specrails-core 3.3.0 → 3.4.0

package/docs/user-docs/installation.md

@@ -1,21 +1,31 @@
 # Installation
 
-Install SpecRails into any git repository in two steps: run the installer, then run `/setup` inside your AI CLI.
+Install SpecRails into any git repository in two steps: install, then run `/specrails:setup` inside your AI CLI.
 
 SpecRails supports both **Claude Code** and **OpenAI Codex**. The installer detects which CLI you have and configures accordingly. See [Codex vs Claude Code](codex-vs-claude-code.md) for a feature comparison.
 
+> **Looking for the comprehensive reference?** See [Installation & Setup](../installation.md) for full wizard phase details and advanced configuration.
+
 ## Requirements
 
+### Plugin method (recommended)
+
 | Tool | Version | Notes |
 |------|---------|-------|
-| **Node.js** | 18+ | Required for the installer |
-| **Claude Code** | Latest | Stable — [install guide](https://docs.anthropic.com/en/docs/claude-code) |
-| **Codex CLI** | Latest | Beta — `npm i -g @openai/codex` |
+| **Claude Code** | Latest | [install guide](https://docs.anthropic.com/en/docs/claude-code) |
 | **Git** | Any | Your project must be a git repository |
 
-You need at least one of Claude Code or Codex CLI. If both are installed, the installer uses Claude Code by default. Override with `--provider codex` (or the env var `CLI_PROVIDER=codex`).
+No Node.js required.
+
+### Scaffold method (npx / Codex)
+
+| Tool | Version | Notes |
+|------|---------|-------|
+| **Node.js** | 18+ | Required for the installer |
+| **Claude Code** or **Codex CLI** | Latest | See [Codex vs Claude Code](codex-vs-claude-code.md) |
+| **Git** | Any | Your project must be a git repository |
 
-Optional but recommended:
+Optional but recommended (both methods):
 
 | Tool | Why |
 |------|-----|
@@ -23,16 +33,28 @@ Optional but recommended:
 
 ## Install
 
-Run the installer from inside your project directory:
+### Plugin method (Claude Code)
+
+```bash
+claude plugin install sr
+```
+
+No cloning, no npm, nothing else. The plugin is now ready in all your Claude Code sessions.
+
+To update later: `claude plugin update sr`
+
+### Scaffold method (Claude Code or Codex)
+
+Run from inside your project directory:
 
 ```bash
 cd your-project
 npx specrails-core@latest init --root-dir .
 ```
 
-The installer copies agent templates, skills, and configuration files into `.claude/` (Claude Code) or `.codex/` (Codex). It does not modify your existing code.
+The installer copies templates and commands into `.claude/` (Claude Code) or `.codex/` (Codex). It does not modify your existing code.
 
-### Flags
+#### Flags
 
 | Flag | Effect |
 |------|--------|
@@ -40,30 +62,17 @@ The installer copies agent templates, skills, and configuration files into `.cla
 | `--yes` / `-y` | Skip confirmation prompts |
 | `--provider <claude\|codex>` | Force a specific AI CLI (default: auto-detect) |
 
-You can also force a specific provider:
-
-```bash
-npx specrails-core@latest init --root-dir . --provider codex
-```
-
-Alternatively, use the `CLI_PROVIDER` env var (legacy):
-
-```bash
-CLI_PROVIDER=codex npx specrails-core@latest init --root-dir .
-```
-
-### What gets installed
+#### What gets installed (scaffold method)
 
 **Claude Code:**
 
 ```
 your-project/
 └── .claude/
-    ├── commands/setup.md         # The /setup wizard
-    ├── skills/                   # Workflow skills (/sr:*, /opsx:*)
+    ├── commands/specrails/setup.md      # The /specrails:setup wizard
+    ├── skills/                   # Workflow skills (/specrails:*, /opsx:*)
     ├── agents/                   # Agent definitions
     ├── rules/                    # Per-layer coding conventions
-    ├── web-manager/              # Pipeline Monitor dashboard (optional)
     └── settings.json             # Permissions
 ```
 
@@ -73,7 +82,7 @@ your-project/
 your-project/
 ├── AGENTS.md                     # SpecRails agent instructions for Codex
 └── .codex/
-    ├── skills/                   # Workflow skills (/sr:*, /opsx:*)
+    ├── skills/                   # Workflow skills (/specrails:*, /opsx:*)
     ├── agents/                   # Agent definitions (TOML)
     ├── rules/                    # Per-layer coding conventions
     └── config.toml               # Permissions
@@ -81,9 +90,9 @@ your-project/
 
 The installer also writes `.specrails-version` and `.specrails-manifest.json` to track the installed version.
 
-## Configure with /setup
+## Configure with /specrails:setup
 
-After installation, open your AI CLI in your project and run the setup wizard:
+After either installation method, open your AI CLI in your project and run:
 
 ```bash
 claude    # Claude Code
@@ -92,35 +101,36 @@ codex     # Codex
 ```
 
 ```
-/setup
+/specrails:setup
 ```
 
-By default, `/setup` runs the full 5-phase wizard:
+By default, `/specrails:setup` runs the full 5-phase wizard:
 
 | Phase | What happens |
 |-------|-------------|
 | **1. Analyze** | Detects your tech stack, architecture layers, and CI commands |
 | **2. Personas** | Researches your domain and generates VPC user profiles |
 | **3. Configure** | Asks about your backlog provider, git workflow, and agent selection |
-| **4. Generate** | Fills all templates with your project-specific context |
-| **5. Cleanup** | Removes setup files, leaving only your tailored workflow |
-
-**In a hurry?** Run `/setup --lite` instead — three questions, sensible defaults, done in under a minute.
+| **4. Generate** | Generates project data files (`.specrails/` or `.claude/`) with your context |
+| **5. Cleanup** | Removes setup scaffolding, leaving only your tailored workflow |
 
-After setup, `.claude/` contains fully configured agents and commands ready to use. The `/setup` command removes itself — it only runs once.
+**In a hurry?** Run `/specrails:setup --lite` instead — three questions, sensible defaults, done in under a minute.
 
 ## Verify
 
 Check that everything installed correctly:
 
 ```bash
-# List generated agents
+# Plugin method: check project data was generated
+ls .specrails/
+
+# Scaffold method: list generated agents
 ls .claude/agents/
 
-# Check for unresolved placeholders (should return nothing)
+# Scaffold method: check for unresolved placeholders (should return nothing)
 grep -r '{{[A-Z_]*}}' .claude/agents/ .claude/commands/ .claude/rules/
 
-# Check the installed version
+# Scaffold method: check the installed version
 cat .specrails-version
 ```
 
@@ -141,7 +151,7 @@ The installer warns if SpecRails artifacts already exist. You can merge (install
 
 ### Placeholders not resolved
 
-If you see `{{PLACEHOLDER}}` in generated files, the `/setup` wizard did not complete. Re-run `/setup` or fill the values manually.
+If you see `{{PLACEHOLDER}}` in generated files (scaffold method), the `/specrails:setup` wizard did not complete. Re-run `/specrails:setup` or fill the values manually.
 
 ### "No Claude API key configured"
 
@@ -183,4 +193,4 @@ npx specrails-core@latest init --root-dir . --provider codex
 
 ---
 
-[Quick Start →](quick-start.md) · [Getting Started (Codex) →](getting-started-codex.md) · [CLI Reference →](cli-reference.md)
+[← Getting Started](../getting-started.md) · [Quick Start →](quick-start.md) · [Getting Started (Codex) →](getting-started-codex.md) · [CLI Reference →](cli-reference.md)

package/docs/user-docs/quick-start.md

@@ -7,7 +7,6 @@ Get SpecRails running in your project in under 10 minutes.
 ## Before you begin
 
 You need:
-- **Node.js 18+** — check with `node --version`
 - **Claude Code** — install from [docs.anthropic.com/en/docs/claude-code](https://docs.anthropic.com/en/docs/claude-code)
 - **A git repository** — your project must have a `.git` directory
 
@@ -16,21 +15,19 @@ Optional:
 
 ## Step 1: Install
 
-From inside your project directory:
+### Plugin method (recommended — no Node.js required)
 
 ```bash
-npx specrails-core@latest init --root-dir .
+claude plugin install sr
 ```
 
-Expected output:
+### Scaffold method (if you need Node.js / Codex)
 
-```
-✓ Prerequisites checked
-✓ Templates installed → .claude/
-✓ Version tracked → .specrails-version
+```bash
+npx specrails-core@latest init --root-dir .
 ```
 
-This copies agent templates and commands into `.claude/`. Your existing code is not touched.
+Your existing code is not touched by either method.
 
 ## Step 2: Run the setup wizard
 
@@ -43,7 +40,7 @@ claude
 Then run:
 
 ```
-/setup
+/specrails:setup
 ```
 
 The wizard runs the full 5-phase setup (about 5 minutes). It analyzes your codebase and configures SpecRails for your specific project:
@@ -63,32 +60,29 @@ Phase 3/5  Configuration...
            → Git workflow: trunk-based
 
 Phase 4/5  Generating files...
-           → sr-architect.md (adapted to your stack)
-           → sr-developer.md (knows your CI commands)
-           → sr-reviewer.md (runs your specific checks)
-           → 11 more agents
+           → .specrails/config.yaml
+           → .specrails/personas/ (3 VPC profiles)
+           → .specrails/rules/ (per-layer conventions)
 
-Phase 5/5  Cleanup complete. /setup removed.
+Phase 5/5  Cleanup complete.
 
-✓ SpecRails is ready. Run /sr:implement to start building.
+✓ SpecRails is ready. Run /specrails:implement to start building.
 ```
 
-After setup, the `/setup` command is gone — it's a one-time wizard.
-
-**In a hurry?** Use `/setup --lite` for a 3-question quick setup (under a minute). You can always run the full wizard later.
+**In a hurry?** Use `/specrails:setup --lite` for a 3-question quick setup (under a minute). You can always run the full wizard later.
 
 ## Step 3: Implement your first feature
 
 Pick something small. Either reference a GitHub Issue or describe it in plain text:
 
 ```
-/sr:implement #42
+/specrails:implement #42
 ```
 
 or:
 
 ```
-/sr:implement "add a health check endpoint to the API"
+/specrails:implement "add a health check endpoint to the API"
 ```
 
 The pipeline runs automatically:
@@ -128,7 +122,7 @@ One command. The PR is ready for human review.
 **Explore the backlog:**
 
 ```
-/sr:product-backlog
+/specrails:product-backlog
 ```
 
 See your tickets ranked by persona fit and effort. The top 3 are safe to implement next. Uses local tickets by default.
@@ -136,7 +130,7 @@ See your tickets ranked by persona fit and effort. The top 3 are safe to impleme
 **Generate new feature ideas:**
 
 ```
-/sr:update-product-driven-backlog
+/specrails:update-product-driven-backlog
 ```
 
 The Product Manager researches your competitive landscape and creates new tickets (local by default, or GitHub Issues if configured).
@@ -144,7 +138,7 @@ The Product Manager researches your competitive landscape and creates new ticket
 **Run multiple features in parallel:**
 
 ```
-/sr:implement #42, #43, #44
+/specrails:implement #42, #43, #44
 ```
 
 Each feature gets its own git worktree. Pipelines run concurrently and merge automatically.
@@ -152,11 +146,11 @@ Each feature gets its own git worktree. Pipelines run concurrently and merge aut
 **Ask why a decision was made:**
 
 ```
-/sr:why "why did we choose this database schema"
+/specrails:why "why did we choose this database schema"
 ```
 
-Agents record their reasoning as they work. `/sr:why` searches those records in plain language.
+Agents record their reasoning as they work. `/specrails:why` searches those records in plain language.
 
 ---
 
-[← Installation](installation.md) · [CLI Reference →](cli-reference.md) · [FAQ →](faq.md)
+[← Getting Started](../getting-started.md) · [← Installation](installation.md) · [CLI Reference →](cli-reference.md) · [FAQ →](faq.md)

package/docs/workflows.md

@@ -2,17 +2,17 @@
 
 SpecRails commands are Claude Code slash commands that orchestrate the agent pipeline. Here's every command, what it does, and when to use it.
 
-## The main workflow: `/sr:implement`
+## The main workflow: `/specrails:implement`
 
 This is the command you'll use most. It takes a feature request and drives it through the entire pipeline — from architecture to shipped PR.
 
 ### Usage
 
 ```
-/sr:implement #85                          # From a GitHub Issue
-/sr:implement #85, #71, #63               # Multiple issues (parallel)
-/sr:implement "add dark mode toggle"       # Text description
-/sr:implement UI, Analytics               # By area (explores + selects)
+/specrails:implement #85                          # From a GitHub Issue
+/specrails:implement #85, #71, #63               # Multiple issues (parallel)
+/specrails:implement "add dark mode toggle"       # Text description
+/specrails:implement UI, Analytics               # By area (explores + selects)
 ```
 
 ### Flags
@@ -24,7 +24,7 @@ This is the command you'll use most. It takes a feature request and drives it th
 
 ### Pipeline phases
 
-When you run `/sr:implement #85`, here's what happens:
+When you run `/specrails:implement #85`, here's what happens:
 
 ```
 Phase -1    Environment check
@@ -65,7 +65,7 @@ For multiple features, each gets its own isolated worktree. Agents run concurren
 ### Example output
 
 ```
-/sr:implement #85
+/specrails:implement #85
 ```
 
 ```
@@ -103,25 +103,25 @@ PR #42 created: feat: add health check endpoint
 
 ---
 
-## `/sr:batch-implement`
+## `/specrails:batch-implement`
 
 Orchestrates **multiple independent features** in parallel using git worktrees. Use this when you have several unrelated features to ship at once.
 
 ```
-/sr:batch-implement #85, #71, #63
+/specrails:batch-implement #85, #71, #63
 ```
 
 Each feature gets its own worktree, its own agent pipeline, and its own PR. Features run concurrently for maximum speed.
 
 ---
 
-## `/sr:product-backlog`
+## `/specrails:product-backlog`
 
 View your prioritized product backlog, ranked by VPC fit and effort.
 
 ```
-/sr:product-backlog                # Full backlog
-/sr:product-backlog UI, API        # Filter by area
+/specrails:product-backlog                # Full backlog
+/specrails:product-backlog UI, API        # Filter by area
 ```
 
 ### What it shows
@@ -151,13 +151,13 @@ Safe Implementation Order (Wave 1):
 
 ---
 
-## `/sr:update-product-driven-backlog`
+## `/specrails:update-product-driven-backlog`
 
 Generate new feature ideas through product discovery. The Product Manager (Opus) researches your competitive landscape and generates ideas evaluated against your personas.
 
 ```
-/sr:update-product-driven-backlog              # All areas
-/sr:update-product-driven-backlog UI, API      # Focus areas
+/specrails:update-product-driven-backlog              # All areas
+/specrails:update-product-driven-backlog UI, API      # Focus areas
 ```
 
 ### What it does
@@ -170,40 +170,28 @@ Generate new feature ideas through product discovery. The Product Manager (Opus)
 
 ---
 
-## `/sr:health-check`
-
-Run a comprehensive codebase quality analysis.
-
-```
-/sr:health-check
-```
-
-Analyzes code quality, test coverage, technical debt, and dependency health. Compares with previous runs to detect regressions.
-
----
-
-## `/sr:refactor-recommender`
+## `/specrails:refactor-recommender`
 
 Scan for refactoring opportunities ranked by impact/effort ratio.
 
 ```
-/sr:refactor-recommender
+/specrails:refactor-recommender
 ```
 
 Identifies duplicates, long functions, large files, dead code, outdated patterns, and complex logic. Optionally creates GitHub Issues for tracking.
 
 ---
 
-## `/sr:compat-check`
+## `/specrails:compat-check`
 
 Analyze the backwards compatibility impact of a proposed change before implementation.
 
 ```
-/sr:compat-check #85                    # Check a specific issue
-/sr:compat-check #85 --save             # Check and save as the new API baseline
+/specrails:compat-check #85                    # Check a specific issue
+/specrails:compat-check #85 --save             # Check and save as the new API baseline
 ```
 
-The Architect's Phase 6 auto-check runs this analysis as part of every `/sr:implement` pipeline. You can also run it standalone to evaluate a change before committing to it.
+The Architect's Phase 6 auto-check runs this analysis as part of every `/specrails:implement` pipeline. You can also run it standalone to evaluate a change before committing to it.
 
 ### What it detects
 
@@ -218,17 +206,17 @@ When breaking changes are found, `compat-check` generates a **migration guide**
 
 ---
 
-## `/sr:why`
+## `/specrails:why`
 
 Search agent explanation records in plain language.
 
 ```
-/sr:why "why did we switch to event sourcing"
-/sr:why "why is pagination implemented this way"
-/sr:why "explain the auth middleware design"
+/specrails:why "why did we switch to event sourcing"
+/specrails:why "why is pagination implemented this way"
+/specrails:why "explain the auth middleware design"
 ```
 
-The Architect, Developer, and Reviewer record decision rationale in `.claude/agent-memory/explanations/` as they work. `/sr:why` searches these records semantically and surfaces the relevant context.
+The Architect, Developer, and Reviewer record decision rationale in `.claude/agent-memory/explanations/` as they work. `/specrails:why` searches these records semantically and surfaces the relevant context.
 
 This is useful for onboarding, code review, and revisiting past decisions without digging through git history.
 
@@ -294,14 +282,14 @@ Open-ended thinking mode. Use for brainstorming, investigating problems, or clar
 /opsx:explore
 ```
 
-### `/sr:opsx-diff` — Spec Change Diff
+### `/specrails:opsx-diff` — Spec Change Diff
 
 Visualize the before/after diff of an OpenSpec change — what behavioral requirements are being added, modified, or removed.
 
 ```
-/sr:opsx-diff <change-name>
-/sr:opsx-diff my-feature --format json
-/sr:opsx-diff my-feature --summary-only
+/specrails:opsx-diff <change-name>
+/specrails:opsx-diff my-feature --format json
+/specrails:opsx-diff my-feature --summary-only
 ```
 
 | Flag | Effect |
@@ -334,16 +322,16 @@ Or step by step:
 
 ---
 
-## `/sr:telemetry`
+## `/specrails:telemetry`
 
 Inspect per-agent execution metrics: token usage, estimated API cost, run count, average duration, and success/failure rate.
 
 ```
-/sr:telemetry
-/sr:telemetry --period today
-/sr:telemetry --agent sr-developer
-/sr:telemetry --format json
-/sr:telemetry --save
+/specrails:telemetry
+/specrails:telemetry --period today
+/specrails:telemetry --agent sr-developer
+/specrails:telemetry --format json
+/specrails:telemetry --save
 ```
 
 ### Flags
@@ -359,14 +347,14 @@ Reads Claude CLI JSONL session logs and agent-memory files to produce a cost das
 
 ---
 
-## `/sr:merge-resolve`
+## `/specrails:merge-resolve`
 
 Resolve git conflict markers using AI-powered context analysis.
 
 ```
-/sr:merge-resolve
-/sr:merge-resolve --files src/api/routes.ts src/db/schema.ts
-/sr:merge-resolve --context openspec/changes/
+/specrails:merge-resolve
+/specrails:merge-resolve --files src/api/routes.ts src/db/schema.ts
+/specrails:merge-resolve --context openspec/changes/
 ```
 
 ### Flags
@@ -381,32 +369,32 @@ For each conflict block, the command reads the OpenSpec context bundles from the
 
 ---
 
-## `/sr:retry`
+## `/specrails:retry`
 
-Resume a failed `/sr:implement` run from the last successful phase — without restarting from scratch.
+Resume a failed `/specrails:implement` run from the last successful phase — without restarting from scratch.
 
 ```
-/sr:retry <feature-name>              # Resume from the failed phase
-/sr:retry --list                      # List all available pipeline states
-/sr:retry <feature-name> --from architect   # Force resume from a specific phase
-/sr:retry <feature-name> --dry-run    # Resume in preview mode
+/specrails:retry <feature-name>              # Resume from the failed phase
+/specrails:retry --list                      # List all available pipeline states
+/specrails:retry <feature-name> --from architect   # Force resume from a specific phase
+/specrails:retry <feature-name> --dry-run    # Resume in preview mode
 ```
 
-When a pipeline fails mid-run (e.g., the reviewer hits a flaky CI issue), SpecRails saves pipeline state to `.claude/pipeline-state/<feature-name>.json`. `/sr:retry` reads that state, identifies which phases completed, and re-executes only the remaining phases.
+When a pipeline fails mid-run (e.g., the reviewer hits a flaky CI issue), SpecRails saves pipeline state to `.claude/pipeline-state/<feature-name>.json`. `/specrails:retry` reads that state, identifies which phases completed, and re-executes only the remaining phases.
 
 Valid `--from` phase values: `architect`, `developer`, `test-writer`, `doc-sync`, `reviewer`, `ship`, `ci`.
 
 ---
 
-## `/sr:vpc-drift`
+## `/specrails:vpc-drift`
 
 Detect when your VPC personas have drifted from what your product actually delivers.
 
 ```
-/sr:vpc-drift                         # Analyze all personas
-/sr:vpc-drift --persona "Alex,Sara"   # Filter to specific personas
-/sr:vpc-drift --verbose               # Show full attribute lists
-/sr:vpc-drift --format json           # Emit report as JSON
+/specrails:vpc-drift                         # Analyze all personas
+/specrails:vpc-drift --persona "Alex,Sara"   # Filter to specific personas
+/specrails:vpc-drift --verbose               # Show full attribute lists
+/specrails:vpc-drift --format json           # Emit report as JSON
 ```
 
 Compares persona Jobs/Pains/Gains against the product backlog, implemented features, and agent memory to surface alignment gaps. Produces a per-persona alignment score and concrete recommendations for updating your VPC.
@@ -415,27 +403,27 @@ Run this when your backlog feels disconnected from your users, or after a major
 
 ---
 
-## `/sr:memory-inspect`
+## `/specrails:memory-inspect`
 
 Inspect agent memory directories to understand what your agents remember and clean up stale data.
 
 ```
-/sr:memory-inspect                    # Inspect all agent memory
-/sr:memory-inspect sr-developer       # Inspect a specific agent
-/sr:memory-inspect --stale 14         # Flag files older than 14 days
-/sr:memory-inspect --prune            # Delete stale files (after confirmation)
+/specrails:memory-inspect                    # Inspect all agent memory
+/specrails:memory-inspect sr-developer       # Inspect a specific agent
+/specrails:memory-inspect --stale 14         # Flag files older than 14 days
+/specrails:memory-inspect --prune            # Delete stale files (after confirmation)
 ```
 
-Agents write persistent memory to `.claude/agent-memory/sr-*/`. Over time this can accumulate stale or orphaned files. `/sr:memory-inspect` shows per-agent stats (file count, size, last modified), recent entries, and actionable cleanup recommendations.
+Agents write persistent memory to `.claude/agent-memory/sr-*/`. Over time this can accumulate stale or orphaned files. `/specrails:memory-inspect` shows per-agent stats (file count, size, last modified), recent entries, and actionable cleanup recommendations.
 
 ---
 
-## `/sr:propose-spec`
+## `/specrails:propose-spec`
 
 Explore a feature idea and produce a structured proposal ready for the OpenSpec pipeline.
 
 ```
-/sr:propose-spec "add rate limiting to the API"
+/specrails:propose-spec "add rate limiting to the API"
 ```
 
 The command explores your codebase to understand existing patterns, then produces a structured proposal with: problem statement, proposed solution, out-of-scope items, acceptance criteria, technical considerations, and a complexity estimate.
@@ -449,7 +437,7 @@ Use this before creating a GitHub Issue when you want a well-formed spec rather
 Any workflow can be run in preview mode to see what would happen without making changes:
 
 ```
-/sr:implement --dry-run #85
+/specrails:implement --dry-run #85
 ```
 
 Preview mode runs the full pipeline but skips:
@@ -460,7 +448,7 @@ Preview mode runs the full pipeline but skips:
 The results are cached. Apply them later with:
 
 ```
-/sr:implement --apply health-check-endpoint
+/specrails:implement --apply health-check-endpoint
 ```
 
 ---

package/install.sh

@@ -276,8 +276,8 @@ if [[ "$CLI_PROVIDER" == "claude" ]]; then
         info "Agent Teams commands: skipped (opt-in, use interactive mode to enable)"
     else
         echo -e "  ${BOLD}Agent Teams commands are available (experimental):${NC}"
-        echo "    /sr:team-review — Multi-perspective code review with AI reviewers"
-        echo "    /sr:team-debug  — Collaborative debugging with competing hypotheses"
+        echo "    /specrails:team-review — Multi-perspective code review with AI reviewers"
+        echo "    /specrails:team-debug  — Collaborative debugging with competing hypotheses"
         echo ""
         echo "  These require Claude Code Agent Teams (experimental feature)."
         read -p "  Install Agent Teams commands? (y/n, default: n): " INSTALL_AGENT_TEAMS || INSTALL_AGENT_TEAMS="n"
@@ -623,7 +623,7 @@ echo -e "${BOLD}${GREEN}Installation summary:${NC}"
 echo ""
 echo "  Provider: $CLI_PROVIDER → output to $SPECRAILS_DIR/"
 if [[ "$AGENT_TEAMS" == "true" ]]; then
-    echo "  Agent Teams: installed (/sr:team-review, /sr:team-debug)"
+    echo "  Agent Teams: installed (/specrails:team-review, /specrails:team-debug)"
     echo "  Feature flag: CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 (required)"
 fi
 echo ""

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "specrails-core",
-  "version": "3.3.0",
+  "version": "3.4.0",
   "description": "AI agent workflow system for Claude Code — installs 12 specialized agents, orchestration commands, and persona-driven product discovery into any repository",
   "bin": {
     "specrails-core": "bin/specrails-core.js"

package/templates/agents/sr-merge-resolver.md

@@ -1,6 +1,6 @@
 ---
 name: sr-merge-resolver
-description: "Use this agent when the /sr:implement pipeline produces conflict markers in Phase 4a (worktree merge), or when the user runs /sr:merge-resolve directly. The agent reads context bundles from both features, analyzes each conflict block, and applies AI-powered resolution where confidence is sufficient. Falls back to clean marker format for low-confidence conflicts.\n\nExamples:\n\n- Example 1:\n  user: (orchestrator) Phase 4a found 3 conflicted files. Resolve them.\n  assistant: \"Launching sr-merge-resolver with conflicted files and context bundles from both features.\"\n\n- Example 2:\n  user: /sr:merge-resolve --files src/config.ts\n  assistant: \"Launching the merge resolver agent to analyze and resolve conflicts in src/config.ts.\""
+description: "Use this agent when the /specrails:implement pipeline produces conflict markers in Phase 4a (worktree merge), or when the user runs /specrails:merge-resolve directly. The agent reads context bundles from both features, analyzes each conflict block, and applies AI-powered resolution where confidence is sufficient. Falls back to clean marker format for low-confidence conflicts.\n\nExamples:\n\n- Example 1:\n  user: (orchestrator) Phase 4a found 3 conflicted files. Resolve them.\n  assistant: \"Launching sr-merge-resolver with conflicted files and context bundles from both features.\"\n\n- Example 2:\n  user: /specrails:merge-resolve --files src/config.ts\n  assistant: \"Launching the merge resolver agent to analyze and resolve conflicts in src/config.ts.\""
 model: sonnet
 color: yellow
 memory: project