mindforge-cc 11.2.1 → 11.3.1

package/.agent/mindforge/workstreams.md

@@ -0,0 +1,35 @@
+---
+name: mindforge:workstreams
+description: Manage parallel feature tracks with isolated state
+argument-hint: [list|create|switch|status|complete]
+allowed-tools:
+  - list_dir
+  - view_file
+  - write_to_file
+  - run_command
+---
+
+<objective>
+Enable developers to work on multiple features or bugs concurrently within the same codebase without state collision. Provides isolated tracking for each "workstream".
+</objective>
+
+<execution_context>
+.claude/commands/mindforge/workstreams.md
+</execution_context>
+
+<context>
+Arguments: $ARGUMENTS (Switch subcommand)
+Storage: .planning/workstreams/
+State: Each workstream maintains its own subset of `STATE.md` or a local context file.
+</context>
+
+<process>
+1. **Route Subcommand**:
+    - `list`: Show all active and archived workstreams in `.planning/workstreams/`.
+    - `create <name>`: Initialize a new workstream directory and baseline state.
+    - `switch <name>`: Update the global pointer in `STATE.md` to the targeted workstream.
+    - `status`: Show the current active workstream and its progress.
+2. **Manage Isolation**:
+    - When switching, ensure current work is saved or stashed if necessary.
+3. **Confirm**: Success/Failure status message to user.
+</process>

package/.agent/mindforge/worktrees.md

@@ -0,0 +1,86 @@
+---
+description: "Manage parallel git worktrees for isolated concurrent work. Usage: /mindforge:worktrees [create|list|remove|cleanup] [--name feature-name]"
+---
+
+<objective>
+Manage git worktrees to enable parallel, isolated development streams — creating, listing, removing, and cleaning up worktrees with proper branch hygiene and state management.
+</objective>
+
+<execution_context>
+@.mindforge/skills/using-git-worktrees/SKILL.md
+</execution_context>
+
+<context>
+Arguments: $ARGUMENTS (action: create|list|remove|cleanup, optional --name for branch/worktree name)
+Knowledge: Current git state, active branches, remote tracking status, .planning/STATE.md.
+</context>
+
+<process>
+1. **Parse action**: Determine the requested operation:
+   - `create` — Create a new worktree with an associated branch
+   - `list` — Show all active worktrees with status
+   - `remove` — Remove a specific worktree and optionally its branch
+   - `cleanup` — Find and remove stale/orphaned worktrees
+   - If no action specified, default to `list`
+
+2. **Verify branch availability** (for create):
+   - Check if --name branch already exists locally or remotely
+   - If exists locally: offer to reuse or create with suffix
+   - If exists remotely but not locally: offer to track
+   - If doesn't exist: proceed with creation
+   - Validate branch name follows conventions (feat/, fix/, etc.)
+
+3. **Execute worktree operation**:
+   - **create**: `git worktree add ../[repo]-[name] -b [branch-name] [base-branch]`
+     - Base branch defaults to main/master unless specified
+     - Worktree directory placed adjacent to main repo
+     - Copy relevant config files (.env.local, .tool-versions) if they exist
+   - **list**: `git worktree list --porcelain` parsed into readable table
+   - **remove**: `git worktree remove [path]` with force flag if dirty
+   - **cleanup**: `git worktree prune` + scan for orphaned directories
+
+4. **Confirm isolation**: After create, verify the worktree is properly isolated:
+   - Confirm separate working directory exists
+   - Confirm branch is checked out in new worktree
+   - Confirm no shared lock files between worktrees
+   - Verify node_modules/venv are independent (or symlinked appropriately)
+   - Run basic sanity check (git status in new worktree shows clean state)
+
+5. **Setup worktree environment** (for create):
+   - Install dependencies if package manager lockfile exists
+   - Copy local-only config (.env.local, .env.development.local)
+   - Initialize any required local state (database migrations, etc.)
+   - Set up IDE/editor workspace if workspace files exist
+
+6. **Report status**: Output clear status information:
+   - For `list`: Table with columns [Path | Branch | Last Commit | Status (clean/dirty)]
+   - For `create`: Full path to new worktree, branch name, base commit
+   - For `remove`: Confirmation of removal, whether branch was also deleted
+   - For `cleanup`: Count of pruned worktrees, freed disk space estimate
+
+7. **Cleanup stale worktrees** (for cleanup action):
+   - Run `git worktree prune` to remove references to deleted directories
+   - Scan for worktree directories that still exist but have no matching git reference
+   - Identify branches associated with merged PRs (safe to remove)
+   - Present list for user confirmation before deletion
+   - Remove node_modules/build artifacts in stale worktrees to free space
+
+8. **Update MindForge state**: Record worktree operations:
+   - Log active worktrees in `.planning/WORKTREES.md`
+   - Track which task/phase each worktree is associated with
+   - Note creation date and last activity date
+   - Flag worktrees inactive for >7 days as candidates for cleanup
+
+9. **Handle edge cases**:
+   - Worktree on a branch that was force-pushed: detect and offer rebase
+   - Worktree with uncommitted changes on remove: warn and require --force
+   - Maximum worktree count (suggest limit of 5 to avoid confusion)
+   - Disk space check before creating (warn if <2GB available)
+
+10. **Output helper commands**: Provide convenience shortcuts:
+    - Command to cd into the new worktree
+    - Command to open worktree in new editor window
+    - Command to run tests in the worktree
+    - Reminder of how to switch back to main worktree
+    - Git commands for merging worktree branch back
+</process>

package/.agent/mindforge/write-rfc.md

@@ -0,0 +1,64 @@
+---
+description: "Author technical RFC or design document. Usage: /mindforge:write-rfc [title] [--template rfc|adr|design-doc|runbook]"
+---
+
+<objective>
+Author a structured technical RFC or design document using the appropriate template, written for a cold reader with code examples and clear trade-off analysis.
+</objective>
+
+<execution_context>
+@.mindforge/skills/technical-writing/SKILL.md
+</execution_context>
+
+<context>
+Arguments: $ARGUMENTS (document title, optional --template rfc|adr|design-doc|runbook)
+Knowledge: Current architecture, existing RFCs/ADRs, team conventions, technical constraints.
+</context>
+
+<process>
+1. **Select template**: Based on --template flag or document purpose:
+   - **RFC**: Full proposal for significant system changes (new service, protocol change, major refactor)
+   - **ADR**: Concise architectural decision record (single decision with context and consequences)
+   - **Design Doc**: Detailed technical design for a feature (implementation-focused)
+   - **Runbook**: Operational procedure for handling incidents or maintenance tasks
+   - Each template has a defined structure — never deviate from it
+
+2. **Fill structure**: Populate the selected template:
+   - **RFC structure**: Title → Status (Draft/Proposed/Accepted/Rejected) → Summary (2-3 sentences) → Motivation (why now, what problem) → Detailed Design (how it works) → Drawbacks (honest downsides) → Alternatives Considered (what else was evaluated) → Open Questions (unresolved decisions) → References
+   - **ADR structure**: Title → Date → Status → Context (forces at play) → Decision (what we chose) → Consequences (positive, negative, neutral)
+   - **Design Doc structure**: Title → Authors → Reviewers → Summary → Background → Goals/Non-Goals → Design → Implementation Plan → Testing Strategy → Rollout Plan → Monitoring → Open Questions
+   - **Runbook structure**: Title → When to Use → Prerequisites → Steps (numbered, exact commands) → Verification → Rollback → Escalation → Post-Incident
+
+3. **Write for cold reader**: Ensure accessibility:
+   - Define all acronyms on first use
+   - Provide context before technical details (why before how)
+   - Use diagrams to explain complex flows (ASCII art or description)
+   - Link to relevant existing documentation (don't repeat, reference)
+   - Write in active voice, present tense
+   - One idea per paragraph, one decision per section
+   - Assume the reader has general engineering knowledge but no project-specific context
+
+4. **Add code examples**: Include concrete implementations:
+   - Minimal working examples (not pseudocode — real, runnable code)
+   - API usage examples showing request and response
+   - Configuration snippets with comments explaining each field
+   - Error handling examples (not just happy path)
+   - Before/after comparisons for migration-type changes
+   - Keep examples short (< 30 lines) — link to full implementation if longer
+
+5. **Review completeness**: Validate the document:
+   - Does the Summary stand alone? (reader should understand the proposal from Summary only)
+   - Are all trade-offs honestly stated? (no strawman alternatives)
+   - Are success criteria defined? (how do we know this worked?)
+   - Are failure modes addressed? (what if this goes wrong?)
+   - Is the scope clear? (what is explicitly NOT covered?)
+   - Are dependencies identified? (what must exist before this can proceed?)
+   - Is there a timeline? (when should this be decided/implemented?)
+
+6. **Submit for feedback**: Prepare for review:
+   - Identify reviewers (domain experts, stakeholders, implementers)
+   - Highlight open questions that need input
+   - Set review deadline (1 week for RFC, 3 days for ADR)
+   - Define approval criteria (who must approve, what constitutes consensus)
+   - Output the complete document in the appropriate location (.planning/rfcs/ or .planning/decisions/)
+</process>

package/.agent/mindforge/zero-trust.md

@@ -0,0 +1,34 @@
+---
+name: mindforge:zero-trust
+description: "Design zero-trust network architecture. Usage: /mindforge:zero-trust [system] [--scope internal|external|both] [--mtls]"
+argument-hint: "[system] [--scope internal|external|both] [--mtls]"
+allowed-tools:
+  - list_dir
+  - view_file
+---
+
+<objective>
+Design a zero-trust network architecture that eliminates implicit trust, enforces continuous verification for every communication flow, and implements micro-segmentation with identity-based access control.
+</objective>
+
+<execution_context>
+@.mindforge/skills/zero-trust-architecture/SKILL.md
+</execution_context>
+
+<context>
+Skills Directory: `.mindforge/skills/zero-trust-architecture/`
+State: Inventories all system communication flows and applies identity verification, mTLS, and micro-segmentation policies.
+</context>
+
+<process>
+1. **Inventory All Communication Flows**: Map every service-to-service, user-to-service, and external integration communication path. Include direction, protocol, port, and data sensitivity classification.
+2. **Classify by Sensitivity**: Assign trust tiers (critical, sensitive, standard) to each flow based on data classification, blast radius, and regulatory requirements. Critical flows get the strictest controls.
+3. **Implement Identity Verification Per Flow**: Require cryptographic identity proof for every request — no request is trusted based on network location alone. Use SPIFFE/SPIRE or equivalent workload identity framework.
+4. **Enable mTLS for Service-to-Service**: Configure mutual TLS for all internal service communication. Automate certificate rotation with short-lived certificates (hours, not months). Define CA hierarchy.
+5. **Configure Micro-Segmentation Policies**: Replace flat network trust with fine-grained allow-list policies. Each service can only communicate with explicitly authorized peers on explicitly authorized ports.
+6. **Add Device Posture Checks**: For user-facing access, verify device health (OS patch level, disk encryption, endpoint protection) before granting access. Degrade gracefully for non-compliant devices.
+7. **Remove Implicit Trust**: Eliminate VPN-equals-trust model. Being on the corporate network grants zero additional privileges. All access requires explicit authentication and authorization regardless of network origin.
+8. **Set Up Continuous Verification**: Implement session re-validation at regular intervals. Monitor for anomalous behavior patterns and trigger step-up authentication or session termination on drift detection.
+9. **Document Access Policies**: Produce a comprehensive policy matrix mapping identities to resources with conditions. Store policies as code for version control, audit, and automated enforcement.
+10. **Validate with Penetration Testing**: Design adversarial tests that simulate lateral movement, credential theft, and privilege escalation to verify zero-trust controls prevent blast radius expansion.
+</process>

package/.agent/skills/mindforge-add-backlog/SKILL.md

@@ -0,0 +1,72 @@
+---
+name: mindforge-add-backlog
+description: Add an idea to the backlog parking lot (999.x numbering)
+---
+
+
+<objective>
+Add a backlog item to the roadmap using 999.x numbering. Backlog items are
+unsequenced ideas that aren't ready for active planning — they live outside
+the normal phase sequence and accumulate context over time.
+</objective>
+
+<process>
+
+1. **Read ROADMAP.md** to find existing backlog entries:
+   ```bash
+   cat .planning/ROADMAP.md
+   ```
+
+2. **Find next backlog number:**
+   ```bash
+   NEXT=$(node ".agent/bin/mindforge-tools.cjs" phase next-decimal 999 --raw)
+   ```
+   If no 999.x phases exist, start at 999.1.
+
+3. **Create the phase directory:**
+   ```bash
+   SLUG=$(node ".agent/bin/mindforge-tools.cjs" generate-slug "$ARGUMENTS")
+   mkdir -p ".planning/phases/${NEXT}-${SLUG}"
+   touch ".planning/phases/${NEXT}-${SLUG}/.gitkeep"
+   ```
+
+4. **Add to ROADMAP.md** under a `## Backlog` section. If the section doesn't exist, create it at the end:
+
+   ```markdown
+   ## Backlog
+
+   ### Phase {NEXT}: {description} (BACKLOG)
+
+   **Goal:** [Captured for future planning]
+   **Requirements:** TBD
+   **Plans:** 0 plans
+
+   Plans:
+   - [ ] TBD (promote with /mindforge-review-backlog when ready)
+   ```
+
+5. **Commit:**
+   ```bash
+   node ".agent/bin/mindforge-tools.cjs" commit "docs: add backlog item ${NEXT} — ${ARGUMENTS}" --files .planning/ROADMAP.md ".planning/phases/${NEXT}-${SLUG}/.gitkeep"
+   ```
+
+6. **Report:**
+   ```
+   ## 📋 Backlog Item Added
+
+   Phase {NEXT}: {description}
+   Directory: .planning/phases/{NEXT}-{slug}/
+
+   This item lives in the backlog parking lot.
+   Use /mindforge-discuss-phase {NEXT} to explore it further.
+   Use /mindforge-review-backlog to promote items to active milestone.
+   ```
+
+</process>
+
+<notes>
+- 999.x numbering keeps backlog items out of the active phase sequence
+- Phase directories are created immediately, so /mindforge-discuss-phase and /mindforge-plan-phase work on them
+- No `Depends on:` field — backlog items are unsequenced by definition
+- Sparse numbering is fine (999.1, 999.3) — always uses next-decimal
+</notes>

package/.agent/skills/mindforge-add-phase/SKILL.md

@@ -0,0 +1,39 @@
+---
+name: mindforge-add-phase
+description: Add phase to end of current milestone in roadmap
+---
+
+
+<objective>
+Add a new integer phase to the end of the current milestone in the roadmap.
+
+Routes to the add-phase workflow which handles:
+- Phase number calculation (next sequential integer)
+- Directory creation with slug generation
+- Roadmap structure updates
+- STATE.md roadmap evolution tracking
+</objective>
+
+<execution_context>
+@.agent/workflows/mindforge-add-phase.md
+</execution_context>
+
+<context>
+Arguments: $ARGUMENTS (phase description)
+
+Roadmap and state are resolved in-workflow via `init phase-op` and targeted tool calls.
+</context>
+
+<process>
+**Follow the add-phase workflow** from `@.agent/workflows/mindforge-add-phase.md`.
+
+The workflow handles all logic including:
+1. Argument parsing and validation
+2. Roadmap existence checking
+3. Current milestone identification
+4. Next phase number calculation (ignoring decimals)
+5. Slug generation from description
+6. Phase directory creation
+7. Roadmap entry insertion
+8. STATE.md updates
+</process>

package/.agent/skills/mindforge-add-tests/SKILL.md

@@ -0,0 +1,28 @@
+---
+name: mindforge-add-tests
+description: Generate tests for a completed phase based on UAT criteria and implementation
+---
+
+<objective>
+Generate unit and E2E tests for a completed phase, using its SUMMARY.md, CONTEXT.md, and VERIFICATION.md as specifications.
+
+Analyzes implementation files, classifies them into TDD (unit), E2E (browser), or Skip categories, presents a test plan for user approval, then generates tests following RED-GREEN conventions.
+
+Output: Test files committed with message `test(phase-{N}): add unit and E2E tests from add-tests command`
+</objective>
+
+<execution_context>
+@.agent/workflows/mindforge-add-tests.md
+</execution_context>
+
+<context>
+Phase: $ARGUMENTS
+
+@.planning/STATE.md
+@.planning/ROADMAP.md
+</context>
+
+<process>
+Execute the add-tests workflow from @.agent/workflows/mindforge-add-tests.md end-to-end.
+Preserve all workflow gates (classification approval, test plan approval, RED-GREEN verification, gap reporting).
+</process>

package/.agent/skills/mindforge-add-todo/SKILL.md

@@ -0,0 +1,42 @@
+---
+name: mindforge-add-todo
+description: Capture idea or task as todo from current conversation context
+---
+
+
+<objective>
+Capture an idea, task, or issue that surfaces during a MindForge session as a structured todo for later work.
+
+Routes to the add-todo workflow which handles:
+- Directory structure creation
+- Content extraction from arguments or conversation
+- Area inference from file paths
+- Duplicate detection and resolution
+- Todo file creation with frontmatter
+- STATE.md updates
+- Git commits
+</objective>
+
+<execution_context>
+@.agent/workflows/mindforge-add-todo.md
+</execution_context>
+
+<context>
+Arguments: $ARGUMENTS (optional todo description)
+
+State is resolved in-workflow via `init todos` and targeted reads.
+</context>
+
+<process>
+**Follow the add-todo workflow** from `@.agent/workflows/mindforge-add-todo.md`.
+
+The workflow handles all logic including:
+1. Directory ensuring
+2. Existing area checking
+3. Content extraction (arguments or conversation)
+4. Area inference
+5. Duplicate checking
+6. File creation with slug generation
+7. STATE.md updates
+8. Git commits
+</process>

package/.agent/skills/mindforge-audit-milestone/SKILL.md

@@ -0,0 +1,29 @@
+---
+name: mindforge-audit-milestone
+description: Audit milestone completion against original intent before archiving
+---
+
+<objective>
+Verify milestone achieved its definition of done. Check requirements coverage, cross-phase integration, and end-to-end flows.
+
+**This command IS the orchestrator.** Reads existing VERIFICATION.md files (phases already verified during execute-phase), aggregates tech debt and deferred gaps, then spawns integration checker for cross-phase wiring.
+</objective>
+
+<execution_context>
+@.agent/workflows/mindforge-audit-milestone.md
+</execution_context>
+
+<context>
+Version: $ARGUMENTS (optional — defaults to current milestone)
+
+Core planning files are resolved in-workflow (`init milestone-op`) and loaded only as needed.
+
+**Completed Work:**
+Glob: .planning/phases/*/*-SUMMARY.md
+Glob: .planning/phases/*/*-VERIFICATION.md
+</context>
+
+<process>
+Execute the audit-milestone workflow from @.agent/workflows/mindforge-audit-milestone.md end-to-end.
+Preserve all workflow gates (scope determination, verification reading, integration check, requirements coverage, routing).
+</process>

package/.agent/skills/mindforge-audit-uat/SKILL.md

@@ -0,0 +1,20 @@
+---
+name: mindforge-audit-uat
+description: Cross-phase audit of all outstanding UAT and verification items
+---
+
+<objective>
+Scan all phases for pending, skipped, blocked, and human_needed UAT items. Cross-reference against codebase to detect stale documentation. Produce prioritized human test plan.
+</objective>
+
+<execution_context>
+@.agent/workflows/mindforge-audit-uat.md
+</execution_context>
+
+<context>
+Core planning files are loaded in-workflow via CLI.
+
+**Scope:**
+Glob: .planning/phases/*/*-UAT.md
+Glob: .planning/phases/*/*-VERIFICATION.md
+</context>

package/.agent/skills/mindforge-autonomous/SKILL.md

@@ -0,0 +1,33 @@
+---
+name: mindforge-autonomous
+description: Run all remaining phases autonomously — discuss→plan→execute per phase
+---
+
+<objective>
+Execute all remaining milestone phases autonomously. For each phase: discuss → plan → execute. Pauses only for user decisions (grey area acceptance, blockers, validation requests).
+
+Uses ROADMAP.md phase discovery and Skill() flat invocations for each phase command. After all phases complete: milestone audit → complete → cleanup.
+
+**Creates/Updates:**
+- `.planning/STATE.md` — updated after each phase
+- `.planning/ROADMAP.md` — progress updated after each phase
+- Phase artifacts — CONTEXT.md, PLANs, SUMMARYs per phase
+
+**After:** Milestone is complete and cleaned up.
+</objective>
+
+<execution_context>
+@.agent/workflows/mindforge-autonomous.md
+@.agent/references/ui-brand.md
+</execution_context>
+
+<context>
+Optional flag: `--from N` — start from phase N instead of the first incomplete phase.
+
+Project context, phase list, and state are resolved inside the workflow using init commands (`mindforge-tools.cjs init milestone-op`, `mindforge-tools.cjs roadmap analyze`). No upfront context loading needed.
+</context>
+
+<process>
+Execute the autonomous workflow from @.agent/workflows/mindforge-autonomous.md end-to-end.
+Preserve all workflow gates (phase discovery, per-phase execution, blocker handling, progress display).
+</process>

package/.agent/skills/mindforge-brainstorming/SKILL.md

@@ -0,0 +1,164 @@
+---
+name: brainstorming
+description: "You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation."
+---
+
+# Brainstorming Ideas Into Designs
+
+Help turn ideas into fully formed designs and specs through natural collaborative dialogue.
+
+Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design and get user approval.
+
+<HARD-GATE>
+Do NOT invoke any implementation skill, write any code, scaffold any project, or take any implementation action until you have presented a design and the user has approved it. This applies to EVERY project regardless of perceived simplicity.
+</HARD-GATE>
+
+## Anti-Pattern: "This Is Too Simple To Need A Design"
+
+Every project goes through this process. A todo list, a single-function utility, a config change — all of them. "Simple" projects are where unexamined assumptions cause the most wasted work. The design can be short (a few sentences for truly simple projects), but you MUST present it and get approval.
+
+## Checklist
+
+You MUST create a task for each of these items and complete them in order:
+
+1. **Explore project context** — check files, docs, recent commits
+2. **Offer visual companion** (if topic will involve visual questions) — this is its own message, not combined with a clarifying question. See the Visual Companion section below.
+3. **Ask clarifying questions** — one at a time, understand purpose/constraints/success criteria
+4. **Propose 2-3 approaches** — with trade-offs and your recommendation
+5. **Present design** — in sections scaled to their complexity, get user approval after each section
+6. **Write design doc** — save to `docs/mindforge/specs/YYYY-MM-DD-<topic>-design.md` and commit
+7. **Spec self-review** — quick inline check for placeholders, contradictions, ambiguity, scope (see below)
+8. **User reviews written spec** — ask user to review the spec file before proceeding
+9. **Transition to implementation** — invoke mindforge-plan-phase_extended skill to create implementation plan
+
+## Process Flow
+
+```dot
+digraph brainstorming {
+    "Explore project context" [shape=box];
+    "Visual questions ahead?" [shape=diamond];
+    "Offer Visual Companion\n(own message, no other content)" [shape=box];
+    "Ask clarifying questions" [shape=box];
+    "Propose 2-3 approaches" [shape=box];
+    "Present design sections" [shape=box];
+    "User approves design?" [shape=diamond];
+    "Write design doc" [shape=box];
+    "Spec self-review\n(fix inline)" [shape=box];
+    "User reviews spec?" [shape=diamond];
+    "Invoke mindforge-plan-phase_extended skill" [shape=doublecircle];
+
+    "Explore project context" -> "Visual questions ahead?";
+    "Visual questions ahead?" -> "Offer Visual Companion\n(own message, no other content)" [label="yes"];
+    "Visual questions ahead?" -> "Ask clarifying questions" [label="no"];
+    "Offer Visual Companion\n(own message, no other content)" -> "Ask clarifying questions";
+    "Ask clarifying questions" -> "Propose 2-3 approaches";
+    "Propose 2-3 approaches" -> "Present design sections";
+    "Present design sections" -> "User approves design?";
+    "User approves design?" -> "Present design sections" [label="no, revise"];
+    "User approves design?" -> "Write design doc" [label="yes"];
+    "Write design doc" -> "Spec self-review\n(fix inline)";
+    "Spec self-review\n(fix inline)" -> "User reviews spec?";
+    "User reviews spec?" -> "Write design doc" [label="changes requested"];
+    "User reviews spec?" -> "Invoke mindforge-plan-phase_extended skill" [label="approved"];
+}
+```
+
+**The terminal state is invoking mindforge-plan-phase_extended.** Do NOT invoke frontend-design, mcp-builder, or any other implementation skill. The ONLY skill you invoke after brainstorming is mindforge-plan-phase_extended.
+
+## The Process
+
+**Understanding the idea:**
+
+- Check out the current project state first (files, docs, recent commits)
+- Before asking detailed questions, assess scope: if the request describes multiple independent subsystems (e.g., "build a platform with chat, file storage, billing, and analytics"), flag this immediately. Don't spend questions refining details of a project that needs to be decomposed first.
+- If the project is too large for a single spec, help the user decompose into sub-projects: what are the independent pieces, how do they relate, what order should they be built? Then brainstorm the first sub-project through the normal design flow. Each sub-project gets its own spec → plan → implementation cycle.
+- For appropriately-scoped projects, ask questions one at a time to refine the idea
+- Prefer multiple choice questions when possible, but open-ended is fine too
+- Only one question per message - if a topic needs more exploration, break it into multiple questions
+- Focus on understanding: purpose, constraints, success criteria
+
+**Exploring approaches:**
+
+- Propose 2-3 different approaches with trade-offs
+- Present options conversationally with your recommendation and reasoning
+- Lead with your recommended option and explain why
+
+**Presenting the design:**
+
+- Once you believe you understand what you're building, present the design
+- Scale each section to its complexity: a few sentences if straightforward, up to 200-300 words if nuanced
+- Ask after each section whether it looks right so far
+- Cover: architecture, components, data flow, error handling, testing
+- Be ready to go back and clarify if something doesn't make sense
+
+**Design for isolation and clarity:**
+
+- Break the system into smaller units that each have one clear purpose, communicate through well-defined interfaces, and can be understood and tested independently
+- For each unit, you should be able to answer: what does it do, how do you use it, and what does it depend on?
+- Can someone understand what a unit does without reading its internals? Can you change the internals without breaking consumers? If not, the boundaries need work.
+- Smaller, well-bounded units are also easier for you to work with - you reason better about code you can hold in context at once, and your edits are more reliable when files are focused. When a file grows large, that's often a signal that it's doing too much.
+
+**Working in existing codebases:**
+
+- Explore the current structure before proposing changes. Follow existing patterns.
+- Where existing code has problems that affect the work (e.g., a file that's grown too large, unclear boundaries, tangled responsibilities), include targeted improvements as part of the design - the way a good developer improves code they're working in.
+- Don't propose unrelated refactoring. Stay focused on what serves the current goal.
+
+## After the Design
+
+**Documentation:**
+
+- Write the validated design (spec) to `docs/mindforge/specs/YYYY-MM-DD-<topic>-design.md`
+  - (User preferences for spec location override this default)
+- Use mindforge:writing-clearly-and-concisely skill if available
+- Commit the design document to git
+
+**Spec Self-Review:**
+After writing the spec document, look at it with fresh eyes:
+
+1. **Placeholder scan:** Any "TBD", "TODO", incomplete sections, or vague requirements? Fix them.
+2. **Internal consistency:** Do any sections contradict each other? Does the architecture match the feature descriptions?
+3. **Scope check:** Is this focused enough for a single implementation plan, or does it need decomposition?
+4. **Ambiguity check:** Could any requirement be interpreted two different ways? If so, pick one and make it explicit.
+
+Fix any issues inline. No need to re-review — just fix and move on.
+
+**User Review Gate:**
+After the spec review loop passes, ask the user to review the written spec before proceeding:
+
+> "Spec written and committed to `<path>`. Please review it and let me know if you want to make any changes before we start writing out the implementation plan."
+
+Wait for the user's response. If they request changes, make them and re-run the spec review loop. Only proceed once the user approves.
+
+**Implementation:**
+
+- Invoke the mindforge-plan-phase_extended skill to create a detailed implementation plan
+- Do NOT invoke any other skill. mindforge-plan-phase_extended is the next step.
+
+## Key Principles
+
+- **One question at a time** - Don't overwhelm with multiple questions
+- **Multiple choice preferred** - Easier to answer than open-ended when possible
+- **YAGNI ruthlessly** - Remove unnecessary features from all designs
+- **Explore alternatives** - Always propose 2-3 approaches before settling
+- **Incremental validation** - Present design, get approval before moving on
+- **Be flexible** - Go back and clarify when something doesn't make sense
+
+## Visual Companion
+
+A browser-based companion for showing mockups, diagrams, and visual options during brainstorming. Available as a tool — not a mode. Accepting the companion means it's available for questions that benefit from visual treatment; it does NOT mean every question goes through the browser.
+
+**Offering the companion:** When you anticipate that upcoming questions will involve visual content (mockups, layouts, diagrams), offer it once for consent:
+> "Some of what we're working on might be easier to explain if I can show it to you in a web browser. I can put together mockups, diagrams, comparisons, and other visuals as we go. This feature is still new and can be token-intensive. Want to try it? (Requires opening a local URL)"
+
+**This offer MUST be its own message.** Do not combine it with clarifying questions, context summaries, or any other content. The message should contain ONLY the offer above and nothing else. Wait for the user's response before continuing. If they decline, proceed with text-only brainstorming.
+
+**Per-question decision:** Even after the user accepts, decide FOR EACH QUESTION whether to use the browser or the terminal. The test: **would the user understand this better by seeing it than reading it?**
+
+- **Use the browser** for content that IS visual — mockups, wireframes, layout comparisons, architecture diagrams, side-by-side visual designs
+- **Use the terminal** for content that is text — requirements questions, conceptual choices, tradeoff lists, A/B/C/D text options, scope decisions
+
+A question about a UI topic is not automatically a visual question. "What does personality mean in this context?" is a conceptual question — use the terminal. "Which wizard layout works better?" is a visual question — use the browser.
+
+If they agree to the companion, read the detailed guide before proceeding:
+`skills/brainstorming/visual-companion.md`