)
+
+### Error Handling
+
+- If an agent fails or times out: log the failure, continue with remaining agents, note the gap in the output
+- If agents produce conflicting findings: the lead agent resolves conflicts; flag unresolved disagreements for user review
 
 ## Environment
 

package/app/skills/teams/reference/presets.md

@@ -0,0 +1,52 @@
+# Agent Teams Preset Definitions
+
+Detailed configuration for each `/teams` preset. Each preset defines agents, ownership, aggregation strategy, and output format.
+
+## review
+
+- **Agents**: code-reviewer (lead), security-auditor, performance-optimizer
+- **Ownership**: code-reviewer owns review summary; others own their domain reports
+- **Aggregation**: consensus (flag issues found by 2+ agents as high priority)
+- **Output**: `REVIEW.md` with severity-ranked findings
+
+## debug
+
+- **Agents**: debugger (lead), backend-specialist, incident-responder
+- **Ownership**: debugger owns root-cause analysis; others own hypothesis testing
+- **Aggregation**: relay (debugger synthesizes findings from others)
+- **Output**: `DEBUG_REPORT.md` with root cause and fix
+
+## feature
+
+- **Agents**: orchestrator (lead), backend-specialist, frontend-specialist, test-engineer
+- **Ownership**: orchestrator owns plan; specialists own their files; test-engineer owns tests
+- **Aggregation**: map-reduce (orchestrator integrates all outputs)
+- **Output**: implemented feature + tests
+
+## fullstack
+
+- **Agents**: backend-specialist, frontend-specialist, database-architect, devops-implementer
+- **Ownership**: each agent owns their layer (API, UI, DB, infra)
+- **Aggregation**: relay (backend-specialist synthesizes integration)
+- **Output**: full stack implementation
+
+## research
+
+- **Agents**: technical-researcher (lead), data-analyst, prompt-engineer
+- **Ownership**: technical-researcher owns synthesis; others own domain findings
+- **Aggregation**: consensus (areas of agreement highlighted)
+- **Output**: `RESEARCH.md` with findings and recommendations
+
+## security
+
+- **Agents**: security-architect (lead), security-auditor, backend-specialist
+- **Ownership**: security-architect owns threat model; auditor owns findings; backend owns remediation
+- **Aggregation**: relay (security-architect integrates all)
+- **Output**: `SECURITY_AUDIT.md` with CVSS-scored findings
+
+## migration
+
+- **Agents**: database-architect (lead), backend-specialist, devops-implementer
+- **Ownership**: database-architect owns schema; backend owns code changes; devops owns deployment
+- **Aggregation**: relay (database-architect coordinates sequence)
+- **Output**: migration scripts + rollback plan + deployment runbook

package/app/skills/verification-before-completion/SKILL.md

@@ -54,6 +54,9 @@ Skip any step = lying, not verifying
 | Regression test works | Red-green cycle verified | Test passes once |
 | Agent completed | VCS diff shows changes | Agent reports "success" |
 | Requirements met | Line-by-line checklist | Tests passing |
+| No dead code (Art. VI.1) | Grep for every removed/renamed symbol: 0 references | "I cleaned up what I touched" |
+| Behavior change covered (Art. VI.2) | Integration test for the API surface + unit test + docs updated | Unit test on the helper only |
+| Diff is clean (Art. VI.4) | Re-read full diff: no orphaned imports, no stale docs, no skipped fixes | "I only changed what I needed" |
 
 ## Red Flags — STOP
 
@@ -102,6 +105,10 @@ CORRECT:  Agent reports success → Check VCS diff → Verify changes → Report
 WRONG:    Trust agent report at face value
 ```
 
+## Constitutional Anchors
+
+This skill enforces **Constitution Art. VI.4 (Verify Before Claiming Done)**. The diff re-read is not optional: before any completion claim, confirm no orphaned references, no missing test coverage for changed paths, no stale docs. A task is not done while any of those exist.
+
 ## The Bottom Line
 
 Run the command. Read the output. THEN claim the result.

package/kb/reference/architecture-overview.md

@@ -35,7 +35,7 @@ ai-toolkit/
     rules/                   # Rules auto-injected into ~/.claude/CLAUDE.md
     hooks/                   # Hook scripts (copied to ~/.softspark/ai-toolkit/hooks/)
     hooks.json               # Hook definitions (merged into ~/.claude/settings.json)
-    constitution.md          # Immutable safety rules, 5 articles (marker-injected)
+    constitution.md          # Immutable safety rules, 6 articles (marker-injected)
     ARCHITECTURE.md          # System architecture reference (marker-injected)
     CLAUDE.md.template       # Template for project CLAUDE.md (used by init)
     settings.local.json.template
@@ -292,15 +292,16 @@ Agents (code-reviewer, debugger, devops-implementer, ...)
 
 Scripts at `~/.softspark/ai-toolkit/hooks/`. See [hooks-catalog.md](hooks-catalog.md) for details.
 
-## Constitution (5 Articles)
+## Constitution (6 Articles)
 
 | Article | Key Rule |
 |---------|----------|
-| I Safety First | No data loss, no blind execution, max 3 loop iterations |
+| I Safety First | No data loss, no blind execution, max 5 loop iterations |
 | II Hierarchy of Truth | KB is source of truth, research protocol mandatory |
 | III Operational Integrity | Green tests = Done, logs are evidence |
 | IV Self-Preservation | Constitution is read-only, kill switch via system-governor |
 | V Resource Governance | No destructive commands without confirmation |
+| VI Repair Discipline | No dead code, fix every found bug, tests and docs follow behavior, verify before done |
 
 ## Persona Presets
 

package/kb/reference/enterprise-config-guide.md

@@ -175,9 +175,9 @@ Requirements:
 
 ## Constitution Immutability
 
-- **Articles I-V** (toolkit core) are absolutely immutable
+- **Articles I-VI** (toolkit core) are absolutely immutable
 - **Base config articles** are immutable — projects cannot modify them
-- Projects can **only ADD** new articles (article 6+)
+- Projects can **only ADD** new articles (article 7+)
 
 ```json
 {

package/llms-full.txt

@@ -65,7 +65,7 @@
 - **app-builder**: Full-stack app scaffolding with stack-selection matrix: Next.js, React+Vite, Nuxt, Astro, FastAPI, Django, Laravel, React Native, Flutter, Unity. Triggers: scaffold, bootstrap, new project, starter template, build app, landing page, dashboard, API, mobile app, CLI, e-commerce, game. Load when user wants to start a new project from scratch.
 - **architecture-audit**: Explore codebase organically for architectural friction, discover shallow modules, and propose module-deepening refactors as GitHub issue RFCs using parallel sub-agent interface designs. Use when user wants to improve architecture, find shallow modules, deepen modules, or reduce coupling.
 - **architecture-decision**: Architecture decision making via trade-off analysis in RFC/RFD/ADR format: context, constraints, 3+ options, comparison, recommendation. Triggers: architecture decision, ADR, RFC, RFD, trade-offs, options comparison, design choice, pick between, should we use, evaluate approach. Load when weighing 2+ architectural options or writing decision records.
-- **biz-scan**: Scan codebase for business opportunities and KPIs
+- **biz-scan**: Scans codebase for business opportunities by analyzing database schemas, API endpoints, tracking events, and feature flags to surface underutilized capabilities, missing KPIs, and monetization gaps. Use when the user asks about revenue opportunities, business metrics, KPI coverage, analytics gaps, or monetization analysis of a codebase.
 - **brand-voice**: Loaded when writing documentation, content, README, or user-facing text. Prevents generic LLM rhetoric and enforces direct, technical voice.
 - **briefing**: Generate executive daily briefing across all agents
 - **build**: Build the project with auto-detected toolchain
@@ -90,7 +90,7 @@
 - **documentation-standards**: KB document conventions: YAML frontmatter (7 required fields), 5-category taxonomy (reference/howto/procedures/troubleshooting/best-practices), directory-category matching, validate.sh CI rules. Triggers: kb/, KB document, architecture note, SOP, runbook, howto, frontmatter, knowledge base entry, documentation standard. Load when creating or editing any file under kb/.
 - **ecommerce-patterns**: E-commerce domain patterns: cart, checkout flow, payment providers (Stripe/Adyen), order state machine, inventory, promotions, tax, B2B vs B2C. Triggers: cart, checkout, product, SKU, inventory, payment, Stripe, Shopify, Medusa, Magento, order status, promotion, tax calculation, coupon, refund. Load when working on any e-commerce feature.
 - **evaluate**: Evaluate skill quality and RAG retrieval accuracy
-- **evolve**: Evolve agent definitions via meta-architect
+- **evolve**: Analyzes failure patterns and inefficiencies in agent/skill definitions, then drafts and applies targeted improvements to system prompts, tool permissions, and behavioral rules. Use when the user asks to improve agent behavior, refine skill definitions, update system prompts, or optimize agent configurations based on observed failures.
 - **explain**: Explain code, architecture, or concepts with diagrams
 - **explore**: Explore codebase structure, stack, and architecture
 - **fix**: Auto-fix lint errors, type issues, and simple bugs
@@ -121,13 +121,13 @@
 - **panic**: Emergency stabilization via system-governor agent
 - **performance-profiling**: Performance measurement and optimization: four golden signals (latency/traffic/errors/saturation), p50/p95/p99, baseline-change-measure loop, flame graphs, load testing. Triggers: performance, slow, latency, p99, flame graph, profile, bottleneck, optimization, load test, benchmark, CPU profiling, memory leak. Load when diagnosing or optimizing slow code or services.
 - **persona**: Switch engineering persona at runtime: backend-lead, frontend-lead, devops-eng, junior-dev
-- **plan**: Plan implementation with tasks and success criteria
+- **plan**: Breaks down feature requests and project goals into phased implementation plans with task lists, agent assignments, dependency graphs, and success criteria. Use when the user asks to plan a feature, create an implementation roadmap, break down a coding task, or outline project phases.
 - **plan-writing**: Implementation plan and pre-mortem drafting: phase breakdown, success criteria, risks, rollback plan, acceptance tests, estimated effort. Triggers: implementation plan, pre-mortem, phased plan, project plan, task breakdown, success criteria, rollback strategy, risk register. Load when user asks to write a plan or pre-mortem document.
 - **plugin-creator**: Creates experimental opt-in plugin packs with manifests, conventions, and optional module scaffolding for Claude and Codex runtimes
 - **pr**: Create pull requests with pre-flight validation
 - **prd-to-issues**: Break a PRD into independently-grabbable GitHub issues using vertical slices with HITL/AFK tagging and dependency ordering. Use when user wants to convert a PRD to issues, create tickets, or break down a PRD into work items.
 - **prd-to-plan**: Convert a PRD into a phased implementation plan using tracer-bullet vertical slices. Use when user wants to break down a PRD, create an implementation plan, plan phases from a PRD, or mentions tracer bullets.
-- **predict**: Predict regressions and impact before changes land
+- **predict**: Analyzes code diffs and file changes to identify potential regressions, maps dependency impact across the codebase, and generates a risk-scored impact report. Use when reviewing pull requests, assessing code change risk, checking for breaking changes, or analyzing the blast radius of a diff.
 - **prompt-caching-patterns**: Loaded when user builds with Anthropic API and needs to cut cost or latency via prompt caching. Covers TTL, cache breakpoints, stacking, invalidation, and measuring hit rate.
 - **qa-session**: Interactive QA session where user reports bugs conversationally and agent files GitHub issues with domain language. Explores codebase in background for context. Use when user wants to report bugs, do QA, file issues conversationally, or mentions QA session.
 - **rag-patterns**: RAG architecture: embeddings, chunking strategies, hybrid search (BM25 + vector), reranking, CRAG/self-correcting, multi-hop reasoning, evaluation metrics. Triggers: RAG, embedding, vector search, pgvector, Qdrant, Pinecone, Weaviate, chunking, reranker, retrieval, hybrid search, semantic search, knowledge base, cosine similarity. Load when building or tuning RAG systems.
@@ -148,7 +148,7 @@
 - **swarm**: Execute tasks via Map-Reduce, Consensus, or Relay swarms
 - **swift-patterns**: Swift and iOS development patterns: SwiftUI, Combine, async/await, property wrappers, actors, Swift Package Manager, Core Data, UIKit interop, @MainActor. Triggers: Swift, SwiftUI, Combine, iOS, Xcode, actor, property wrapper, Core Data, SPM, UIKit, @MainActor, @State, @Binding. Load when writing or reviewing Swift code.
 - **tdd**: Test-driven development with red-green-refactor loop and vertical slices. Use when user wants TDD, test-first development, red-green-refactor, or building features with tests driving the implementation.
-- **teams**: Launch pre-configured Agent Teams for common workflows
+- **teams**: Launches pre-configured multi-agent teams for code review, debugging, feature development, security audits, and database migrations. Use when the user asks to start a multi-agent workflow, coordinate agent teams, run a team review, or needs parallel agent collaboration on a complex task.
 - **test**: Run tests with coverage analysis and reporting
 - **testing-patterns**: Testing strategy and craft: pyramid vs trophy, unit/integration/e2e split, fixtures, mocks vs fakes vs stubs, AAA pattern, flaky test diagnosis, coverage goals, property-based testing. Triggers: test, testing strategy, fixture, mock, stub, AAA, unit test, integration test, e2e, Playwright, Cypress, flaky, coverage, TDD, test pyramid. Load when writing, reviewing, or designing test suites.
 - **triage-issue**: Triage a bug by deeply exploring the codebase for root cause, then create a GitHub issue with a TDD-based fix plan. Mostly hands-off — minimal user interaction. Use when user reports a bug, wants to investigate an issue, mentions triage, or wants a fix plan.
@@ -4630,7 +4630,7 @@ ai-toolkit/
     rules/                   # Rules auto-injected into ~/.claude/CLAUDE.md
     hooks/                   # Hook scripts (copied to ~/.softspark/ai-toolkit/hooks/)
     hooks.json               # Hook definitions (merged into ~/.claude/settings.json)
-    constitution.md          # Immutable safety rules, 5 articles (marker-injected)
+    constitution.md          # Immutable safety rules, 6 articles (marker-injected)
     ARCHITECTURE.md          # System architecture reference (marker-injected)
     CLAUDE.md.template       # Template for project CLAUDE.md (used by init)
     settings.local.json.template
@@ -4887,15 +4887,16 @@ Agents (code-reviewer, debugger, devops-implementer, ...)
 
 Scripts at `~/.softspark/ai-toolkit/hooks/`. See [hooks-catalog.md](hooks-catalog.md) for details.
 
-## Constitution (5 Articles)
+## Constitution (6 Articles)
 
 | Article | Key Rule |
 |---------|----------|
-| I Safety First | No data loss, no blind execution, max 3 loop iterations |
+| I Safety First | No data loss, no blind execution, max 5 loop iterations |
 | II Hierarchy of Truth | KB is source of truth, research protocol mandatory |
 | III Operational Integrity | Green tests = Done, logs are evidence |
 | IV Self-Preservation | Constitution is read-only, kill switch via system-governor |
 | V Resource Governance | No destructive commands without confirmation |
+| VI Repair Discipline | No dead code, fix every found bug, tests and docs follow behavior, verify before done |
 
 ## Persona Presets
 
@@ -6520,9 +6521,9 @@ Requirements:
 
 ## Constitution Immutability
 
-- **Articles I-V** (toolkit core) are absolutely immutable
+- **Articles I-VI** (toolkit core) are absolutely immutable
 - **Base config articles** are immutable — projects cannot modify them
-- Projects can **only ADD** new articles (article 6+)
+- Projects can **only ADD** new articles (article 7+)
 
 ```json
 {

package/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "2.9.0",
+  "version": "2.10.1",
   "components": {
     "agents": {
       "description": "44 specialized agents (orchestrator, backend, frontend, security, devops, etc.)",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@softspark/ai-toolkit",
-  "version": "2.9.0",
+  "version": "2.10.1",
   "description": "AI coding toolkit: 99 skills, 44 agents, 12-editor write-through (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo, Aider, Augment, Antigravity, Codex, opencode), machine-enforced safety constitution, SARIF audit, signed npm provenance.",
   "keywords": [
     "claude",

package/scripts/config_cli.py

@@ -217,7 +217,7 @@ def _diff_constitution(base: dict, project: dict) -> None:
     if base_articles or proj_articles:
         print()
         print("  Constitution:")
-        print("    = Articles I-V              (immutable)")
+        print("    = Articles I-VI             (immutable)")
         for num, art in sorted(base_articles.items()):
             print(f"    = Article {num}: {art['title']}  (inherited from base)")
         for num, art in sorted(proj_articles.items()):

package/scripts/config_merger.py

@@ -2,7 +2,7 @@
 """Config merger for ai-toolkit extends system.
 
 Implements layered deep merge with:
-- Constitution immutability (Articles I-V absolute, base articles immutable)
+- Constitution immutability (Articles I-VI absolute, base articles immutable)
 - Agent merge with requiredAgents enforcement
 - Override validation (override:true + justification required)
 - enforce block constraints (minHookProfile, requiredPlugins, forbidOverride, requiredAgents)
@@ -22,7 +22,7 @@ from typing import Any
 # Constants
 # ---------------------------------------------------------------------------
 
-IMMUTABLE_ARTICLES = frozenset({1, 2, 3, 4, 5})
+IMMUTABLE_ARTICLES = frozenset({1, 2, 3, 4, 5, 6})
 
 HOOK_PROFILE_ORDER = {"minimal": 0, "standard": 1, "strict": 2}
 
@@ -163,7 +163,7 @@ def _merge_constitution(
     """Merge constitution — additions only, no modifications.
 
     Rules:
-    1. Articles I-V (1-5) are ABSOLUTELY immutable — toolkit core.
+    1. Articles I-VI (1-6) are ABSOLUTELY immutable — toolkit core.
     2. Articles defined by base configs are immutable — projects cannot modify.
     3. Projects can ADD new articles with article numbers not in base.
     """
@@ -177,8 +177,8 @@ def _merge_constitution(
         if article_num in IMMUTABLE_ARTICLES:
             raise ConfigMergeError(
                 f"Cannot modify Constitution Article {article_num} — immutable.\n"
-                f"Articles I-V are defined by ai-toolkit and cannot be overridden.\n"
-                f"You can ADD new articles (article 6+)."
+                f"Articles I-VI are defined by ai-toolkit and cannot be overridden.\n"
+                f"You can ADD new articles (article 7+)."
             )
         if article_num in base_amendments:
             raise ConfigMergeError(

package/scripts/config_validator.py

@@ -21,7 +21,7 @@ from typing import Any
 VALID_PROFILES = {"minimal", "standard", "strict", "full", "offline-slm"}
 VALID_HOOK_PROFILES = {"minimal", "standard", "strict"}
 HOOK_PROFILE_ORDER = {"minimal": 0, "standard": 1, "strict": 2}
-IMMUTABLE_ARTICLES = frozenset({1, 2, 3, 4, 5})
+IMMUTABLE_ARTICLES = frozenset({1, 2, 3, 4, 5, 6})
 MIN_JUSTIFICATION_LEN = 20