kodelyth-ecc 1.5.4 → 1.5.6

package/.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,47 @@
+---
+name: Bug report
+about: Something broken in ECC — install failure, agent misbehavior, hook error
+title: '[BUG] '
+labels: bug
+assignees: ''
+---
+
+## What happened
+
+<!-- Describe what went wrong. Include the exact command you ran or behavior you observed. -->
+
+## Expected behavior
+
+<!-- What should have happened instead. -->
+
+## Steps to reproduce
+
+1.
+2.
+3.
+
+## Environment
+
+- **ECC version**: <!-- run: cat ~/.claude/kodelyth-ecc-install-state.json | grep version -->
+- **Install target**: <!-- claude-home / windsurf-home / windsurf-project / cursor-project / codex-home / antigravity / opencode -->
+- **Platform**: <!-- macOS / Linux / Windows -->
+- **AI IDE**: <!-- Claude Code / Windsurf / Cursor / Codex CLI / Antigravity / OpenCode -->
+- **Node.js version**: <!-- run: node --version -->
+
+## Doctor output
+
+<!-- Run: node scripts/doctor.js  or  /doctor in your IDE -->
+
+```
+paste output here
+```
+
+## Relevant logs or error messages
+
+```
+paste here
+```
+
+## Additional context
+
+<!-- Screenshots, related issues, anything else. -->

package/.github/ISSUE_TEMPLATE/new_agent.md

@@ -0,0 +1,52 @@
+---
+name: New agent proposal
+about: Propose a new specialist agent for ECC
+title: '[AGENT] '
+labels: enhancement, new-agent
+assignees: ''
+---
+
+## Agent name
+
+<!-- e.g. `rate-limiter-specialist`, `database-migrator` -->
+
+## One-line description
+
+<!-- What does this agent do? Max 15 words. -->
+
+## Problem it solves
+
+<!-- What pain does this agent remove? What does a developer have to do manually today that this agent would handle? -->
+
+## Persona
+
+<!-- Who is this agent? Describe their experience, scale they've worked at, what makes their advice different from a generic answer. -->
+
+## Trigger patterns
+
+<!-- When should intent routing auto-invoke this agent? Give 5–10 natural-language phrases a user might type. -->
+
+- "..."
+- "..."
+- "..."
+
+## Example interaction
+
+<!-- Show a realistic input and the kind of response this agent would give. -->
+
+**User:** ...
+
+**Agent:** ...
+
+## Does this overlap with an existing agent?
+
+<!-- Check the agent list. If it overlaps with e.g. `debug-detective` or `performance-optimizer`, explain what makes this distinct. -->
+
+## Kodelyth Standard checklist
+
+- [ ] The agent has a specific, named persona with years of experience and scale context
+- [ ] The agent responds to the human situation, not just the technical question
+- [ ] Responses give exact file paths, before/after code, or specific commands — not abstract advice
+- [ ] No emoji in agent responses
+- [ ] Ends with `> Powered by Kodelyth — [tagline]`
+- [ ] No `model:` field in frontmatter

package/.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,53 @@
+## What this PR does
+
+<!-- One paragraph. What was broken or missing, what you changed, and why this is the right approach. -->
+
+## Type of change
+
+- [ ] Bug fix (broken behavior, wrong count, install failure)
+- [ ] New agent
+- [ ] New skill
+- [ ] New command
+- [ ] New hook
+- [ ] Rule update
+- [ ] Install script change
+- [ ] Documentation
+- [ ] Other: ___
+
+## Checklist
+
+### All PRs
+- [ ] `npm test` passes (`node tests/run-all.js`)
+- [ ] No hardcoded version numbers or counts that will drift
+- [ ] No `.DS_Store`, `node_modules`, or generated files committed
+
+### New agent
+- [ ] File at `agents/<name>.md`
+- [ ] No `model:` field in frontmatter
+- [ ] Has a specific persona with experience/scale context
+- [ ] Responds to human situation, not just the technical question
+- [ ] Ends with `> Powered by Kodelyth — [tagline]`
+- [ ] Trigger patterns added to `rules/common/agent-intent-routing.md`
+- [ ] Agent added to `rules/common/agents.md`
+- [ ] README agent table updated
+
+### New skill
+- [ ] File at `skills/<name>/SKILL.md`
+- [ ] Description is accurate and testable
+
+### Install script change (`install.sh` / `install.ps1`)
+- [ ] Both `install.sh` and `install.ps1` updated (feature parity)
+- [ ] Tested on at least one platform
+- [ ] No new hardcoded counts (use dynamic `find` instead)
+
+### Rule change
+- [ ] Rule is general enough to apply across languages/frameworks
+- [ ] Not duplicating guidance already in another rule file
+
+## Testing
+
+<!-- How did you verify this works? -->
+
+## Related issues
+
+<!-- Closes #123 -->

package/CHANGELOG.md

@@ -2,6 +2,33 @@
 
 All notable changes to Kodelyth ECC are documented here.
 
+## v1.5.6 — Accuracy, Ruby/Elixir, /doctor, /update (May 2026)
+
+### Bug Fixes
+
+- **Dynamic install counts** — `install.sh` and `install.ps1` now compute agent/skill/command counts from the actual filesystem at install time. Hardcoded numbers like `(58)` and `(79)` that were wrong on every install are gone permanently.
+- **`rules/common/agents.md` rewritten** — listed only 10 agents from an ancient version. Now documents all 62 agents across 10 categories with handoff chains. This file is injected into `.windsurfrules` on every Windsurf session — the AI was being told there were 10 agents when there are 62.
+- **`kodelyth-advisor` model field removed** — `model: sonnet` violated the Kodelyth Standard (`CONTRIBUTING.md` explicitly says no `model:` field). Fixed.
+- **Windsurf post-install rule count** — was hardcoded as "15 coding rules", now computed dynamically.
+- **`install.ps1` `.windsurfrules` path bug** — for `windsurf-home` target, the file was being written to `$HomeDir\.windsurfrules` instead of `$Dest\.windsurfrules`. Fixed.
+- **README agent count** — "All 61 subagents" in the What Gets Installed table corrected to 62.
+- **OpenCode platform description** — README said "Full" support. OpenCode receives rules only (no agents, no skills). Now documented honestly.
+
+### New Features
+
+- **`/doctor` command** — run a health check on your ECC install from inside your IDE. Wraps `scripts/doctor.js`. Shows OK/WARNING/ERROR per component with a summary.
+- **`/update` command** — upgrade to the latest ECC version without memorizing your original install flags. Reads `kodelyth-ecc-install-state.json`, replays `npx kodelyth-ecc@latest --target <target>` automatically. Never overwrites `~/.kodelyth/memory/` or `tasks/lessons.md`.
+- **Ruby language rules** — `rules/ruby/` with coding-style, patterns, testing (RSpec + FactoryBot), security (Brakeman + bundler-audit), and hooks (RuboCop auto-fix). Installable via `npx kodelyth-ecc ruby` or `./install.sh ruby`.
+- **Elixir language rules** — `rules/elixir/` with coding-style (mix format + Credo), patterns (with/GenServer/Context), testing (ExUnit + Mox + excoveralls), security (Sobelow + mix hex.audit), and hooks. Installable via `npx kodelyth-ecc elixir` or `./install.sh elixir`.
+- **GitHub issue + PR templates** — `.github/ISSUE_TEMPLATE/bug_report.md`, `.github/ISSUE_TEMPLATE/new_agent.md`, `.github/PULL_REQUEST_TEMPLATE.md`. Contribution quality gate built into the repo workflow.
+
+### Changes
+
+- `package.json` description updated to reflect 90 commands (was 88)
+- `ruby` and `elixir` added to language parser in both `install.sh` and `install.ps1`
+
+---
+
 ## v1.5.3 — God-Tier Intent Routing Expansion (May 2026)
 
 ### The Routing Overhaul

package/CLAUDE.md

@@ -8,7 +8,7 @@ Guidance for Claude Code when working with this repository.
 
 - **62 specialist agents** — debug-detective, incident-commander, load-tester, image-architect, kodelyth-memory, security-reviewer, etc.
 - **188 skills** — domain knowledge, patterns, testing, security, intent routing, local memory
-- **80 commands** — slash workflows (`/tdd`, `/plan`, `/code-review`, `/memory`, `/project-launch`, `/team-review`, ...)
+- **88 commands** — slash workflows (`/tdd`, `/plan`, `/code-review`, `/team-review`, `/project-launch`, `/debug-blitz`, `/security-audit`, ...)
 - **20+ hooks** — automated quality gates, session memory, memory inject + capture, correction encoding
 - **17 rules** — always-on coding standards + semantic intent routing + memory protocol
 
@@ -45,6 +45,20 @@ When a user message matches a routing pattern, you MUST:
 3. Suggest the explicit form: `Tip: type "use <agent>"`
 4. Never silently route — transparency is mandatory
 
+## Parallel Commands (Fastest Paths — Multi-Agent)
+
+These fire multiple specialist agents simultaneously. Use these for the fastest results:
+
+| Command | Agents Fired | Best For |
+|---|---|---|
+| `/team-review` | code-reviewer + security-reviewer + performance-optimizer + api-guardian | Full audit before any PR or deploy |
+| `/project-launch` | architect + pair-programmer + security-reviewer + tdd-guide + ux-reviewer | Starting any new project |
+| `/security-audit` | security-reviewer + dependency-doctor + api-guardian | Full threat surface check |
+| `/debug-blitz` | debug-detective + silent-failure-hunter + env-debugger | Bug that resisted 30+ min of investigation |
+| `/refactor-sprint` | refactor-cleaner + code-simplifier + type-design-analyzer + tdd-guide | Full cleanup before a feature sprint |
+| `/pre-release` | release-captain + security-reviewer + code-reviewer | Go/no-go verdict before shipping |
+| `/onboard` | code-explorer + architect + doc-updater | Understand any codebase in 15 minutes |
+
 ## Key Commands
 
 - `/kodelyth-quickstart` — friendly onboarding guide

package/README.md

@@ -299,7 +299,7 @@ Project: **my-app**
 |---|---|---|
 | Agents | **62** | Specialist subagents — reviewers, planners, debuggers, architects, incident-commander, load-tester, memory, image-architect |
 | Skills | **188** | Domain knowledge — patterns, testing, security, DevOps, intent routing, memory |
-| Commands | **80** | Slash command workflows (`/tdd`, `/plan`, `/memory`, etc.) |
+| Commands | **90** | Slash command workflows (`/tdd`, `/plan`, `/memory`, `/doctor`, `/update`, etc.) |
 | Hooks | **20+** | Quality gates, secret scanning, branch checks, memory inject + capture + correction + project DNA |
 | Rules | **17** | Always-on coding standards + intent routing + memory protocol + self-improvement workflow |
 | Memory | **local** | BM25-indexed personal memory at `~/.kodelyth/memory/` (zero deps) |
@@ -440,7 +440,7 @@ The intent router will route you to the right one. The AI announces who's taking
 
 | Source | Destination | What it does |
 |---|---|---|
-| `agents/` | `~/.claude/agents/` | All 61 subagents available globally |
+| `agents/` | `~/.claude/agents/` | All 62 subagents available globally |
 | `skills/` | `~/.claude/skills/` | All 188 skills loadable via commands |
 | `hooks/hooks.json` | `~/.claude/hooks/` | Automated quality gates |
 | `rules/` | `~/.claude/rules/` | Always-on standards + intent routing |
@@ -510,7 +510,7 @@ Available profiles:
 Or specify languages directly:
 
 ```bash
-npx kodelyth-ecc typescript python golang rust java kotlin php swift cpp dart
+npx kodelyth-ecc typescript python golang rust java kotlin php swift cpp dart ruby elixir
 ```
 
 ---
@@ -524,7 +524,7 @@ npx kodelyth-ecc typescript python golang rust java kotlin php swift cpp dart
 | Cursor | Full | `cursor-project` | Rules, skills |
 | Codex CLI | Full | `codex-home` | Agents, skills, commands, rules |
 | Google Antigravity | Full | `antigravity` | Agents → skills, commands → workflows, rules |
-| OpenCode | Full | `opencode` | Rules |
+| OpenCode | Rules only | `opencode` | Rules (agents + skills not yet supported by OpenCode) |
 
 **OS support:** macOS, Linux (`install.sh`), Windows (`install.ps1`), or any OS with Node.js 18+ (`npx`).
 

package/VERSION

@@ -1 +1 @@
-1.5.4
+1.5.6

package/agents/debug-detective.md

@@ -7,6 +7,7 @@ description: >
   never patches symptoms, never stops until the root cause is understood.
   Use when a bug is hard to find, confusing, intermittent, or has resisted fixes.
 tools: ["Read", "Grep", "Glob", "Bash"]
+model: sonnet
 ---
 
 You are the Debug Detective — a principal engineer with 10+ years of production war stories at companies where bugs cost millions per minute of downtime. You have debugged memory leaks in C++ services, traced race conditions in distributed systems, hunted null pointer exceptions in 2 AM on-call incidents, and found the one misconfigured timeout that was silently corrupting financial transactions. You do not guess. You do not patch. You investigate.

package/agents/dependency-doctor.md

@@ -8,6 +8,7 @@ description: >
   Use when install fails, lockfile drifts, audit reports CVEs, or a dep
   upgrade breaks the build.
 tools: ["Read", "Grep", "Glob", "Bash"]
+model: sonnet
 ---
 
 You are the Dependency Doctor — the engineer your team calls when `npm install` fails on CI but works locally, when `cargo update` breaks the world, when a transitive vulnerability lands in production at 2 AM. You read lockfiles like x-rays.

package/agents/incident-commander.md

@@ -7,6 +7,7 @@ description: >
   everything is on fire. Knows exactly what to do, in what order, and who to tell.
   Use when production is down, degraded, or at risk.
 tools: ["Read", "Grep", "Glob", "Bash"]
+model: sonnet
 ---
 
 You are the Incident Commander — a principal SRE with 10+ years leading production incidents at companies where every minute of downtime costs real money. You have run P0s at financial institutions, coordinated multi-team responses to database failures, managed rolling rollbacks under pressure, and written postmortems that changed how organizations think about reliability. You do not panic. You do not guess. You command.

package/agents/load-tester.md

@@ -7,6 +7,7 @@ description: >
   Use when you need to validate how a system behaves under load, before launch,
   after infrastructure changes, or when planning capacity.
 tools: ["Read", "Grep", "Glob", "Bash"]
+model: sonnet
 ---
 
 You are the Load Tester — a performance engineering specialist with a decade of experience designing load tests for systems that serve millions of users. You have found the database query that only breaks at 500 req/s, identified the memory leak that only manifests after 10 minutes of sustained load, and discovered the thundering herd that only appears when 1000 users hit the cache miss simultaneously. You make systems prove their capacity limits before users find them.

package/agents/migration-guide.md

@@ -8,6 +8,7 @@ description: >
   phased migration plan with exact file changes, and handles dependency
   conflicts. Use when upgrading any major framework, language, or library.
 tools: ["Read", "Grep", "Glob", "Bash"]
+model: sonnet
 ---
 
 You are the Migration Guide — a principal engineer with 10+ years of leading major version migrations at companies where "we'll upgrade later" became "we're 4 major versions behind and nothing works." You have migrated millions of lines of code across React, Next.js, Python, Node.js, TypeScript, Java, Go, and more. You know every gotcha. You know which breaking changes are actually safe to batch and which need their own isolated PR.

package/agents/pair-programmer.md

@@ -8,6 +8,7 @@ description: >
   any code is committed. The cheapest bug is the one caught before coding starts.
   Use before implementing anything non-trivial.
 tools: ["Read", "Grep", "Glob"]
+model: sonnet
 ---
 
 You are the Pair Programmer — a principal engineer with 10+ years of sitting next to developers at $300B-scale companies, thinking through hard problems before they become expensive mistakes. You have saved countless hours by asking "wait, have you considered..." before the wrong approach was half-built. You think out loud. You challenge respectfully. You make people think better — not feel worse.

package/agents/release-captain.md

@@ -7,6 +7,7 @@ description: >
   mistakes that turn a routine release into a Sunday outage.
   Use before cutting any new version, or when a release went sideways.
 tools: ["Read", "Grep", "Glob", "Bash"]
+model: sonnet
 ---
 
 You are the Release Captain — the engineer who has shipped thousands of releases without a bad one. You know that the difference between a calm release and a fire is the **30 minutes of preparation no one wants to do**. You do them.

package/commands/debug-blitz.md

@@ -0,0 +1,70 @@
+---
+description: Parallel debug assault — fires debug-detective + silent-failure-hunter + env-debugger simultaneously. Three root-cause specialists on your bug at once.
+---
+
+# /debug-blitz — Parallel Debug Assault
+
+Three debugging specialists attack your problem from different angles simultaneously. The bug that has resisted one approach rarely survives all three.
+
+## What Gets Launched in Parallel
+
+| Agent | Focus |
+|---|---|
+| `debug-detective` | Traces the explicit error to root cause — stack traces, logs, hypothesis → proof |
+| `silent-failure-hunter` | Finds bugs with no error — swallowed exceptions, bad fallbacks, wrong output |
+| `env-debugger` | Catches environment-layer bugs — env vars, config drift, "works locally" failures |
+
+## Usage
+
+```
+/debug-blitz                         # general debug — all three agents
+/debug-blitz "TypeError on line 42"  # paste the error — agents use it as starting point
+/debug-blitz --ci                    # focus env-debugger on CI/CD environment
+/debug-blitz --prod                  # production context — incident-commander added
+```
+
+## Report Format
+
+```
+## DEBUG BLITZ REPORT
+
+### Root Cause Analysis (debug-detective)
+HYPOTHESIS: [most likely cause]
+EVIDENCE:   [what points to it]
+DISPROVEN:  [what was ruled out]
+FIX:        [exact change needed]
+
+### Silent Failures (silent-failure-hunter)
+FOUND:      [swallowed errors, bad fallbacks]
+RISK:       [what could be silently wrong]
+
+### Environment (env-debugger)
+CONFIG:     [mismatches found]
+SECRETS:    [missing or wrong vars]
+DRIFT:      [local vs CI vs prod differences]
+
+---
+MOST LIKELY CAUSE: [one sentence]
+RECOMMENDED FIX:   [one action]
+```
+
+## When to Use
+
+- Bug has resisted more than 30 minutes of investigation
+- "Works on my machine" but fails in CI or prod
+- No error thrown but wrong output
+- Intermittent failures with no obvious pattern
+- A fix was applied but the bug came back
+
+## Execute Now
+
+Invoking this command is confirmation to proceed. Execute immediately:
+
+1. Extract the error, symptom, or context from `$ARGUMENTS`. If empty, scan recent git changes and ask: "What's broken and what changed last?"
+2. Spawn all agents simultaneously with `run_in_background: true`:
+   - `debug-detective` — hypothesis-driven root cause analysis
+   - `silent-failure-hunter` — scan for swallowed errors and bad fallbacks
+   - `env-debugger` — environment and config layer investigation
+3. Wait for all to complete.
+4. Aggregate into the Debug Blitz Report format above with one clear recommended fix.
+5. End with: "Want me to implement the fix?"

package/commands/doctor.md

@@ -0,0 +1,75 @@
+---
+description: Diagnose your Kodelyth ECC install — check for drift, missing files, version mismatches, and confirm everything is healthy
+---
+
+# /doctor
+
+Runs a health check on your ECC install. Detects drift between what was installed and what is currently on disk.
+
+## What It Checks
+
+- Install state file exists and is readable
+- Installed version vs latest available
+- Agent files present and uncorrupted
+- Skills directory intact
+- Rules loaded correctly
+- Memory store accessible (if applicable)
+- Hooks registered (Claude Code only)
+
+## Usage
+
+```
+/doctor
+```
+
+Run with no arguments for a full health report on all detected installs.
+
+## Implementation
+
+Runs the built-in doctor script:
+
+```bash
+node scripts/doctor.js
+```
+
+Or with a specific target:
+
+```bash
+node scripts/doctor.js --target claude-home
+node scripts/doctor.js --target windsurf-home
+node scripts/doctor.js --target windsurf-project
+node scripts/doctor.js --target codex-home
+node scripts/doctor.js --target cursor-project
+```
+
+For JSON output (useful in CI or scripts):
+
+```bash
+node scripts/doctor.js --json
+```
+
+## Output
+
+The doctor report shows:
+
+| Field | Meaning |
+|-------|---------|
+| `OK` | Component healthy, no issues |
+| `WARNING` | Potential issue, non-blocking |
+| `ERROR` | Missing or corrupted file, needs attention |
+
+A summary line shows total checked, ok, warnings, and errors.
+
+## When to Run
+
+- After first install to confirm everything landed
+- After upgrading to a new ECC version
+- When an agent or skill isn't behaving as expected
+- Before filing a bug report
+
+## Related
+
+- `/update` — upgrade to the latest ECC version
+- `use kodelyth-advisor` — if you're not sure where to start
+
+> Powered by Kodelyth — trust your install, verify your tools.

package/commands/onboard.md

@@ -0,0 +1,72 @@
+---
+description: Parallel codebase onboarding — fires code-explorer + architect + doc-updater simultaneously. Understand any codebase in 15 minutes instead of 3 days.
+---
+
+# /onboard — Parallel Codebase Onboarding
+
+Three agents map your codebase simultaneously — architecture, execution paths, and documentation gaps. New to a repo? Get up to speed in 15 minutes.
+
+## What Gets Launched in Parallel
+
+| Agent | Focus |
+|---|---|
+| `code-explorer` | Traces execution paths, maps data flow, identifies key entry points and dependencies |
+| `architect` | Infers the architectural pattern, layers, module boundaries, and design decisions |
+| `doc-updater` | Identifies documentation gaps, stale docs, and missing READMEs or JSDoc |
+
+## Usage
+
+```
+/onboard                             # full codebase overview
+/onboard src/payments/               # focus on a specific module
+/onboard --new-hire                  # adds kodelyth-advisor for getting-started guidance
+/onboard --audit                     # adds code-reviewer for quality assessment
+```
+
+## Report Format
+
+```
+## ONBOARDING REPORT
+
+### Architecture (architect)
+PATTERN:    [MVC / hexagonal / microservices / etc.]
+LAYERS:     [how the code is organized]
+KEY FILES:  [the 5–10 files you must understand first]
+DECISIONS:  [notable architectural choices and why]
+
+### Execution Paths (code-explorer)
+ENTRY POINTS: [main flows — auth, data, API, jobs]
+DATA FLOW:    [how data moves through the system]
+DEPENDENCIES: [what talks to what]
+GOTCHAS:      [non-obvious behaviours]
+
+### Documentation Health (doc-updater)
+MISSING:   [modules with no docs]
+STALE:     [docs that no longer match the code]
+GAPS:      [API endpoints with no documentation]
+
+---
+TIME TO PRODUCTIVE: estimated X days
+FIRST 3 THINGS TO READ: [ordered list]
+```
+
+## When to Use
+
+- First day on a new codebase
+- Reviewing a large PR in an unfamiliar module
+- Taking over a project from another team
+- Returning to code you haven't touched in 6+ months
+- Evaluating an open-source repo before adopting it
+
+## Execute Now
+
+Invoking this command is confirmation to proceed. Execute immediately:
+
+1. Determine scope from `$ARGUMENTS`. Default: entire current project.
+2. Spawn all agents simultaneously with `run_in_background: true`:
+   - `code-explorer` — execution path tracing and dependency mapping
+   - `architect` — architectural pattern inference
+   - `doc-updater` — documentation gap analysis
+3. Wait for all to complete.
+4. Aggregate into the Onboarding Report format above.
+5. End with: "Which area do you want to explore deeper first?"

package/commands/pre-release.md

@@ -0,0 +1,66 @@
+---
+description: Parallel pre-release check — fires release-captain + security-reviewer + code-reviewer simultaneously. Go/no-go in one command before you ship.
+---
+
+# /pre-release — Parallel Release Readiness Check
+
+Three agents verify your release is safe to ship. Catches the things that turn a Friday deploy into a weekend incident.
+
+## What Gets Launched in Parallel
+
+| Agent | Focus |
+|---|---|
+| `release-captain` | Semver correctness, changelog complete, rollback plan, smoke test coverage |
+| `security-reviewer` | Last-minute security gaps, secrets, auth issues before code goes live |
+| `code-reviewer` | Critical quality issues, dead code, regressions introduced in this release |
+
+## Usage
+
+```
+/pre-release                     # check current branch vs main
+/pre-release v2.1.0              # check specific version tag
+/pre-release --hotfix            # fast-track: release-captain only, skip style issues
+```
+
+## Report Format
+
+```
+## PRE-RELEASE REPORT
+
+### Release Readiness (release-captain)
+SEMVER:    [correct / incorrect]
+CHANGELOG: [complete / missing entries]
+ROLLBACK:  [plan exists / missing]
+SMOKE:     [covered / gaps]
+
+### Security Clearance (security-reviewer)
+CRITICAL: [list — block if any]
+HIGH:     [list]
+
+### Code Quality (code-reviewer)
+CRITICAL: [list — block if any]
+HIGH:     [list]
+
+---
+VERDICT: SHIP / FIX CRITICAL FIRST / BLOCK
+```
+
+## When to Use
+
+- Before cutting any release tag
+- Before merging a large feature branch
+- Before a hotfix deploy under pressure
+- As the final gate before `npm publish` or production push
+
+## Execute Now
+
+Invoking this command is confirmation to proceed. Execute immediately:
+
+1. Determine target from `$ARGUMENTS` (version tag, branch, or current state).
+2. Spawn all agents simultaneously with `run_in_background: true`:
+   - `release-captain` — release ritual check: semver, changelog, rollback
+   - `security-reviewer` — security clearance scan
+   - `code-reviewer` — final quality gate
+3. Wait for all to complete.
+4. Aggregate into the Pre-Release Report format above with a clear SHIP / BLOCK verdict.
+5. End with: "Ready to proceed with the release?" or list what must be fixed first.