learnship 1.9.0

package/learnship/references/learning-design.md

@@ -0,0 +1,142 @@
+# Learning × Design Integration
+
+How to use the Learning Partner and Design System together. These two layers amplify each other when used at the right moments.
+
+---
+
+## The Core Idea
+
+Building software teaches you things. Building *interfaces* teaches you even more — because design decisions are high-stakes, visible, and often irreversible once shipped. The Learning Partner captures that knowledge before it evaporates.
+
+The pattern:
+1. **Before design** — brainstorm to surface blind spots
+2. **During design** — use steering commands to maintain quality
+3. **After design** — reflect to consolidate what you learned
+
+---
+
+## Before Any Design Work
+
+### Start with brainstorm
+
+Before writing a line of UI code, use:
+```
+@agentic-learning brainstorm [interface or feature name]
+```
+
+This surfaces:
+- What problem does this UI solve? For whom?
+- What mental model does the user have coming in?
+- What are the 2-3 approaches? What are the trade-offs?
+- What's the one thing they'll remember about this interface?
+
+The brainstorm is saved to `docs/brainstorm/` — it becomes a design brief that both the agent and you can reference.
+
+### Use either-or to log design decisions
+
+When you choose between two approaches (card layout vs. table, modal vs. inline edit, sidebar vs. tabs), log it:
+```
+@agentic-learning either-or
+```
+
+This creates a decision journal entry — paths considered, the choice, the rationale. When you revisit the design in 3 weeks and wonder "why did we do it this way?", the journal has the answer.
+
+---
+
+## During Design Sprints
+
+### Use steering commands to maintain quality
+
+While building interfaces, invoke design steering commands directly:
+
+| Moment | Command |
+|--------|---------|
+| Before starting any new component | `/audit` — check what quality problems to avoid |
+| After first pass of implementation | `/critique` — get honest feedback before polish |
+| Typography looks off | `/typography` — systematic type review |
+| Colors feel wrong | `/color` — OKLCH-based palette review |
+| Layout feels cramped or cluttered | `/layout` — spatial rhythm review |
+| Adding animations | `/motion` — purposeful motion, not decoration |
+| Building forms | `/forms` — labels, validation, error states |
+| Writing button labels or headings | `/copy` — UX writing review |
+| Worried about accessibility | `/accessibility` — focus, contrast, screen readers |
+
+### The AI Slop Test
+
+Run `/critique` and ask: "If someone saw this and said 'AI made this' — would they be right?"
+
+If yes, that's the signal to push harder. Use `@agentic-learning struggle` to work through it yourself first:
+```
+@agentic-learning struggle "make this interface feel genuinely designed, not AI-generated"
+```
+
+This forces you to try your own design thinking before getting a solution — which builds the design intuition that transfers to the next project.
+
+---
+
+## After Design Phases
+
+### Reflect after execute-phase
+
+When a UI phase finishes executing:
+```
+@agentic-learning reflect
+```
+
+Three questions:
+1. What design decisions did you make? Which ones felt right?
+2. What were you trying to achieve aesthetically and functionally?
+3. What's still fuzzy — patterns you used but don't fully understand?
+
+### Schedule design patterns for review
+
+After a design-heavy phase:
+```
+@agentic-learning space
+```
+
+This schedules the design patterns you used (OKLCH color, container queries, motion easing, etc.) for spaced review — so they transfer to long-term memory instead of being forgotten between projects.
+
+---
+
+## Learning Design Patterns Explicitly
+
+When you encounter a design pattern you want to understand deeply (not just copy):
+
+```
+@agentic-learning learn [pattern name]
+```
+
+Examples:
+- `@agentic-learning learn OKLCH color spaces`
+- `@agentic-learning learn container queries vs media queries`
+- `@agentic-learning learn exponential easing curves`
+- `@agentic-learning learn fluid typography with clamp()`
+
+The `learn` action uses active retrieval — you explain what you know first, then gaps are filled. This is how design patterns become intuition, not just copy-paste.
+
+### Quiz yourself on design principles
+
+After reading the design skill reference files:
+```
+@agentic-learning quiz typography
+@agentic-learning quiz color-and-contrast
+@agentic-learning quiz motion-design
+```
+
+---
+
+## The Full Design-Learning Loop
+
+```
+brainstorm → build → /critique → /polish → reflect → space
+```
+
+1. `@agentic-learning brainstorm` — clarify the problem and approach
+2. Build with steering commands as checkpoints
+3. `/critique` — honest quality check
+4. `/polish` — elevate and refine
+5. `@agentic-learning reflect` — consolidate what you learned
+6. `@agentic-learning space` — schedule patterns for review
+
+Each time through this loop, the design decisions get better — not because the AI gets better, but because *you* do.

package/learnship/references/model-profiles.md

@@ -0,0 +1,90 @@
+# Model Profiles
+
+Model profiles control which AI model each learnship agent uses. This allows balancing quality vs token spend.
+
+## Profile Definitions
+
+| Agent | `quality` | `balanced` | `budget` |
+|-------|-----------|------------|----------|
+| planner | opus | opus | sonnet |
+| roadmapper | opus | sonnet | sonnet |
+| executor | opus | sonnet | sonnet |
+| phase-researcher | opus | sonnet | haiku |
+| project-researcher | opus | sonnet | haiku |
+| research-synthesizer | sonnet | sonnet | haiku |
+| debugger | opus | sonnet | sonnet |
+| codebase-mapper | sonnet | haiku | haiku |
+| verifier | sonnet | sonnet | haiku |
+| plan-checker | sonnet | sonnet | haiku |
+| integration-checker | sonnet | sonnet | haiku |
+| nyquist-auditor | sonnet | sonnet | haiku |
+
+## Profile Philosophy
+
+**quality** - Maximum reasoning power
+- Opus for all decision-making agents
+- Sonnet for read-only verification
+- Use when: quota available, critical architecture work
+
+**balanced** (default) - Smart allocation
+- Opus only for planning (where architecture decisions happen)
+- Sonnet for execution and research (follows explicit instructions)
+- Sonnet for verification (needs reasoning, not just pattern matching)
+- Use when: normal development, good balance of quality and cost
+
+**budget** - Minimal Opus usage
+- Sonnet for anything that writes code
+- Haiku for research and verification
+- Use when: conserving quota, high-volume work, less critical phases
+
+## Resolution Logic
+
+Resolution order:
+
+```
+1. Read .planning/config.json
+2. Check model_overrides for agent-specific override
+3. If no override, look up agent in profile table
+4. Apply the resolved profile when adopting the agent persona
+```
+
+## Per-Agent Overrides
+
+Override specific agents without changing the entire profile:
+
+```json
+{
+  "model_profile": "balanced",
+  "model_overrides": {
+    "executor": "opus",
+    "planner": "haiku"
+  }
+}
+```
+
+Overrides take precedence over the profile. Valid values: `opus`, `sonnet`, `haiku`.
+
+## Switching Profiles
+
+Runtime: `/set-profile <profile>`
+
+Per-project default: Set in `.planning/config.json`:
+```json
+{
+  "model_profile": "balanced"
+}
+```
+
+## Design Rationale
+
+**Why Opus for the planner?**
+Planning involves architecture decisions, goal decomposition, and task design. This is where model quality has the highest impact.
+
+**Why Sonnet for the executor?**
+Executors follow explicit PLAN.md instructions. The plan already contains the reasoning; execution is implementation.
+
+**Why Sonnet (not Haiku) for verifiers in balanced?**
+Verification requires goal-backward reasoning — checking if code *delivers* what the phase promised, not just pattern matching. Sonnet handles this well; Haiku may miss subtle gaps.
+
+**Why Haiku for the codebase-mapper?**
+Read-only exploration and pattern extraction. No reasoning required, just structured output from file contents.

package/learnship/references/planning-config.md

@@ -0,0 +1,184 @@
+<planning_config>
+
+Configuration options for `.planning/` directory behavior.
+
+<config_schema>
+```json
+"planning": {
+  "commit_docs": true,
+  "search_gitignored": false
+},
+"git": {
+  "branching_strategy": "none",
+  "phase_branch_template": "phase-{phase}-{slug}",
+  "milestone_branch_template": "{milestone}-{slug}"
+}
+```
+
+| Option | Default | Description |
+|--------|---------|-------------|
+| `commit_docs` | `true` | Whether to commit planning artifacts to git |
+| `search_gitignored` | `false` | Add `--no-ignore` to broad rg searches |
+| `git.branching_strategy` | `"none"` | Git branching approach: `"none"`, `"phase"`, or `"milestone"` |
+| `git.phase_branch_template` | `"phase-{phase}-{slug}"` | Branch template for phase strategy |
+| `git.milestone_branch_template` | `"{milestone}-{slug}"` | Branch template for milestone strategy |
+</config_schema>
+
+<commit_docs_behavior>
+
+**When `commit_docs: true` (default):**
+- Planning files committed normally
+- SUMMARY.md, STATE.md, ROADMAP.md tracked in git
+- Full history of planning decisions preserved
+
+**When `commit_docs: false`:**
+- Skip all `git add`/`git commit` for `.planning/` files
+- User must add `.planning/` to `.gitignore`
+- Useful for: OSS contributions, client projects, keeping planning private
+
+**Reading `commit_docs` from config:**
+
+```bash
+# Read commit_docs from config.json
+COMMIT_DOCS=$(python3 -c "import json; c=json.load(open('.planning/config.json')); print(c.get('planning',{}).get('commit_docs','true'))" 2>/dev/null || echo 'true')
+```
+
+**Auto-detection:** If `.planning/` is gitignored, treat `commit_docs` as `false` regardless of config.json. This prevents git errors.
+
+```bash
+# Check if .planning/ is gitignored
+git check-ignore -q .planning && COMMIT_DOCS=false
+```
+
+**Committing planning docs (when commit_docs is true):**
+
+```bash
+git add .planning/STATE.md && git commit -m "docs: update state"
+```
+
+</commit_docs_behavior>
+
+<search_behavior>
+
+**When `search_gitignored: false` (default):**
+- Standard rg behavior (respects .gitignore)
+- Direct path searches work: `rg "pattern" .planning/` finds files
+- Broad searches skip gitignored: `rg "pattern"` skips `.planning/`
+
+**When `search_gitignored: true`:**
+- Add `--no-ignore` to broad rg searches that should include `.planning/`
+- Only needed when searching entire repo and expecting `.planning/` matches
+
+**Note:** Most learnship operations use direct file reads or explicit paths, which work regardless of gitignore status.
+
+</search_behavior>
+
+<setup_uncommitted_mode>
+
+To use uncommitted mode:
+
+1. **Set config:**
+   ```json
+   "planning": {
+     "commit_docs": false,
+     "search_gitignored": true
+   }
+   ```
+
+2. **Add to .gitignore:**
+   ```
+   .planning/
+   ```
+
+3. **Existing tracked files:** If `.planning/` was previously tracked:
+   ```bash
+   git rm -r --cached .planning/
+   git commit -m "chore: stop tracking planning docs"
+   ```
+
+4. **Branch merges:** When using `branching_strategy: phase` or `milestone`, the `complete-milestone` workflow automatically strips `.planning/` files from staging before merge commits when `commit_docs: false`.
+
+</setup_uncommitted_mode>
+
+<branching_strategy_behavior>
+
+**Branching Strategies:**
+
+| Strategy | When branch created | Branch scope | Merge point |
+|----------|---------------------|--------------|-------------|
+| `none` | Never | N/A | N/A |
+| `phase` | At `execute-phase` start | Single phase | User merges after phase |
+| `milestone` | At first `execute-phase` of milestone | Entire milestone | At `complete-milestone` |
+
+**When `git.branching_strategy: "none"` (default):**
+- All work commits to current branch
+- **Standard learnship behavior**
+
+**When `git.branching_strategy: "phase"`:**
+- `execute-phase` creates/switches to a branch before execution
+- Branch name from `phase_branch_template` (e.g., `phase-03-authentication`)
+- All plan commits go to that branch
+- User merges branches manually after phase completion
+- `complete-milestone` offers to merge all phase branches
+
+**When `git.branching_strategy: "milestone"`:**
+- First `execute-phase` of milestone creates the milestone branch
+- Branch name from `milestone_branch_template` (e.g., `v1.0-mvp`)
+- All phases in milestone commit to same branch
+- `complete-milestone` offers to merge milestone branch to main
+
+**Template variables:**
+
+| Variable | Available in | Description |
+|----------|--------------|-------------|
+| `{phase}` | phase_branch_template | Zero-padded phase number (e.g., "03") |
+| `{slug}` | Both | Lowercase, hyphenated name |
+| `{milestone}` | milestone_branch_template | Milestone version (e.g., "v1.0") |
+
+**Checking the config:**
+
+Read config directly:
+```bash
+python3 -c "import json; c=json.load(open('.planning/config.json')); g=c.get('git',{}); print(g.get('branching_strategy','none'), g.get('phase_branch_template','phase-{phase}-{slug}'), g.get('milestone_branch_template','{milestone}-{slug}'))"
+```
+
+**Branch creation:**
+
+```bash
+# For phase strategy
+if [ "$BRANCHING_STRATEGY" = "phase" ]; then
+  PHASE_SLUG=$(echo "$PHASE_NAME" | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9]/-/g' | sed 's/--*/-/g' | sed 's/^-//;s/-$//')
+  BRANCH_NAME=$(echo "$PHASE_BRANCH_TEMPLATE" | sed "s/{phase}/$PADDED_PHASE/g" | sed "s/{slug}/$PHASE_SLUG/g")
+  git checkout -b "$BRANCH_NAME" 2>/dev/null || git checkout "$BRANCH_NAME"
+fi
+
+# For milestone strategy
+if [ "$BRANCHING_STRATEGY" = "milestone" ]; then
+  MILESTONE_SLUG=$(echo "$MILESTONE_NAME" | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9]/-/g' | sed 's/--*/-/g' | sed 's/^-//;s/-$//')
+  BRANCH_NAME=$(echo "$MILESTONE_BRANCH_TEMPLATE" | sed "s/{milestone}/$MILESTONE_VERSION/g" | sed "s/{slug}/$MILESTONE_SLUG/g")
+  git checkout -b "$BRANCH_NAME" 2>/dev/null || git checkout "$BRANCH_NAME"
+fi
+```
+
+**Merge options at complete-milestone:**
+
+| Option | Git command | Result |
+|--------|-------------|--------|
+| Squash merge (recommended) | `git merge --squash` | Single clean commit per branch |
+| Merge with history | `git merge --no-ff` | Preserves all individual commits |
+| Delete without merging | `git branch -D` | Discard branch work |
+| Keep branches | (none) | Manual handling later |
+
+Squash merge is recommended — keeps main branch history clean while preserving the full development history in the branch (until deleted).
+
+**Use cases:**
+
+| Strategy | Best for |
+|----------|----------|
+| `none` | Solo development, simple projects |
+| `phase` | Code review per phase, granular rollback, team collaboration |
+| `milestone` | Release branches, staging environments, PR per version |
+
+</branching_strategy_behavior>
+
+</planning_config>

package/learnship/references/questioning.md

@@ -0,0 +1,162 @@
+<questioning_guide>
+
+Project initialization is dream extraction, not requirements gathering. You're helping the user discover and articulate what they want to build. This isn't a contract negotiation — it's collaborative thinking.
+
+<philosophy>
+
+**You are a thinking partner, not an interviewer.**
+
+The user often has a fuzzy idea. Your job is to help them sharpen it. Ask questions that make them think "oh, I hadn't considered that" or "yes, that's exactly what I mean."
+
+Don't interrogate. Collaborate. Don't follow a script. Follow the thread.
+
+</philosophy>
+
+<the_goal>
+
+By the end of questioning, you need enough clarity to write a PROJECT.md that downstream phases can act on:
+
+- **Research** needs: what domain to research, what the user already knows, what unknowns exist
+- **Requirements** needs: clear enough vision to scope v1 features
+- **Roadmap** needs: clear enough vision to decompose into phases, what "done" looks like
+- **plan-phase** needs: specific requirements to break into tasks, context for implementation choices
+- **execute-phase** needs: success criteria to verify against, the "why" behind requirements
+
+A vague PROJECT.md forces every downstream phase to guess. The cost compounds.
+
+</the_goal>
+
+<how_to_question>
+
+**Start open.** Let them dump their mental model. Don't interrupt with structure.
+
+**Follow energy.** Whatever they emphasized, dig into that. What excited them? What problem sparked this?
+
+**Challenge vagueness.** Never accept fuzzy answers. "Good" means what? "Users" means who? "Simple" means how?
+
+**Make the abstract concrete.** "Walk me through using this." "What does that actually look like?"
+
+**Clarify ambiguity.** "When you say Z, do you mean A or B?" "You mentioned X — tell me more."
+
+**Know when to stop.** When you understand what they want, why they want it, who it's for, and what done looks like — offer to proceed.
+
+</how_to_question>
+
+<question_types>
+
+Use these as inspiration, not a checklist. Pick what's relevant to the thread.
+
+**Motivation — why this exists:**
+- "What prompted this?"
+- "What are you doing today that this replaces?"
+- "What would you do if this existed?"
+
+**Concreteness — what it actually is:**
+- "Walk me through using this"
+- "You said X — what does that actually look like?"
+- "Give me an example"
+
+**Clarification — what they mean:**
+- "When you say Z, do you mean A or B?"
+- "You mentioned X — tell me more about that"
+
+**Success — how you'll know it's working:**
+- "How will you know this is working?"
+- "What does done look like?"
+
+</question_types>
+
+<using_askuserquestion>
+
+Use AskUserQuestion to help users think by presenting concrete options to react to.
+
+**Good options:**
+- Interpretations of what they might mean
+- Specific examples to confirm or deny
+- Concrete choices that reveal priorities
+
+**Bad options:**
+- Generic categories ("Technical", "Business", "Other")
+- Leading options that presume an answer
+- Too many options (2-4 is ideal)
+- Headers longer than 12 characters (hard limit — validation will reject them)
+
+**Example — vague answer:**
+User says "it should be fast"
+
+- header: "Fast"
+- question: "Fast how?"
+- options: ["Sub-second response", "Handles large datasets", "Quick to build", "Let me explain"]
+
+**Example — following a thread:**
+User mentions "frustrated with current tools"
+
+- header: "Frustration"
+- question: "What specifically frustrates you?"
+- options: ["Too many clicks", "Missing features", "Unreliable", "Let me explain"]
+
+**Tip for users — modifying an option:**
+Users who want a slightly modified version of an option can select "Other" and reference the option by number: `#1 but for finger joints only` or `#2 with pagination disabled`. This avoids retyping the full option text.
+
+</using_askuserquestion>
+
+<freeform_rule>
+
+**When the user wants to explain freely, STOP using AskUserQuestion.**
+
+If a user selects "Other" and their response signals they want to describe something in their own words (e.g., "let me describe it", "I'll explain", "something else", or any open-ended reply that isn't choosing/modifying an existing option), you MUST:
+
+1. **Ask your follow-up as plain text** — NOT via AskUserQuestion
+2. **Wait for them to type at the normal prompt**
+3. **Resume AskUserQuestion** only after processing their freeform response
+
+The same applies if YOU include a freeform-indicating option (like "Let me explain" or "Describe in detail") and the user selects it.
+
+**Wrong:** User says "let me describe it" → AskUserQuestion("What feature?", ["Feature A", "Feature B", "Describe in detail"])
+**Right:** User says "let me describe it" → "Go ahead — what are you thinking?"
+
+</freeform_rule>
+
+<context_checklist>
+
+Use this as a **background checklist**, not a conversation structure. Check these mentally as you go. If gaps remain, weave questions naturally.
+
+- [ ] What they're building (concrete enough to explain to a stranger)
+- [ ] Why it needs to exist (the problem or desire driving it)
+- [ ] Who it's for (even if just themselves)
+- [ ] What "done" looks like (observable outcomes)
+
+Four things. If they volunteer more, capture it.
+
+</context_checklist>
+
+<decision_gate>
+
+When you could write a clear PROJECT.md, offer to proceed:
+
+- header: "Ready?"
+- question: "I think I understand what you're after. Ready to create PROJECT.md?"
+- options:
+  - "Create PROJECT.md" — Let's move forward
+  - "Keep exploring" — I want to share more / ask me more
+
+If "Keep exploring" — ask what they want to add or identify gaps and probe naturally.
+
+Loop until "Create PROJECT.md" selected.
+
+</decision_gate>
+
+<anti_patterns>
+
+- **Checklist walking** — Going through domains regardless of what they said
+- **Canned questions** — "What's your core value?" "What's out of scope?" regardless of context
+- **Corporate speak** — "What are your success criteria?" "Who are your stakeholders?"
+- **Interrogation** — Firing questions without building on answers
+- **Rushing** — Minimizing questions to get to "the work"
+- **Shallow acceptance** — Taking vague answers without probing
+- **Premature constraints** — Asking about tech stack before understanding the idea
+- **User skills** — NEVER ask about user's technical experience. Claude builds.
+
+</anti_patterns>
+
+</questioning_guide>