learnship 1.9.22 → 2.0.0

package/learnship/workflows/sync-upstream-skills.md

@@ -1,5 +1,5 @@
 ---
-description: Sync agentic-learning and impeccable skills from their upstream repos (FavioVazquez/agentic-learn + pbakaus/impeccable) — run this when upstream skills have been updated
+description: Sync agentic-learning and impeccable skills from their upstream repos (FavioVazquez/agentic-learning + pbakaus/impeccable) — run this when upstream skills have been updated
 ---
 
 # sync-upstream-skills
@@ -33,8 +33,8 @@ If any check fails, stop and report what is missing.
 Show the user what they're about to pull so there are no surprises:
 
 ```bash
-# Latest commit on agentic-learn main
-git ls-remote https://github.com/FavioVazquez/agentic-learn.git HEAD | awk '{print "agentic-learn HEAD: " $1}'
+# Latest commit on agentic-learning main
+git ls-remote https://github.com/FavioVazquez/agentic-learning.git HEAD | awk '{print "agentic-learning HEAD: " $1}'
 
 # Latest commit on impeccable main
 git ls-remote https://github.com/pbakaus/impeccable.git HEAD | awk '{print "impeccable HEAD:    " $1}'
@@ -53,7 +53,7 @@ Display:
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 
 Will pull from:
-  agentic-learn  → github.com/FavioVazquez/agentic-learn (main)
+  agentic-learning  → github.com/FavioVazquez/agentic-learning (main)
   impeccable     → github.com/pbakaus/impeccable (main)
 
 Files updated:
@@ -75,11 +75,11 @@ Wait for confirmation.
 
 ```bash
 TMPDIR=$(mktemp -d)
-AGENTIC_LEARN_TMP="$TMPDIR/agentic-learn"
+AGENTIC_LEARN_TMP="$TMPDIR/agentic-learning"
 IMPECCABLE_TMP="$TMPDIR/impeccable"
 
-echo "Cloning agentic-learn..."
-git clone --depth 1 https://github.com/FavioVazquez/agentic-learn.git "$AGENTIC_LEARN_TMP"
+echo "Cloning agentic-learning..."
+git clone --depth 1 https://github.com/FavioVazquez/agentic-learning.git "$AGENTIC_LEARN_TMP"
 
 echo "Cloning impeccable..."
 git clone --depth 1 https://github.com/pbakaus/impeccable.git "$IMPECCABLE_TMP"
@@ -223,7 +223,7 @@ node bin/install.js --all
 
 This ensures:
 - **Windsurf** — skills already live in `.windsurf/skills/` (updated in place above)
-- **Claude Code** — `~/.claude/plugins/learnship/` rebuilt with updated skill content + rewritten `references/` paths
+- **Claude Code** — `~/.claude/skills/` rebuilt with updated skill content + rewritten `references/` paths
 - **OpenCode / Gemini CLI / Codex** — `learnship/skills/` context files updated
 
 ---
@@ -247,7 +247,7 @@ Display summary:
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 
 agentic-learning:
-  SKILL.md       ✓ synced from FavioVazquez/agentic-learn
+  SKILL.md       ✓ synced from FavioVazquez/agentic-learning
   references/    ✓ synced ([N] files)
 
 impeccable:
@@ -256,7 +256,7 @@ impeccable:
 
 All platforms updated (installer re-run):
   Windsurf       ✓ skills updated in place
-  Claude Code    ✓ plugins/learnship/ rebuilt
+  Claude Code    ✓ ~/.claude/skills/ rebuilt
   Other platforms ✓ learnship/skills/ context files updated
 
 Backup saved at: .windsurf/skills/.upstream-backup-<timestamp>/

package/learnship/workflows/validate-phase.md

@@ -14,10 +14,10 @@ Retroactively audit and fill test coverage gaps for a completed phase. Useful af
 
 Read `.planning/config.json`:
 ```bash
-cat .planning/config.json | grep "nyquist_validation"
+cat .planning/config.json | grep "validation"
 ```
 
-If `nyquist_validation: false`: stop — "Validation is disabled. Enable it in `/settings` to use this workflow."
+If `validation: false`: stop — "Validation is disabled. Enable it in `/settings` to use this workflow."
 
 ## Step 2: Validate Phase
 
@@ -76,7 +76,7 @@ For each requirement ID assigned to this phase:
    - **PARTIAL** — test exists but incomplete or failing
    - **MISSING** — no test found
 
-If no gaps (all COVERED): proceed directly to step 8 with `nyquist_compliant: true`.
+If no gaps (all COVERED): proceed directly to step 8 with `compliant: true`.
 
 ## Step 7: Present Gap Plan and Fill
 
@@ -118,7 +118,7 @@ Write `$PHASE_DIR/[padded_phase]-VALIDATION.md`:
 
 ```markdown
 ---
-nyquist_compliant: true | false
+compliant: true | false
 wave_0_complete: true | false
 phase: [N]
 validated: [date]

package/learnship/workflows/verify-work.md

@@ -185,6 +185,9 @@ Display summary:
 ```
 All tests passed. ✓
 
+💡 Compound learnings? Run `/compound` to capture any notable solutions
+or patterns from this phase while context is fresh.
+
 ▶ Next: discuss-phase [X+1]
 ```
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "learnship",
-  "version": "1.9.22",
+  "version": "2.0.0",
   "description": "Learn as you build. Build with intent. — A multi-platform agentic engineering system for Windsurf, Claude Code, Cursor, OpenCode, Gemini CLI, and Codex: spec-driven workflows, integrated learning, and production-grade design.",
   "keywords": [
     "agentic",

package/references/model-profiles.md

@@ -1,40 +1,49 @@
 # Model Profiles
 
-Model profiles control which AI model each learnship agent uses. This allows balancing quality vs token spend.
+Model profiles control which AI model tier each learnship agent uses. Profiles are platform-agnostic — they use three tiers (`large`, `medium`, `small`) that map to specific models depending on your platform.
 
 ## 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 |
+| planner | large | large | medium |
+| executor | large | medium | medium |
+| phase-researcher | large | medium | small |
+| debugger | large | medium | medium |
+| verifier | medium | medium | small |
+| plan-checker | medium | medium | small |
+| solution-writer | medium | medium | small |
+| code-reviewer | large | medium | medium |
+| challenger | large | medium | medium |
+| ideation-agent | large | medium | small |
+
+## Platform Model Resolution
+
+Each tier resolves to the best available model on your platform:
+
+| Tier | Anthropic (Claude Code) | Google (Gemini CLI) | OpenAI (Codex CLI) | Windsurf / Cursor / OpenCode |
+|------|------------------------|--------------------|--------------------|-----------------------------|
+| `large` | Claude Opus 4.6 | Gemini 3.1 Pro | GPT-5.4 | Uses platform default (best available) |
+| `medium` | Claude Sonnet 4.6 | Gemini 3.1 Flash | GPT-5.4-mini | Uses platform default |
+| `small` | Claude Haiku 4.5 | Gemini 3.1 Flash-Lite | GPT-5.4-nano | Uses platform default |
+
+> **Note:** Windsurf, Cursor, and OpenCode do not expose per-agent model selection. The profile tiers are still useful — they signal the *intended complexity* of each agent's task, and workflows will adapt their prompting strategy accordingly (e.g., more explicit instructions for `small`-tier agents).
 
 ## Profile Philosophy
 
-**quality** - Maximum reasoning power
-- Opus for all decision-making agents
-- Sonnet for read-only verification
+**quality** — Maximum reasoning power
+- `large` for all decision-making agents (planner, researcher, reviewer, challenger)
+- `medium` for verification (needs reasoning, not just pattern matching)
 - 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)
+**balanced** (default) — Smart allocation
+- `large` only for planning (where architecture decisions happen)
+- `medium` for execution, research, and verification
 - 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
+**budget** — Minimal large-model usage
+- `medium` for anything that writes code
+- `small` for research and verification
 - Use when: conserving quota, high-volume work, less critical phases
 
 ## Resolution Logic
@@ -45,7 +54,8 @@ 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
+4. Map the tier (large/medium/small) to the platform's actual model
+5. Apply the resolved model when adopting the agent persona
 ```
 
 ## Per-Agent Overrides
@@ -56,13 +66,13 @@ Override specific agents without changing the entire profile:
 {
   "model_profile": "balanced",
   "model_overrides": {
-    "executor": "opus",
-    "planner": "haiku"
+    "executor": "large",
+    "planner": "small"
   }
 }
 ```
 
-Overrides take precedence over the profile. Valid values: `opus`, `sonnet`, `haiku`.
+Overrides take precedence over the profile. Valid values: `large`, `medium`, `small`.
 
 ## Switching Profiles
 
@@ -77,14 +87,12 @@ Per-project default: Set in `.planning/config.json`:
 
 ## Design Rationale
 
-**Why Opus for the planner?**
+**Why `large` 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?**
+**Why `medium` 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 `medium` (not `small`) for verifiers in balanced?**
+Verification requires goal-backward reasoning — checking if code *delivers* what the phase promised, not just pattern matching. Medium-tier models handle this well; small-tier models 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/templates/config.json

@@ -3,6 +3,8 @@
   "granularity": "standard",
   "model_profile": "balanced",
   "learning_mode": "auto",
+  "parallelization": false,
+  "test_first": false,
   "planning": {
     "commit_docs": true,
     "commit_mode": "auto",
@@ -12,7 +14,17 @@
     "research": true,
     "plan_check": true,
     "verifier": true,
-    "nyquist_validation": true
+    "validation": true,
+    "review": true,
+    "solutions_search": true
+  },
+  "review": {
+    "auto_after_verify": false
+  },
+  "ship": {
+    "auto_test": true,
+    "conventional_commits": true,
+    "pr_template": true
   },
   "git": {
     "branching_strategy": "none",