rubyn-code 0.4.0 → 0.5.1

data/lib/rubyn_code/tools/review_pr.rb

@@ -24,7 +24,7 @@ module RubynCode
       }.freeze
       RISK_LEVEL = :read
 
-      def execute(base_branch: 'main', focus: 'all')
+      def execute(base_branch: 'main', focus: 'all', pack_context: nil)
         error = validate_git_repo
         return error if error
 
@@ -37,7 +37,7 @@ module RubynCode
         diff = run_git("diff #{base_branch}...HEAD")
         return "No changes found between #{current} and #{base_branch}." if diff.strip.empty?
 
-        build_full_review(current, base_branch, diff, focus)
+        build_full_review(current, base_branch, diff, focus, pack_context: pack_context)
       end
 
       FILE_CATEGORIES = [
@@ -80,8 +80,9 @@ module RubynCode
         [nil, "Error: Base branch '#{base_branch}' not found."]
       end
 
-      def build_full_review(current, base_branch, diff, focus)
-        review = build_review_header(current, base_branch)
+      def build_full_review(current, base_branch, diff, focus, pack_context: nil)
+        review = build_pack_context_section(pack_context)
+        review.concat(build_review_header(current, base_branch))
         review.concat(build_file_categories(base_branch))
         review.concat(build_focus_section(focus))
         review.concat(build_diff_section(diff))
@@ -158,6 +159,16 @@ module RubynCode
         ]
       end
 
+      def build_pack_context_section(pack_context)
+        return [] if pack_context.nil? || pack_context.strip.empty?
+
+        [
+          '## Skill Pack Context',
+          pack_context.strip,
+          ''
+        ]
+      end
+
       def run_git(command)
         `cd #{project_root} && git #{command} 2>/dev/null`
       end

data/lib/rubyn_code/tools/web_search.rb

@@ -85,7 +85,8 @@ module RubynCode
         html.scan(%r{<a[^>]+href="(https?://(?!lite\.duckduckgo)[^"]+)"[^>]*>(.*?)</a>}i)
       end
 
-      def build_ddg_results(links, snippets, max) # rubocop:disable Metrics/AbcSize -- HTML parsing with filtering
+      # -- HTML parsing with filtering
+      def build_ddg_results(links, snippets, max)
         results = []
         links.each_with_index do |match, idx|
           break if results.length >= max

data/lib/rubyn_code/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module RubynCode
-  VERSION = '0.4.0'
+  VERSION = '0.5.1'
 end

data/lib/rubyn_code.rb

@@ -137,7 +137,16 @@ module RubynCode
     autoload :Loader, 'rubyn_code/skills/loader'
     autoload :Catalog, 'rubyn_code/skills/catalog'
     autoload :Document, 'rubyn_code/skills/document'
+    autoload :Matcher, 'rubyn_code/skills/matcher'
+    autoload :RegistryAutoload, 'rubyn_code/skills/registry_autoload'
     autoload :TtlManager, 'rubyn_code/skills/ttl_manager'
+    autoload :RegistryClient, 'rubyn_code/skills/registry_client'
+    autoload :PackManager, 'rubyn_code/skills/pack_manager'
+    autoload :PackInstaller, 'rubyn_code/skills/pack_installer'
+    autoload :PackContext, 'rubyn_code/skills/pack_context'
+    autoload :GemfileParser, 'rubyn_code/skills/gemfile_parser'
+    autoload :AutoSuggest, 'rubyn_code/skills/auto_suggest'
+    autoload :RegistryError, 'rubyn_code/skills/registry_client'
   end
 
   # Layer 6: Sub-Agents
@@ -153,6 +162,13 @@ module RubynCode
     autoload :Models, 'rubyn_code/tasks/models'
   end
 
+  # Layer 7b: Megaplan
+  module Megaplan
+    autoload :PlanProposer, 'rubyn_code/megaplan/plan_proposer'
+    autoload :InterviewSession, 'rubyn_code/megaplan/interview_session'
+    autoload :CiRecovery, 'rubyn_code/megaplan/ci_recovery'
+  end
+
   # Layer 8: Background
   module Background
     autoload :Worker, 'rubyn_code/background/worker'
@@ -284,6 +300,10 @@ module RubynCode
       autoload :Model, 'rubyn_code/cli/commands/model'
       autoload :NewSession, 'rubyn_code/cli/commands/new_session'
       autoload :Provider, 'rubyn_code/cli/commands/provider'
+      autoload :InstallSkills, 'rubyn_code/cli/commands/install_skills'
+      autoload :RemoveSkills, 'rubyn_code/cli/commands/remove_skills'
+      autoload :Skills, 'rubyn_code/cli/commands/skills'
+      autoload :Megaplan, 'rubyn_code/cli/commands/megaplan'
     end
   end
 

data/skills/megaplan/megaplan.md

@@ -0,0 +1,156 @@
+---
+name: megaplan
+description: Phased project planning. Interview the user one question at a time, then scaffold numbered phase folders (requirements/design/tasks). Trigger phrases include "megaplan", "mega plan", "plan phases", "phase this out", or any feature spanning 3+ PRs.
+tags:
+  - planning
+  - process
+  - phases
+  - megaplan
+triggers:
+  - megaplan
+  - mega plan
+  - plan phases
+  - phase this out
+---
+
+# Megaplan — Phased Project Planning
+
+Ship in vertical slices. Each phase merges cleanly and leaves the trunk working.
+
+## Don't use for
+
+- Single-PR features — just do them
+- Pure research / exploration — nothing shippable
+- Work where the *shape* (not just the details) will change weekly — plan something smaller first
+
+## Design principles to apply throughout
+
+Hold the work to these when proposing phases and reviewing each `design.md`:
+
+- **Vertical slices, not horizontal.** A phase touches every layer it needs to be end-to-end testable. The classic anti-pattern this skill exists to prevent: "Phase 1: all models. Phase 2: all controllers. Phase 3: all views." Trunk is unshippable until Phase 3 and Phase 2 has nothing to test. Instead: "Phase 1: one feature, full-stack, behind a flag."
+- **SOLID, applied lightly.** Single Responsibility and Dependency Inversion are the two that actually bite at the phase-design level. The others usually take care of themselves if those two are clean.
+- **KISS.** Skip the abstraction until you have two concrete callers. Three similar lines beat a premature framework. Inline before you extract.
+- **Justify abstractions.** Every new module/service/class in `design.md` needs a one-sentence reason it exists separately. If you can't write it, inline the code.
+
+## The workflow
+
+### 1. Interview first
+
+Don't propose phases until you understand the shape. Walk through the agenda below **one question per turn** — never dump the full list in a single message. The point is to let the operator steer at every step.
+
+**How to ask:**
+
+- **One topic per turn.** Pick the next unanswered item from the agenda. Ask only about that.
+- **Number the options.** Whenever the question has 2+ plausible answers, present them as a numbered list so the operator can reply with just the number. Include a **recommended** pick (the one you'd default to given what you know so far) and say *why* it's the recommendation in one short line.
+- **Restate locked-in answers at the top of each follow-up.** A running "Decisions so far:" block of one-line bullets, so the operator can spot drift and you can spot contradictions.
+- **Open-ended questions are fine** when no obvious option set exists (e.g. "What's the end-state in user-facing terms?"). Still ask one at a time.
+- **Stop when you're 95% sure of the shape.** Don't run the whole agenda for its own sake — skip topics that are already obvious from context. The agenda is a checklist *for you*, not a script to read aloud.
+
+**Agenda (interviewer's checklist, not a dump):**
+
+- **Goal** — end state in user-facing terms
+- **Constraints** — deadlines, infra limits, things you can't break
+- **Existing assets** — what's there to build on or rip out
+- **Natural ordering** — dependency sequence (data → API → UI)?
+- **External dependencies** — other teams, third-party APIs, infra access, design review. These reorder phases more than technical concerns do.
+- **Destructive operations** — schema drops, data deletes, deprecations. These need their own phase with an explicit rollback note.
+- **Test strategy** — what coverage is needed?
+- **Done-per-phase** — minimum manual test that proves each phase shipped?
+
+### 2. Propose phases, get agreement
+
+A good phase:
+- Is a vertical slice — testable end-to-end at merge time
+- Ships independently — trunk works at every boundary
+- Has a clear definition of done
+- Is roughly 1–3 days of focused work
+- Has a name that survives the PR title. If it adds *and* removes, capture both (e.g. "TX-Only Checkout + Geofencing Removal").
+
+A good phase list:
+- 3–8 phases for most projects
+- Ordered by dependency, not priority
+- Destructive operations isolated to their own phase
+- Ends with a phase that visibly delivers the goal
+
+Propose as a numbered outline. Let the user reorder, merge, or split before any files exist.
+
+### 3. Scaffold the structure
+
+```
+docs/
+  README.md                # roadmap tracker
+  NN-slug/
+    requirements.md        # user stories + acceptance criteria
+    design.md              # architecture + interfaces + test strategy
+    tasks.md               # numbered checklist
+```
+
+Numbering: zero-padded (`01-`, `02-`). Slugs: kebab-case, ≤4 words.
+
+Default: fully scaffold the *current* phase; future phases stay as one-liners in `README.md` until you start them. Later phases mutate based on what's learned early — don't pre-write what you'll have to rewrite.
+
+### 4. Implement phase-by-phase
+
+For each phase:
+1. **Read the running architecture doc first** (`CLAUDE.md` or equivalent). That's how you don't repeat decisions or miss constraints from earlier phases.
+2. Branch off main: `git checkout -b phase-NN-slug`
+3. Work `tasks.md` top-to-bottom, checking subtasks as you go
+4. Commit at section boundaries: `Phase N (M/X): description` — where `M` is the current section number and `X` is the total number of sections in `tasks.md`
+5. Run full test suite + lint + format at each commit boundary
+6. When `tasks.md` is fully checked, push and open a PR (see PR description shape below)
+7. After merge: check the box in `docs/README.md`, update the running architecture doc if anything moved
+
+## File templates
+
+### requirements.md
+
+Use RFC 2119 SHALL/SHOULD/MAY language for acceptance criteria. They're contracts — write them as something a QA tester could check.
+
+Sections: Overview, Glossary, Requirements (per requirement: user story + numbered SHALL criteria), Out of scope.
+
+### design.md
+
+Sections: Overview, Architecture (each component gets Responsibility, Collaborators, "Why not inline?"), Data model changes, Test strategy, Migration / rollout, Future enhancements.
+
+Every new abstraction needs a justification line. If you can't answer "why not inline this", inline it.
+
+### tasks.md
+
+Sections (`## [ ] N. <name>`) and tasks (`- [ ] N.M ...`) both get checkboxes. A section ticks only when every task under it ticks. Reference requirements by ID (`refs Req 1.1`) so coverage gaps are visible. Always end with a Validation section that includes the manual smoke flow.
+
+## PR description shape
+
+Three bullets. Don't pad them.
+
+```
+## What shipped
+- <user-facing capability or removal>
+
+## What proves it
+- <new tests, smoke flow, manual check>
+
+## What's deferred
+- <link to later phase, or "none">
+```
+
+## Patterns and pitfalls
+
+**Patterns to keep:**
+- **Branch per phase:** `phase-NN-slug` — disposable, one PR per branch
+- **Squash-merge:** one phase = one commit on main, full PR description preserved
+- **Plan before code:** `requirements.md` is finalized and `design.md` is sketched before any task in `tasks.md` gets implemented.
+- **Semantic test anchors** so later phases don't break earlier tests
+- **One running architecture doc** kept current — read it before each phase, update it after
+
+**When to break the rules:**
+- **Phase grew mid-stream?** Split it. Add `NN-a-slug` / `NN-b-slug` or renumber.
+- **Later phase invalidates an earlier requirement?** Update the earlier doc with a "Superseded by Phase N" note.
+- **Phase ships nothing user-visible** (e.g. refactor prep)? Still its own PR — but say so in the description.
+
+**Pitfalls to avoid:**
+- **Horizontal-slice phases** (all models / all controllers / all views). Trunk is unshippable until the last phase merges.
+- **Scaffolding all phases upfront in full detail** — later phases get invalidated by what you learn early.
+- **Phases longer than ~3 days** — the phase should split. Long phases hide scope creep.
+- **Requirements without acceptance criteria** — "Make X work" isn't a requirement; "When <condition>, the system SHALL <observable behavior>" is.
+- **Tasks that don't reference requirements** — if you can't cite which requirement a task serves, the task probably isn't load-bearing.
+- **Destructive operations mixed with feature work** — schema drops, deletes, deprecations belong in their own phase with a rollback note.

data/skills/rubyn_self_test.md

@@ -115,6 +115,81 @@ Score: 18/22 (82%) — 4 failures
 - **glob**: Check that all 16 layer directories exist under `lib/rubyn_code/`. PASS if at least 14 found.
 - **read_file**: Read `lib/rubyn_code.rb` and verify it has modules for Agent, Tools, Context, Skills, Memory, Observability, Learning. PASS if all 7 found.
 
+### 15. Skill-Pack Autoload — Live Registry Roundtrip
+
+End-to-end exercise of the autoload pipeline against the real registry at `rubyn.ai`: fetch the catalog, install a pack the user does **not** already have, verify it works on disk + in the catalog + through the matcher, then remove it. The user's pre-existing installed packs are not touched.
+
+- **Live roundtrip**: `bash` with the script below. PASS if the final line is `ROUNDTRIP: PASS`. SKIP if the final line starts with `SKIP:` (means every registry pack is already installed locally — rare).
+
+  ```bash
+  bundle exec ruby -e '
+    require_relative "lib/rubyn_code"
+
+    client = RubynCode::Skills::RegistryClient.new
+    pack_manager = RubynCode::Skills::PackManager.new
+
+    catalog_packs = client.fetch_catalog[:data] || []
+    abort "FAIL: empty registry catalog" if catalog_packs.empty?
+
+    already_installed = catalog_packs.map { |p| p[:name] || p["name"] }
+                                     .select { |n| pack_manager.installed?(n) }
+    target = catalog_packs.find { |p| !already_installed.include?(p[:name] || p["name"]) }
+    abort "SKIP: every registry pack is already installed" if target.nil?
+
+    name = target[:name] || target["name"]
+    puts "TEST PACK: #{name}"
+
+    success = false
+    begin
+      result = client.fetch_pack(name)
+      pack_manager.install(result[:data], etag: result[:etag])
+      raise "install did not create directory" unless pack_manager.installed?(name)
+      puts "STEP install: PASS"
+
+      catalog_obj = RubynCode::Skills::Catalog.new(
+        File.join(Dir.home, ".rubyn-code", "skill-packs")
+      )
+      skills = catalog_obj.available.select { |e| e[:path].include?("/#{name}/") }
+      raise "catalog sees no skills" if skills.empty?
+      raise "no skills have triggers" if skills.none? { |s| !s[:triggers].empty? }
+      puts "STEP catalog: PASS (#{skills.size} skills, #{skills.count { |s| !s[:triggers].empty? }} with triggers)"
+
+      sample = skills.find { |s| !s[:triggers].empty? }
+      matcher = RubynCode::Skills::Matcher.new(catalog: catalog_obj)
+      hits = matcher.match("question about #{sample[:triggers].first}")
+      raise "matcher did not hit on \"#{sample[:triggers].first}\"" if hits.none? { |h| h[:name] == sample[:name] }
+      puts "STEP matcher: PASS (hit \"#{sample[:name]}\" via \"#{sample[:triggers].first}\")"
+      success = true
+    ensure
+      pack_manager.remove(name)
+      if pack_manager.installed?(name)
+        puts "STEP cleanup: FAIL (pack still on disk)"
+      else
+        puts "STEP cleanup: PASS"
+      end
+    end
+
+    puts(success ? "ROUNDTRIP: PASS" : "ROUNDTRIP: FAIL")
+  '
+  ```
+
+  The script:
+  1. Fetches the registry catalog (proves the static API at `rubyn.ai/api/v1/skills/packs.json` is reachable).
+  2. Picks the first pack the user does **not** have installed, so we never touch their existing packs.
+  3. Installs the pack via `RegistryClient#fetch_pack` + `PackManager#install` — exactly the path the autoload pipeline uses.
+  4. Reads the disk back through a fresh `Skills::Catalog` and confirms the new skills are visible with parsed triggers.
+  5. Runs `Skills::Matcher#match` against a real trigger from one of the freshly-installed skills, confirming the matcher would have fired in a real session.
+  6. Removes the pack in an `ensure` block so a partial failure still leaves the user's system clean.
+
+  PASS criteria: `STEP install`, `STEP catalog`, `STEP matcher`, and `STEP cleanup` all `PASS`, with a final `ROUNDTRIP: PASS`.
+
+- **Live autoload notification (manual verification, not scored)**: This isn't a tool call — it's a hint to surface in the scorecard for the user. Tell them: after the self-test completes, send a follow-up prompt that includes a trigger word from any pack in the registry (e.g. `"explain turbo drive"`). The Rubyn renderer should print:
+  ```
+  📥 Fetching skill pack 'hotwire' from registry…
+  📚 Loaded: turbo-drive
+  ```
+  before the next response (the `📥` line appears only if the pack wasn't already installed). Do **not** count this as PASS/FAIL — just mention it in the scorecard so the user can verify the renderer side themselves.
+
 ## Scoring
 
 Count total PASS results out of total tests run. Report the percentage.

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: rubyn-code
 version: !ruby/object:Gem::Version
-  version: 0.4.0
+  version: 0.5.1
 platform: ruby
 authors:
 - fadedmaturity
@@ -226,16 +226,21 @@ files:
 - lib/rubyn_code/cli/commands/diff.rb
 - lib/rubyn_code/cli/commands/doctor.rb
 - lib/rubyn_code/cli/commands/help.rb
+- lib/rubyn_code/cli/commands/install_skills.rb
+- lib/rubyn_code/cli/commands/list_skills.rb
 - lib/rubyn_code/cli/commands/mcp.rb
+- lib/rubyn_code/cli/commands/megaplan.rb
 - lib/rubyn_code/cli/commands/model.rb
 - lib/rubyn_code/cli/commands/new_session.rb
 - lib/rubyn_code/cli/commands/plan.rb
 - lib/rubyn_code/cli/commands/provider.rb
 - lib/rubyn_code/cli/commands/quit.rb
 - lib/rubyn_code/cli/commands/registry.rb
+- lib/rubyn_code/cli/commands/remove_skills.rb
 - lib/rubyn_code/cli/commands/resume.rb
 - lib/rubyn_code/cli/commands/review.rb
 - lib/rubyn_code/cli/commands/skill.rb
+- lib/rubyn_code/cli/commands/skills.rb
 - lib/rubyn_code/cli/commands/spawn.rb
 - lib/rubyn_code/cli/commands/tasks.rb
 - lib/rubyn_code/cli/commands/tokens.rb
@@ -290,7 +295,12 @@ files:
 - lib/rubyn_code/ide/handlers/config_set_handler.rb
 - lib/rubyn_code/ide/handlers/initialize_handler.rb
 - lib/rubyn_code/ide/handlers/models_list_handler.rb
+- lib/rubyn_code/ide/handlers/plan_interview_answer_handler.rb
+- lib/rubyn_code/ide/handlers/plan_interview_cancel_handler.rb
+- lib/rubyn_code/ide/handlers/plan_interview_start_handler.rb
+- lib/rubyn_code/ide/handlers/plan_propose_handler.rb
 - lib/rubyn_code/ide/handlers/prompt_handler.rb
+- lib/rubyn_code/ide/handlers/recover_ci_handler.rb
 - lib/rubyn_code/ide/handlers/review_handler.rb
 - lib/rubyn_code/ide/handlers/session_fork_handler.rb
 - lib/rubyn_code/ide/handlers/session_list_handler.rb
@@ -326,6 +336,9 @@ files:
 - lib/rubyn_code/mcp/sse_transport.rb
 - lib/rubyn_code/mcp/stdio_transport.rb
 - lib/rubyn_code/mcp/tool_bridge.rb
+- lib/rubyn_code/megaplan/ci_recovery.rb
+- lib/rubyn_code/megaplan/interview_session.rb
+- lib/rubyn_code/megaplan/plan_proposer.rb
 - lib/rubyn_code/memory/RUBYN.md
 - lib/rubyn_code/memory/models.rb
 - lib/rubyn_code/memory/search.rb
@@ -353,9 +366,17 @@ files:
 - lib/rubyn_code/protocols/shutdown_handshake.rb
 - lib/rubyn_code/self_test.rb
 - lib/rubyn_code/skills/RUBYN.md
+- lib/rubyn_code/skills/auto_suggest.rb
 - lib/rubyn_code/skills/catalog.rb
 - lib/rubyn_code/skills/document.rb
+- lib/rubyn_code/skills/gemfile_parser.rb
 - lib/rubyn_code/skills/loader.rb
+- lib/rubyn_code/skills/matcher.rb
+- lib/rubyn_code/skills/pack_context.rb
+- lib/rubyn_code/skills/pack_installer.rb
+- lib/rubyn_code/skills/pack_manager.rb
+- lib/rubyn_code/skills/registry_autoload.rb
+- lib/rubyn_code/skills/registry_client.rb
 - lib/rubyn_code/skills/ttl_manager.rb
 - lib/rubyn_code/sub_agents/RUBYN.md
 - lib/rubyn_code/sub_agents/runner.rb
@@ -440,6 +461,7 @@ files:
 - skills/gems/rubocop.md
 - skills/gems/sidekiq.md
 - skills/gems/stripe.md
+- skills/megaplan/megaplan.md
 - skills/minitest/assertions.md
 - skills/minitest/fixtures.md
 - skills/minitest/integration_tests.md
@@ -530,8 +552,7 @@ post_install_message: |
   Rubyn Code installed! Run `rubyn-code --setup` to pin it to this Ruby
   so it works in any project regardless of .ruby-version.
 
-  Tip: Install with your latest Ruby for best performance:
-    RBENV_VERSION=4.0.2 gem install rubyn-code && rubyn-code --setup
+  Tip: install under your latest Ruby for best performance.
 rdoc_options: []
 require_paths:
 - lib
@@ -539,7 +560,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '4.0'
+      version: 4.0.2
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="