prr-kit 1.4.0 → 2.0.0

package/README.md

@@ -16,6 +16,10 @@ Module system, agent YAML, step-file workflows, CLI installer with full IDE inte
 
 **[🌐 Website](https://prrkit.sitenow.cloud)** **[📖 Full Documentation](https://prrkit.sitenow.cloud/docs)**
 
+<a href="https://unikorn.vn/p/prr-kit?ref=embed" target="_blank"><img src="https://unikorn.vn/api/widgets/badge/prr-kit?theme=light" alt="PR Review Kit trên Unikorn.vn" style="width: 256px; height: 64px;" width="256" height="64" /></a>
+<a href="https://unikorn.vn/p/prr-kit?ref=embed" target="_blank"><img src="https://unikorn.vn/api/widgets/badge/prr-kit/rank?theme=light&type=daily" alt="PR Review Kit - Hàng ngày" style="width: 250px; height: 64px;" width="250" height="64" /></a>
+
+
 ## Quick Start
 
 ```bash
@@ -274,18 +278,20 @@ Pauses **twice** for user input: once to select the PR/branch, once for review i
 
 | Code | Command | Description |
 |------|---------|-------------|
-| `SP` | Select PR | Fetch latest → list open PRs (via `gh`) or branches → select head + base → load diff |
+| `SP` | Select PR | Fetch latest → list open PRs or branches → select head + base → load diff |
 | `DP` | Describe PR | Classify PR type, generate summary, file-by-file walkthrough |
+| `CC` | Collect Context | Build PR-specific knowledge base from project docs, config files, standards, and external tools — run after DP, before any review |
 | `GR` | General Review | Logic, naming, readability, DRY, best practices, etc. — adapted to your stack |
 | `SR` | Security Review | OWASP Top 10, secrets, auth, rate limits, injection, etc. — adapted to your project |
 | `PR` | Performance Review | N+1 queries, memory leaks, async patterns, caching, etc. — adapted to your stack |
 | `AR` | Architecture Review | SOLID, layers, coupling, consistency with codebase, etc. — adapted to your architecture |
 | `BR` | Business Review | User impact, business risk, feature completeness, data safety, observability — adapted to your project |
+| `PM` | Party Mode 🎉 | All reviewers discuss the PR together in one collaborative session |
 | `IC` | Improve Code | Concrete BEFORE/AFTER code suggestions |
 | `AK` | Ask Code | Q&A about specific changes in this PR |
 | `RR` | Generate Report | Compile all findings → Markdown report in `_prr-output/reviews/` |
-| `PC` | Post Comments | Post inline code comments to GitHub PR via `gh` Reviews API |
-| `PM` | Party Mode 🎉 | All reviewers in one collaborative session |
+| `PC` | Post Comments | Post inline review comments to GitHub, GitLab, Azure DevOps, or Bitbucket PR |
+| `SS` | Select Session | List past review sessions and resume one |
 | `CL` | Clear | Remove context files and/or review reports from output folder |
 | `HH` | Help | Show this guide |
 
@@ -316,7 +322,7 @@ Enter PR number → base and head resolved automatically.
 | PRR Master | `/prr-master` | Orchestrator — routes all workflows, full menu |
 | PRR Quick | `/prr-quick` | One-command full pipeline (select → review → report) |
 
-Specialist reviewer agents are orchestrated internally by the master agent and party-mode workflow. Use `[PM] Party Mode` from the master menu to run all reviewers in a collaborative session.
+Specialist reviewer agents are orchestrated internally by the master agent and party-mode workflow. Use **[PM] Party Mode** from the master menu (`/prr-master`) to run all reviewers together in one collaborative session.
 
 ## Reviewers at a Glance
 
@@ -343,7 +349,10 @@ All findings use a standard format:
 
 ## Context Collection
 
-After [DP] Describe PR, context is collected **automatically** — then the agent pauses once for your instructions:
+**In [QR] Quick Review:** context is collected automatically as Phase 2.5 — no manual step needed.
+**In manual mode (SP → DP → reviews):** run **[CC] Collect Context** after [DP] and before starting any review.
+
+Either way, the agent pauses once for your instructions before building the knowledge base:
 
 1. Analyzes changed files to detect domains (`authentication`, `state-management`, etc.)
 2. Reads relevant config files (`.eslintrc`, `.prettierrc`, `tsconfig.json`) and standards docs (`CONTRIBUTING.md`, `ARCHITECTURE.md`)
@@ -367,7 +376,7 @@ When `[PC] Post Comments` is run with `platform_repo` configured, it posts findi
 
 ## Supported IDEs
 
-Antigravity, Auggie, Claude Code, Cline, Codex, Crush, Cursor, Gemini CLI, GitHub Copilot, iFlow, Kilo, Kiro, OpenCode, QwenCoder, Roo Cline, Rovo Dev, Trae, Windsurf
+Antigravity, Augment Code, Claude Code, Cline, Codex, Crush, Cursor, Gemini CLI, GitHub Copilot, iFlow, Kilo, Kiro, OpenCode, QwenCoder, Roo Code, Rovo Dev, Trae, Windsurf
 
 ## Requirements
 
@@ -394,10 +403,12 @@ prr-kit/
 │   ├── core/
 │   │   ├── agents/
 │   │   │   └── prr-master.agent.yaml   # Master orchestrator + menu
-│   │   └── tasks/
-│   │       ├── help.md                 # [HH] Help
-│   │       ├── clear.md                # [CL] Clear output files
-│   │       └── workflow.xml            # Workflow engine rules
+│   │   ├── tasks/
+│   │   │   ├── help.md                 # [HH] Help
+│   │   │   ├── clear.md                # [CL] Clear output files
+│   │   │   └── workflow.xml            # Workflow engine rules
+│   │   └── workflows/
+│   │       └── party-mode/             # [PM] Party Mode — all reviewers together
 │   └── prr/
 │       ├── agents/                     # Specialist reviewer agents (GR SR PR AR)
 │       ├── config-template.yaml        # Full config template with all options

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "prr-kit",
-  "version": "1.4.0",
+  "version": "2.0.0",
   "description": "AI-driven Pull Request Review Kit — structured agent workflows for thorough, consistent code review",
   "main": "tools/cli/prr-cli.js",
   "bin": {

package/src/core/agents/prr-master.agent.yaml

@@ -24,10 +24,11 @@ agent:
       - When a PM MCP is available, extract issue key from branch name and fetch acceptance criteria to use as review checklist
 
   critical_actions:
-    - "Context is collected AUTOMATICALLY after Describe PR — no manual context collection needed"
+    - "In [QR] Quick Review: context is collected AUTOMATICALLY as part of the pipeline — no manual step needed"
+    - "In standalone mode (SP → DP → reviews): context is NOT auto-collected. After running DP, remind the user to run [CC] Collect Context before starting any review workflow for best results"
     - "Run [SP] Select PR FIRST before any review — never review without knowing the exact branch/diff"
     - "After Select PR, suggest running [DP] Describe PR to understand scope before diving into review"
-    - "Context collection happens automatically after DP — it's always fresh and PR-specific"
+    - "Context is always fresh and PR-specific — never stale or cached"
     - "Track completed reviews and remind user of remaining uncompleted review types"
     - "For PRs touching auth, API keys, or user data: always suggest [SR] Security Review"
     - "For feature PRs and PRs with data migration: always run [BR] Business Review to assess user impact and deployment risk"
@@ -46,6 +47,10 @@ agent:
       exec: "{project-root}/_prr/prr/workflows/2-analyze/describe-pr/workflow.md"
       description: "[DP] Describe PR: Auto-generate PR type, summary, file-by-file walkthrough"
 
+    - trigger: "CC or fuzzy match on collect-context"
+      exec: "{project-root}/_prr/prr/workflows/2-analyze/collect-pr-context/workflow.md"
+      description: "[CC] Collect Context: Build PR-specific knowledge base (run after DP, before reviews)"
+
     - trigger: "GR or fuzzy match on general-review"
       workflow: "{project-root}/_prr/prr/workflows/3-review/general-review/workflow.yaml"
       description: "[GR] General Review: Code quality analysis — adapted to your stack"
@@ -70,6 +75,10 @@ agent:
       workflow: "{project-root}/_prr/prr/workflows/4-improve/improve-code/workflow.yaml"
       description: "[IC] Improve Code: Concrete inline code suggestions with before/after fixes"
 
+    - trigger: "PM or fuzzy match on party-mode"
+      exec: "{project-root}/_prr/core/workflows/party-mode/workflow.md"
+      description: "[PM] Party Mode: All reviewers discuss the PR together in one collaborative session"
+
     - trigger: "AK or fuzzy match on ask-code"
       exec: "{project-root}/_prr/prr/workflows/5-ask/ask-code/workflow.md"
       description: "[AK] Ask: Interactive Q&A about specific code changes in this PR"

package/src/core/tasks/help.md

@@ -12,12 +12,13 @@ Use `/prr-help` anytime for guidance on what to do.
 **Per PR — Manual mode (step by step):**
 1. **[SP] Select PR** — Fetch latest, list branches/PRs, choose what to review
 2. **[DP] Describe PR** — Auto-generate PR type, summary, file-by-file walkthrough
-   ↳ *Context collected automatically — fresh, PR-specific, no setup needed*
-3. **[GR/SR/PR/AR/BR] Review** — Run one or more specialized reviews
-4. **[IC] Improve Code** — Get concrete code suggestions with inline fixes
-5. **[AK] Ask** — Ask specific questions about the code changes
-6. **[RR] Generate Report** — Compile all findings into a Markdown report
-7. **[PC] Post Comments** — Post inline review comments to GitHub / GitLab / Azure DevOps / Bitbucket
+3. **[CC] Collect Context** — Build a PR-specific knowledge base from your project docs, configs, stack rules, and external tools (Jira, Confluence, Figma). Run this before any review for best results.
+4. **[GR/SR/PR/AR/BR] Review** — Run one or more specialized reviews
+5. **[PM] Party Mode** 🎉 — All reviewers discuss the PR together in one collaborative session
+6. **[IC] Improve Code** — Get concrete code suggestions with inline fixes
+7. **[AK] Ask** — Ask specific questions about the code changes
+8. **[RR] Generate Report** — Compile all findings into a Markdown report
+9. **[PC] Post Comments** — Post inline review comments to GitHub / GitLab / Azure DevOps / Bitbucket
 
 ### Available Reviews
 
@@ -37,4 +38,5 @@ Use `/prr-help` anytime for guidance on what to do.
 ### Utilities
 
 - **[SS] Select Session** — List past review sessions and resume one. Use this at the start of a new conversation to pick up where you left off.
+- **[HH] Help** — Show this guide.
 - **[CL] Clear** — Delete one or more past review session folders. Choose specific sessions or clear all.

package/src/core/workflows/party-mode/steps/step-01-load-reviewers.md

@@ -15,10 +15,17 @@ It contains stack-specific rules, ESLint/linting rules, project guidelines (CLAU
 
 If no knowledge base exists (DP was not run), proceed with local context only — do not block.
 
-**Read `user_instructions.review_scope`** from the knowledge base:
-- If `"all"` (or knowledge base missing) → all 5 reviewers are active.
-- If a list (e.g. `[SR, AR]`) → only activate reviewers matching those codes:
-  `GR` = Alex · `SR` = Sam · `PR` = Petra · `AR` = Arch · `BR` = Biz
+**Read `user_instructions`** from the knowledge base:
+
+- **`review_scope`**: determines active reviewers
+  - If `"all"` (or knowledge base missing) → all 5 reviewers are active.
+  - If a list (e.g. `[SR, AR]`) → only activate reviewers matching those codes:
+    `GR` = Alex · `SR` = Sam · `PR` = Petra · `AR` = Arch · `BR` = Biz
+
+- **`focus_areas`** / **`custom_requirements`** / **`context_notes`**: if `user_instructions.provided` is true, store these in working context — all active reviewers will apply them in step 2:
+  - `focus_areas` → each reviewer must prioritize these areas above their default checklist
+  - `custom_requirements` → treat as mandatory checks (prefix each with "MANDATORY:")
+  - `context_notes` → background info explaining trade-offs or constraints; do not flag issues the user has explicitly accepted
 
 ### 2. Introduce Party Mode
 

package/src/core/workflows/party-mode/steps/step-02-discussion.md

@@ -9,9 +9,14 @@ description: "Run the multi-reviewer discussion and compile unified findings"
 
 > **Active reviewers only.** Read the active reviewer list from step 1 (determined by `user_instructions.review_scope`). Skip any reviewer section below whose code is not in the active list. Only active reviewers speak and produce findings.
 
+> **User instructions (if `user_instructions.provided` is true):** Before each reviewer begins, they must:
+> 1. Prioritize any `focus_areas` above their default checklist
+> 2. Include all `custom_requirements` as mandatory checks (prefix each finding with "MANDATORY:")
+> 3. Use `context_notes` as background — do not flag issues the user explicitly accepted as trade-offs
+
 ### 1. Round 1 — Each Reviewer's Initial Take
 
-Go through the diff once per reviewer. Each reviewer applies rules from the PR knowledge base loaded in step 1 in addition to their domain expertise.
+Go through the diff once per reviewer. Each reviewer applies rules from the PR knowledge base loaded in step 1, applies `user_instructions` (focus areas, mandatory requirements, context notes), and uses their domain expertise.
 
 ---
 

package/src/prr/workflows/1-discover/select-pr/steps/step-05-confirm.md

@@ -43,7 +43,10 @@ Create the folder:
 mkdir -p "{session_output}"
 ```
 
-**Store `session_output` in working context** — all subsequent workflows in this session will use it.
+**Store in working context** — all subsequent workflows in this session will use these values:
+- `session_output` = computed above
+- `target_branch` = `selected_branch`   ← canonical name used by all downstream workflows
+- `base_branch`, `diff_range`, `pr_number`, `pr_title`, `pr_author`, `pr_body`, `pr_head_sha`, `active_platform`, `platform_repo` = from step 3
 
 ### 0b. Generate Diffs Folder
 

package/src/prr/workflows/2-analyze/collect-pr-context/steps/step-04-build-knowledge-base.md

@@ -16,7 +16,18 @@ Transform collected data into structured knowledge base optimized for reviewers.
 🧠 Building PR-specific knowledge base...
 ```
 
-### 2. Create Knowledge Base Structure
+### 2. Map `manual_context` → `user_instructions`
+
+Using the `manual_context` variable set in step-03:
+
+- **If `manual_context` is null** (user skipped): set `user_instructions.provided = false`, all other fields `null`.
+- **If `manual_context` is not null** (user provided text): set `user_instructions.provided = true`, `raw = manual_context`, then parse the free-form text:
+  - `review_scope` — look for scope signals ("only SR", "skip performance", "security and architecture"). Default `"all"` if none found.
+  - `focus_areas` — extract specific things to prioritize (e.g. "focus on JWT handling" → `["JWT handling"]`). `null` if none.
+  - `custom_requirements` — extract mandatory checks the user stated (e.g. "all endpoints must have auth middleware"). `null` if none.
+  - `context_notes` — extract background info, trade-offs, constraints. `null` if none.
+
+### 3. Create Knowledge Base Structure
 
 Build YAML structure with all collected context:
 
@@ -288,6 +299,11 @@ reviewer_guidance:
     - "Check Pinia setup function style (not Options API)"
     - "Verify SRP adherence"
 
+  business_review:
+    - "Verify feature matches acceptance criteria"
+    - "Check for user-facing regressions"
+    - "Flag missing observability (logging, metrics) for new flows"
+
 context_sources:
   # Track what sources were used
   primary_docs: [CLAUDE.md, AGENTS.md]
@@ -344,4 +360,4 @@ Review workflows (GR, SR, PR, AR, BR) find the knowledge base via working contex
 
 ### 7. Workflow Complete
 
-Mark workflow as complete. Context is ready for use by review workflows (GR, SR, PR, AR).
+Mark workflow as complete. Context is ready for use by review workflows (GR, SR, PR, AR, BR, IC).

package/src/prr/workflows/2-analyze/collect-pr-context/workflow.md

@@ -26,8 +26,10 @@ output_file: "{session_output}/pr-context.yaml"
 
 ## WHEN TO RUN
 
-**Automatically** after [DP] Describe PR in the quick workflow.
-Runs before any review workflows to provide fresh context.
+**In [QR] Quick Review:** runs automatically as Phase 2.5 — no manual step needed.
+
+**In standalone mode:** run manually after [DP] Describe PR and before starting any review workflow (GR/SR/PR/AR/BR).
+The master agent will remind you to run context collection if you attempt to start a review without it.
 
 ## CONTEXT SOURCES
 

package/src/prr/workflows/2-analyze/describe-pr/steps/step-04-output.md

@@ -44,6 +44,11 @@ Summary:
 
 Recommended next steps:
 {recommended_reviews}
+
+💡 Before reviewing: run [CC] Collect Context to build a fresh PR-specific knowledge base.
+   Reviews use this context to apply your project's rules, stack-specific guidelines, and any
+   external sources (Jira, Confluence, Figma) — skipping it means reviewers work with
+   general rules only.
 ```
 
 Workflow complete. Return to agent menu.

package/src/prr/workflows/3-review/architecture-review/instructions.xml

@@ -98,7 +98,7 @@ Context: Loaded architectural patterns & ADRs from project docs
   </step>
 
   <step n="7" goal="Compile and write findings">
-    <action>Group findings: Layer Violations | Coupling Issues | Consistency Problems | SOLID Violations | ❓ Questions for Author</action>
+    <action>Group findings: Layer Violations | Coupling Issues | Consistency Problems | Blast Radius &amp; Breaking Changes | SOLID Violations | ❓ Questions for Author</action>
     <action>For each finding: reference the EXISTING pattern that should be followed instead</action>
     <action>Write findings to {output_file}</action>
     <action>Update {pr_context}: add 'architecture-review' to completed list</action>

package/src/prr/workflows/3-review/business-review/workflow.yaml

@@ -14,5 +14,5 @@ installed_path: "{project-root}/_prr/prr/workflows/3-review/business-review"
 instructions: "{installed_path}/instructions.xml"
 validation: "{installed_path}/checklist.md"
 
-pr_context: "working-context:target_branch,base_branch,pr_number,pr_knowledge_base"
+pr_context: "working-context:target_branch,base_branch,pr_number,pr_knowledge_base,pr_type,completed_reviews"
 output_file: "{session_output}/business-review.md"

package/src/prr/workflows/6-report/generate-report/steps/step-01-collect.md

@@ -41,6 +41,12 @@ From each file, extract all findings with their:
 - `🟢` or `Low` → Suggestion
 - `❓` → Question (collect separately — do not count as blocker/warning/suggestion)
 
+**Special handling — `improve-code.md`:**
+The improve-code output uses `[CATEGORY]` format (`[BUGS]`, `[QUALITY]`, `[PERFORMANCE]`, `[BEST-PRACTICES]`), not severity emojis. Treat improve-code findings as a separate collection:
+- Do NOT mix them into the Blockers/Warnings/Suggestions counts
+- Include them in the report's **💡 Code Improvement Suggestions** section (see template)
+- Map `[BUGS]` → 🔴 only if the improve-code entry describes an actual bug that could cause incorrect behavior; otherwise keep as 💡 Improvement
+
 ### 4. Count Statistics
 
 Count:

package/src/prr/workflows/6-report/post-comments/steps/step-01-format.md

@@ -54,6 +54,19 @@ Store as `{commit_sha}`.
 
 ### 3. Load Review Report
 
+Check that `{session_output}/final-review.md` exists:
+```bash
+ls "{session_output}/final-review.md"
+```
+
+If it does NOT exist:
+```
+❌ No report found at {session_output}/final-review.md
+   Run [RR] Generate Report first to compile all findings into a report,
+   then run [PC] Post Comments to post them.
+```
+Stop workflow.
+
 Read the report at `{session_output}/final-review.md`.
 
 ### 4. Parse All Findings

package/src/prr/workflows/6-report/post-comments/steps/step-02-post.md

@@ -74,21 +74,40 @@ done
 ---
 
 **Bitbucket:**
+
+**⚠️ Do NOT embed `$(cat ...)` in curl `-d` — the summary body contains emojis and backticks that will break shell expansion.**
+
+Use the runtime script approach to build the summary payload first:
+
+Write `{temp_dir}/build-bb-summary.mjs` (or `.py`) using the Write tool:
+
+```js
+// Node.js
+import { readFileSync, writeFileSync } from 'fs'
+const body = readFileSync("{temp_dir}/prr-summary.md", "utf-8")
+const payload = { content: { raw: body } }
+writeFileSync("{temp_dir}/prr-bb-summary.json", JSON.stringify(payload, null, 2), "utf-8")
+console.log("OK: summary payload written")
+```
+
+Execute: `node "{temp_dir}/build-bb-summary.mjs"`
+
+Then post using `--data @`:
 ```bash
 # Post summary
 curl -s -X POST \
   "https://api.bitbucket.org/2.0/repositories/{platform_repo}/pullrequests/{pr_number}/comments" \
   -H "Authorization: Bearer {BB_TOKEN}" \
   -H "Content-Type: application/json" \
-  -d "{\"content\": {\"raw\": \"$(cat '{temp_dir}/prr-summary.md')\"}}"
+  --data "@{temp_dir}/prr-bb-summary.json"
 
 # Post each inline comment
-for payload in "{temp_dir}/prr-bb-"*.json; do
+for payload in "{temp_dir}/prr-bb-"[0-9]*.json; do
   curl -s -X POST \
     "https://api.bitbucket.org/2.0/repositories/{platform_repo}/pullrequests/{pr_number}/comments" \
     -H "Authorization: Bearer {BB_TOKEN}" \
     -H "Content-Type: application/json" \
-    -d "@$payload"
+    --data "@$payload"
 done
 ```
 
@@ -146,8 +165,12 @@ rm -f "{temp_dir}/prr-payload.json" \
        "{temp_dir}/prr-summary.md" \
        "{temp_dir}/prr-thread-"*.json \
        "{temp_dir}/prr-bb-"*.json \
+       "{temp_dir}/prr-bb-summary.json" \
        "{temp_dir}/build-payload.mjs" \
-       "{temp_dir}/build-payload.py"
+       "{temp_dir}/build-payload.py" \
+       "{temp_dir}/build-bb-summary.mjs" \
+       "{temp_dir}/build-bb-summary.py"
+rmdir "{temp_dir}" 2>/dev/null || true
 ```
 
 ---

package/src/prr/workflows/quick/workflow.md

@@ -238,6 +238,12 @@ Analyze the diff and classify as one of: `bugfix` | `feature` | `refactor` | `pe
 For each changed file, write a 1-2 sentence summary of what changed and why.
 Group by: new files | modified files | deleted files | renamed files.
 
+### 2b2. Generate Impact Map
+Scan for cross-cutting side effects following the same logic as `describe-pr/steps/step-03-walkthrough.md` section 3:
+- Shared/generic module changes → count consumers, flag breaking vs additive
+- Side effect scan → observer/reactive dependencies outside the diff
+- Output the IMPACT MAP block
+
 ### 2c. Output description
 Print to screen:
 ```
@@ -249,8 +255,13 @@ Print to screen:
 
 ### Files Changed
 {walkthrough table}
+
+{impact_map}
 ```
 
+Write description to file: `{session_output}/pr-description.md`
+Store `pr_type` and `risk_level` in working context.
+
 ---
 
 ## PHASE 2.5 — COLLECT PR-SPECIFIC CONTEXT
@@ -268,14 +279,12 @@ On completion, store `pr_knowledge_base` = path to the generated context file.
 ## PHASE 3 — REVIEW
 *Execute all review types automatically, one by one.*
 
-**Before each review, set these variables so the review instructions resolve correctly:**
-- `pr_context` = working context (`target_branch`, `base_branch`, `pr_number`, `pr_knowledge_base`)
-- `target_branch` = `pr_context.pr.target_branch`
-- `base_branch` = `pr_context.pr.base_branch`
-- `pr_number` = `pr_context.pr.pr_number`
-- `pr_knowledge_base` = path stored in `pr_context` (set by Phase 2.5)
-- `target_repo`, `communication_language` = from config
-- `output_file` = per-review path defined below *(ensures findings are saved to disk for [RR] and [PC] later)*
+**Before each review, confirm these variables are set in working context (all set by earlier phases):**
+- `target_branch`, `base_branch`, `pr_number` — set by Phase 1 (Select PR)
+- `pr_knowledge_base` — set by Phase 2.5 (`{session_output}/pr-context.yaml`)
+- `session_output` — set by Phase 1 when session folder was created
+- `target_repo`, `communication_language` — from config
+- `output_file` — per-review path defined below *(ensures findings are saved to disk for [RR] and [PC] later)*
 
 **Scope gate:** Read `user_instructions.review_scope` from `{pr_knowledge_base}`.
 - If `"all"` (or knowledge base missing) → run all reviews 3a–3e normally.
@@ -335,6 +344,7 @@ Count totals:
 - `{blocker_count}` = number of 🔴 findings
 - `{warning_count}` = number of 🟡 findings
 - `{suggestion_count}` = number of 🟢 findings
+- `{question_count}` = number of ❓ findings
 
 Write report to: `{session_output}/final-review.md`
 
@@ -391,6 +401,7 @@ Report:  {session_output}/final-review.md
 🔴 Blockers:    {blocker_count}
 🟡 Warnings:    {warning_count}
 🟢 Suggestions: {suggestion_count}
+❓ Questions:   {question_count}
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 ```
 

package/tools/cli/installers/lib/ide/platform-codes.yaml

@@ -41,7 +41,7 @@ platforms:
       template_type: antigravity
 
   auggie:
-    name: "Auggie"
+    name: "Augment Code"
     preferred: false
     category: cli
     description: "AI development tool"
@@ -122,10 +122,10 @@ platforms:
     description: "OpenCode terminal coding assistant"
     installer:
       targets:
-        - target_dir: .opencode/agent
+        - target_dir: .opencode/agents
           template_type: opencode
           artifact_types: [agents]
-        - target_dir: .opencode/command
+        - target_dir: .opencode/commands
           template_type: opencode
           artifact_types: [workflows]
 
@@ -139,7 +139,7 @@ platforms:
       template_type: default
 
   roo:
-    name: "Roo Cline"
+    name: "Roo Code"
     preferred: false
     category: ide
     description: "Enhanced Cline fork"