godpowers 1.6.0 → 1.6.2

package/CHANGELOG.md

@@ -5,6 +5,66 @@ All notable changes to Godpowers will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.6.2] - 2026-05-16
+
+Codex agent metadata compatibility patch. Keeps the public command surface
+stable while making installed Godpowers specialist agents spawnable in Codex
+sessions that require per-agent TOML metadata.
+
+### Added
+- Added Codex agent metadata generation during `--codex` installs. Every
+  `agents/god-*.md` file now gets a matching `god-*.toml` file with name,
+  description, sandbox mode, and developer instructions.
+- Added install smoke coverage that verifies all 39 Godpowers agents receive
+  Codex metadata.
+- Added `--all` installer coverage for all 15 supported runtimes, including
+  Claude Code, Codex, and Pi.
+
+### Changed
+- Codex runtime support now declares its agent metadata behavior explicitly in
+  the installer instead of relying on an inline special case.
+- Non-Codex runtimes keep their existing markdown agent install format.
+
+### Guardrails
+- This patch does not add slash commands, agents, workflows, recipes, schemas,
+  or public artifact formats.
+- The Codex metadata is generated from the existing agent markdown specs so the
+  Godpowers agent source of truth stays in `agents/*.md`.
+
+## [1.6.1] - 2026-05-15
+
+Release hardening patch. Keeps the 1.6 domain precision surface stable while
+making package publication, release checks, and CI verification harder to drift.
+
+### Added
+- Added `npm run release:check`, which runs the full test suite, audit checks,
+  and package contents verification.
+- Added `scripts/check-package-contents.js` to assert that the npm payload
+  includes load-bearing runtime files and excludes local-only development files.
+- Added `docs/RELEASE-CHECKLIST.md` for versioning, verification, package
+  surface, tag, npm provenance, and post-release cleanup.
+- Added an explicit plan-mode E2E smoke test for the `/god-mode` full-arc
+  workflow against the `todo-app` fixture.
+
+### Changed
+- CI now uses `npm ci`, runs audit checks, runs the E2E smoke path explicitly,
+  and keeps package checks aligned with local npm scripts.
+- Test documentation now describes the current runtime and E2E smoke coverage
+  instead of stale scaffold-only plans.
+- Runtime and reference README files now describe the implemented modules and
+  reference files instead of placeholder future work.
+- Package tarballs are ignored by git, and package contents checks reject
+  generated tarballs.
+- The release script now pushes the git tag and relies on the tag-triggered
+  GitHub Actions npm publish workflow for provenance.
+
+### Guardrails
+- This patch does not add new slash commands, agents, workflows, recipes, or
+  schemas.
+- The 1.6 domain glossary behavior remains unchanged.
+- Future npm publishes should use the tag-triggered GitHub workflow unless a
+  documented emergency requires a manual fallback.
+
 ## [1.6.0] - 2026-05-15
 
 Domain precision release. Adds a Godpowers-native vocabulary layer so fuzzy or
@@ -32,6 +92,8 @@ roadmap, stack, docs, or lint artifacts.
   reverse, surprising without context, and based on a real tradeoff.
 - Public release metadata, package version, and README badge now point to
   1.6.0.
+- Release history now has a `v1.6.0` git tag matching the published npm
+  package.
 
 ### Guardrails
 - The domain glossary is preparation context only. It does not replace PRD,

package/README.md

@@ -2,7 +2,7 @@
 
 [![CI](https://github.com/aihxp/godpowers/actions/workflows/ci.yml/badge.svg)](https://github.com/aihxp/godpowers/actions/workflows/ci.yml)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
-[![Version](https://img.shields.io/badge/version-1.6.0-blue)](CHANGELOG.md)
+[![Version](https://img.shields.io/badge/version-1.6.2-blue)](CHANGELOG.md)
 [![npm](https://img.shields.io/npm/v/godpowers.svg)](https://www.npmjs.com/package/godpowers)
 
 **Ship fast. Ship right. Ship everything. Ship accountably.**
@@ -12,9 +12,10 @@ idea to hardened production. It runs as **slash commands inside your AI coding
 tool** (Claude Code, Codex, Cursor, etc.) that orchestrate **specialist agents**
 in fresh contexts to do the work.
 
-Version 1.6.0 adds domain precision: `/god-discuss` can resolve overloaded
-project language into `.godpowers/domain/GLOSSARY.md`, and downstream planning,
-architecture, stack, roadmap, docs, and lint flows use that vocabulary.
+Version 1.6.2 hardens Codex agent integration around the 1.6 domain precision
+layer: Codex installs now include per-agent TOML metadata for all 39
+Godpowers specialist agents, while release checks cover every supported
+runtime surface.
 
 It fuses four disciplines into one unified workflow:
 
@@ -46,6 +47,7 @@ T3 Code is transparently supported through the underlying agent.
 The installer copies:
 - Slash command skills to `<runtime>/skills/`
 - Specialist agents to `<runtime>/agents/`
+- Codex agent metadata to `<runtime>/agents/*.toml`
 - SessionStart hook (Claude Code only) to `<runtime>/hooks/`
 
 ## Usage

package/RELEASE.md

@@ -1,10 +1,11 @@
-# Godpowers 1.6.0 Release
+# Godpowers 1.6.2 Release
 
-Date: 2026-05-15
+Date: 2026-05-16
 
-Godpowers 1.6.0 adds domain precision. The goal of this release is to keep
-project language sharp before it becomes product scope, system shape, delivery
-sequence, stack rationale, documentation, or linted artifact text.
+Godpowers 1.6.2 hardens Codex agent integration around the stable 1.6 domain
+precision release. The goal of this patch is to make every installed
+Godpowers specialist agent spawnable in Codex sessions that require per-agent
+metadata, without changing the public command surface.
 
 ## What is stable
 
@@ -13,44 +14,46 @@ sequence, stack rationale, documentation, or linted artifact text.
 - 13 executable workflows
 - 36 intent recipes
 - 15-runtime installer
+- Codex installs with 39 generated `god-*.toml` agent metadata files
 - Native Pillars project context through `AGENTS.md` and `agents/*.md`
 - `.godpowers/` workflow state and artifact layout
 - Core schemas: intent, state, events, workflow, routing, recipes, extension
   manifests
 - Extension pack compatibility range for the 1.x line
+- Domain precision through `.godpowers/domain/GLOSSARY.md` and DG-01 through
+  DG-05 checks
 
 ## What is new
 
-- `/god-discuss` now performs domain grilling during next-phase scoping.
-- `.godpowers/domain/GLOSSARY.md` records canonical terms, avoided aliases,
-  relationships, example dialogue, source notes, and flagged ambiguities.
-- `templates/DOMAIN-GLOSSARY.md` provides the native glossary shape.
-- `god-explorer` inspects code or docs before asking the user when repo
-  evidence can answer a domain question.
-- PM, architect, roadmapper, stack selector, and docs writer agents now read
-  `.godpowers/domain/GLOSSARY.md` when present.
-- `/god-lint` now recognizes domain glossary artifacts and reports DG-01
-  through DG-05 findings.
-- Architecture guidance now creates ADRs only when a decision is hard to
-  reverse, surprising without context, and based on a real tradeoff.
-
-## What 1.6 means
-
-Godpowers now has a native vocabulary layer that supports planning without
-creating a competing source of truth. The domain glossary is preparation
-context. PRD, ARCH, ROADMAP, STACK, docs, and Pillars files still carry the
-durable decisions for their own domains.
-
-The glossary helps agents converge on exact project language before they write
-load-bearing artifacts. It is especially useful for brownfield and bluefield
-projects where existing docs, code names, org vocabulary, and user intent can
-use the same word for different things.
+- Codex runtime support now declares an `agentMetadata: "toml"` capability in
+  the installer.
+- Codex installs generate a matching TOML metadata file for every
+  `agents/god-*.md` source file.
+- Codex metadata includes agent name, description, workspace-write sandbox
+  mode, and developer instructions derived from the markdown agent spec.
+- Install smoke tests now verify all 39 Codex metadata files, plus
+  runtime-specific install surfaces for all 15 supported runtimes.
+- Claude Code, Pi, and the other non-Codex runtimes keep their existing
+  markdown agent install behavior.
+
+## What 1.6.2 means
+
+Godpowers 1.6.2 does not expand the public command surface. It tightens the
+runtime compatibility path so the installed Codex agent registry can see the
+same Godpowers agents already shipped in `agents/*.md`.
+
+The domain glossary remains preparation context. PRD, ARCH, ROADMAP, STACK,
+docs, and Pillars files still carry durable decisions for their own domains.
 
 ## Stability policy
 
 During the 1.x stability window, do not add broad new command families, change
 schema formats, or rename public artifacts without evidence from real use.
 
+The `v1.6.2` git tag points to the release commit that matches the npm
+`godpowers@1.6.2` package. Public publishes should prefer the tag-triggered
+GitHub workflow so npm provenance, git history, and release notes stay aligned.
+
 Allowed changes:
 
 - Critical bug fixes
@@ -69,6 +72,5 @@ Deferred changes:
 
 ## Adoption ask
 
-Use `/god-discuss` before a PRD, feature, refactor, or migration where terms
-feel fuzzy. Report where the glossary catches ambiguity early, where it adds
-noise, and which domain checks should become stricter.
+Run `npm run release:check` before publishing changes. Report any release path
+step that still depends on memory, manual inspection, or local machine state.

package/bin/install.js

@@ -36,6 +36,7 @@ const RUNTIMES = {
     configDir: path.join(os.homedir(), '.codex'),
     skillsDir: 'skills',
     configFile: 'config.toml',
+    agentMetadata: 'toml',
   },
   cursor: {
     name: 'Cursor',
@@ -182,6 +183,84 @@ function installSkillFile(srcFile, skillsDest, runtimeKey, targetName = null) {
   fs.copyFileSync(srcFile, path.join(skillsDest, `${baseName}.md`));
 }
 
+function parseAgentFrontmatter(content) {
+  const fallback = { name: null, description: null };
+  if (!content.startsWith('---\n')) return fallback;
+
+  const end = content.indexOf('\n---', 4);
+  if (end === -1) return fallback;
+
+  const lines = content.slice(4, end).split('\n');
+  const parsed = { ...fallback };
+
+  for (let i = 0; i < lines.length; i++) {
+    const line = lines[i];
+    const nameMatch = line.match(/^name:\s*(.+)\s*$/);
+    if (nameMatch) {
+      parsed.name = nameMatch[1].replace(/^["']|["']$/g, '');
+      continue;
+    }
+
+    if (line === 'description: |') {
+      const desc = [];
+      i++;
+      while (i < lines.length && /^ {2}/.test(lines[i])) {
+        desc.push(lines[i].slice(2));
+        i++;
+      }
+      i--;
+      parsed.description = desc.join('\n').trim();
+      continue;
+    }
+
+    const descMatch = line.match(/^description:\s*(.+)\s*$/);
+    if (descMatch) {
+      parsed.description = descMatch[1].replace(/^["']|["']$/g, '');
+    }
+  }
+
+  return parsed;
+}
+
+function stripFrontmatter(content) {
+  if (!content.startsWith('---\n')) return content.trim();
+  const end = content.indexOf('\n---', 4);
+  if (end === -1) return content.trim();
+  return content.slice(end + 4).trim();
+}
+
+function tomlString(value) {
+  return JSON.stringify(value || '');
+}
+
+function tomlLiteral(value) {
+  return `'''\n${(value || '').replace(/'''/g, "'''\\'''")}\n'''`;
+}
+
+function writeCodexAgentToml(srcFile, agentsDest) {
+  const content = fs.readFileSync(srcFile, 'utf8');
+  const frontmatter = parseAgentFrontmatter(content);
+  const name = frontmatter.name || path.basename(srcFile, '.md');
+  const description = frontmatter.description || `Godpowers specialist agent: ${name}.`;
+  const instructions = stripFrontmatter(content);
+  const toml = [
+    `name = ${tomlString(name)}`,
+    `description = ${tomlString(description)}`,
+    'sandbox_mode = "workspace-write"',
+    `developer_instructions = ${tomlLiteral(instructions)}`,
+    ''
+  ].join('\n');
+
+  fs.writeFileSync(path.join(agentsDest, `${name}.toml`), toml);
+}
+
+function installAgentFile(srcFile, agentsDest, runtime) {
+  fs.copyFileSync(srcFile, path.join(agentsDest, path.basename(srcFile)));
+  if (runtime.agentMetadata === 'toml') {
+    writeCodexAgentToml(srcFile, agentsDest);
+  }
+}
+
 function removeSkillEntry(skillsDir, entry) {
   const entryPath = path.join(skillsDir, entry.name);
   if (entry.isDirectory()) {
@@ -289,11 +368,13 @@ function installForRuntime(runtimeKey, srcDir) {
     let count = 0;
     for (const file of fs.readdirSync(agentsSrc)) {
       if (file.endsWith('.md')) {
-        fs.copyFileSync(path.join(agentsSrc, file), path.join(agentsDest, file));
+        const srcFile = path.join(agentsSrc, file);
+        installAgentFile(srcFile, agentsDest, runtime);
         count++;
       }
     }
-    success(`Installed ${count} specialist agents to agents/`);
+    const shape = runtime.agentMetadata === 'toml' ? 'agents/ with Codex metadata' : 'agents/';
+    success(`Installed ${count} specialist agents to ${shape}`);
   }
 
   // 3. Install the master SKILL.md (always-on context)

package/lib/README.md

@@ -1,28 +1,80 @@
-# lib/ - Runtime Library (placeholder)
+# lib/ - Runtime Library
 
-This directory is reserved for v0.5+ runtime modules. v0.4 has the schemas
-defined; v0.5 implements them.
+This directory contains the JavaScript runtime modules that support Godpowers
+validation, routing, workflow execution, state management, observability, and
+package-level integrations.
 
-## Planned modules
+## Core state and intent
 
-| Module | Purpose | Target version |
-|--------|---------|----------------|
-| `state.js` | Read/write `.godpowers/state.json` with schema validation | v0.5 |
-| `events.js` | Append OpenTelemetry-shape events to events.jsonl | v0.5 |
-| `intent.js` | Read/validate `intent.yaml` (or `.godpowers/intent.yaml`) | v0.5 |
-| `workflow-runtime.js` | Parse and execute workflow YAML | v0.5 |
-| `reflog.js` | Append to `.godpowers/log` and rewind state | v0.6 |
-| `trash.js` | Recoverable deletion to `.godpowers/.trash/` | v0.6 |
-| `metrics.js` | Compute per-tier stats from events.jsonl | v0.7 |
-| `extension-loader.js` | Lazy-activate skill packs | v0.8 |
+| Module | Purpose |
+|--------|---------|
+| `state.js` | Read, initialize, validate, and write `.godpowers/state.json`. |
+| `state-lock.js` | Coordinate state writes with a lock file. |
+| `intent.js` | Read and validate `intent.yaml` from project roots or `.godpowers/`. |
+| `checkpoint.js` | Create and inspect resumable checkpoint artifacts. |
+| `budget.js` | Read and enforce configured budget controls. |
+| `cost-tracker.js` | Track token and cost estimates from event streams. |
 
-## Why placeholder
+## Events and observability
 
-In v0.4 (current), Godpowers is markdown skills + agent prose. There's no
-runtime that needs these modules; agents read/write artifacts directly.
+| Module | Purpose |
+|--------|---------|
+| `events.js` | Append structured runtime events. |
+| `event-reader.js` | Read and aggregate event streams. |
+| `otel-exporter.js` | Export Godpowers events in an OpenTelemetry-shaped format. |
+| `runtime-audit.js` | Audit runtime health and expected project state. |
+| `runtime-test.js` | Provide runtime checks used by package tests. |
 
-In v0.5+, the workflow runtime needs structured access to state. That's when
-these modules ship.
+## Routing and execution
 
-See `../ARCHITECTURE.md` for the design and `../docs/ROADMAP.md` for the
-sequencing.
+| Module | Purpose |
+|--------|---------|
+| `router.js` | Resolve user intent to skills, agents, recipes, and workflows. |
+| `recipes.js` | Load and validate routing recipes. |
+| `workflow-parser.js` | Parse workflow YAML into executable steps. |
+| `workflow-runner.js` | Execute workflow steps with validation hooks. |
+| `agent-cache.js` | Cache agent metadata for faster routing. |
+| `agent-validator.js` | Validate agent frontmatter and contracts. |
+
+## Artifact quality
+
+| Module | Purpose |
+|--------|---------|
+| `artifact-linter.js` | Check artifacts for required labels, evidence, and domain precision. |
+| `artifact-diff.js` | Compare artifact changes for review and release workflows. |
+| `have-nots-validator.js` | Check artifacts against known failure modes. |
+| `meta-linter.js` | Validate Godpowers documentation and skill metadata. |
+| `story-validator.js` | Validate story artifacts and story lifecycle state. |
+
+## Design, context, and integrations
+
+| Module | Purpose |
+|--------|---------|
+| `context-writer.js` | Produce tool-specific context files. |
+| `context-budget.js` | Keep generated context within budget. |
+| `design-detector.js` | Detect design-system conventions. |
+| `design-spec.js` | Normalize design specifications. |
+| `awesome-design.js` | Validate design guidance against awesome-design rules. |
+| `browser-bridge.js` | Connect browser verification flows. |
+| `agent-browser-driver.js` | Drive browser-backed agent checks. |
+| `skillui-bridge.js` | Bridge skill metadata into UI surfaces. |
+| `impeccable-bridge.js` | Bridge runtime checks into impeccable quality workflows. |
+| `extensions.js` | Load and validate extension packs. |
+
+## Repository and graph helpers
+
+| Module | Purpose |
+|--------|---------|
+| `code-scanner.js` | Scan source trees for routing and quality evidence. |
+| `cross-artifact-impact.js` | Detect relationships between changed artifacts. |
+| `cross-repo-linkage.js` | Track suite-level repository relationships. |
+| `drift-detector.js` | Detect context drift between artifacts and implementation. |
+| `impact.js` | Summarize expected impact of proposed changes. |
+| `linkage.js` | Connect artifacts, stories, and implementation files. |
+| `multi-repo-detector.js` | Detect multi-repository workspaces. |
+| `reverse-sync.js` | Reflect implementation changes back into artifacts. |
+| `review-required.js` | Decide when review gates should block progress. |
+| `suite-state.js` | Manage state across registered project suites. |
+
+See `../ARCHITECTURE.md` for system design and `../docs/ROADMAP.md` for planned
+runtime work.

package/package.json

@@ -1,12 +1,12 @@
 {
   "name": "godpowers",
-  "version": "1.6.0",
+  "version": "1.6.2",
   "description": "AI-powered development system: 106 slash commands and 39 specialist agents that take a project from raw idea to hardened production. Runs inside Claude Code, Codex, Cursor, Windsurf, Gemini, and 10+ other AI coding tools.",
   "bin": {
     "godpowers": "./bin/install.js"
   },
   "scripts": {
-    "test": "node scripts/validate-skills.js && node scripts/test-doc-surface-counts.js && bash scripts/smoke.sh && node scripts/test-runtime.js && node scripts/test-router.js && node scripts/test-recipes.js && node scripts/test-context-writer.js && node scripts/test-pillars.js && node scripts/test-artifact-linter.js && node scripts/test-artifact-diff.js && node scripts/test-design-foundation.js && node scripts/test-linkage.js && node scripts/test-impact.js && node scripts/test-reverse-sync.js && node scripts/test-integration.js && node scripts/test-cross-artifact.js && node scripts/test-awesome-design.js && node scripts/test-skillui-bridge.js && node scripts/test-runtime-verification.js && node scripts/test-agent-browser.js && node scripts/test-mode-d.js && node scripts/test-runtime-heuristics.js && node scripts/test-agent-validator.js && node scripts/test-story-validator.js && node scripts/test-state.js && node scripts/test-intent.js && node scripts/test-events.js && node scripts/test-golden-artifacts.js && node scripts/test-install-smoke.js && node scripts/test-checkpoint.js && node scripts/test-extensions.js && node scripts/test-event-reader.js && node scripts/test-state-lock.js && node scripts/test-cost-saver.js && node scripts/test-budget-onoff.js && node scripts/test-workflow-runner.js && node scripts/test-otel-exporter.js && node scripts/test-extensions-publish.js",
+    "test": "node scripts/validate-skills.js && node scripts/test-doc-surface-counts.js && bash scripts/smoke.sh && node scripts/test-runtime.js && node scripts/test-router.js && node scripts/test-recipes.js && node scripts/test-context-writer.js && node scripts/test-pillars.js && node scripts/test-artifact-linter.js && node scripts/test-artifact-diff.js && node scripts/test-design-foundation.js && node scripts/test-linkage.js && node scripts/test-impact.js && node scripts/test-reverse-sync.js && node scripts/test-integration.js && node scripts/test-cross-artifact.js && node scripts/test-awesome-design.js && node scripts/test-skillui-bridge.js && node scripts/test-runtime-verification.js && node scripts/test-agent-browser.js && node scripts/test-mode-d.js && node scripts/test-runtime-heuristics.js && node scripts/test-agent-validator.js && node scripts/test-story-validator.js && node scripts/test-state.js && node scripts/test-intent.js && node scripts/test-events.js && node scripts/test-golden-artifacts.js && node scripts/test-install-smoke.js && node scripts/test-checkpoint.js && node scripts/test-extensions.js && node scripts/test-event-reader.js && node scripts/test-state-lock.js && node scripts/test-cost-saver.js && node scripts/test-budget-onoff.js && node scripts/test-workflow-runner.js && npm run test:e2e && node scripts/test-otel-exporter.js && node scripts/test-extensions-publish.js",
     "prepublishOnly": "npm test",
     "validate-skills": "node scripts/validate-skills.js",
     "test:surface": "node scripts/test-doc-surface-counts.js",
@@ -17,7 +17,11 @@
     "test:context": "node scripts/test-context-writer.js",
     "test:pillars": "node scripts/test-pillars.js",
     "test:linter": "node scripts/test-artifact-linter.js",
-    "test:diff": "node scripts/test-artifact-diff.js"
+    "test:diff": "node scripts/test-artifact-diff.js",
+    "test:e2e": "node tests/integration/full-arc.test.js",
+    "test:audit": "npm audit --omit=dev && git diff --check && npm run test:surface",
+    "pack:check": "node scripts/check-package-contents.js",
+    "release:check": "npm test && npm run test:audit && npm run pack:check"
   },
   "keywords": [
     "ai",

package/references/building/README.md

@@ -4,14 +4,12 @@ Per-tier reference content for Tier 2 (Building: Repo, Build).
 
 ## Files
 
-- (placeholder)
+- `BUILD-ANTIPATTERNS.md`: failure modes for implementation planning and execution.
+- `BUILD-VERTICAL-SLICES.md`: guidance for slicing work into user-visible increments.
+- `BUILD-WAVES.md`: dependency-aware parallelism patterns for multi-agent work.
 
-## Planned content
+## Use
 
-- TDD violation examples with how-to-fix
-- Two-stage review checklists with worked findings
-- Vertical slice anatomy with anti-examples (horizontal "set up the database")
-- Atomic commit examples
-- Wave parallelism dependency analysis worked examples
-
-See [HAVE-NOTS.md](../HAVE-NOTS.md) for the canonical failure-mode catalog.
+Use these references when reviewing implementation plans, build execution, and
+agent workstream shape. Pair them with [HAVE-NOTS.md](../HAVE-NOTS.md) for the
+canonical failure-mode catalog.

package/references/planning/README.md

@@ -4,13 +4,16 @@ Per-tier reference content for Tier 1 (Planning: PRD, Architecture, Roadmap, Sta
 
 ## Files
 
-- (placeholder; antipattern catalogs and worked examples to be added)
+- `PRD-ANATOMY.md`: structure and evidence expectations for product requirements.
+- `PRD-ANTIPATTERNS.md`: common ways PRDs become generic, untestable, or ungrounded.
+- `ARCH-ANATOMY.md`: architecture decision structure, boundaries, and tradeoff framing.
+- `ARCH-ANTIPATTERNS.md`: architecture theater, cargo-cult patterns, and weak constraints.
+- `STACK-ANATOMY.md`: stack decision shape, flip points, and operational fit.
+- `STACK-ANTIPATTERNS.md`: technology-choice failure modes and substitution-test misses.
+- `ROADMAP-ANATOMY.md`: sequencing, dependency, and milestone structure.
+- `ROADMAP-ANTIPATTERNS.md`: feature-factory, Gantt theater, and shelf-roadmap failures.
 
-## Planned content
+## Use
 
-- PRD anatomy with line-by-line annotations of a substitution-tested example
-- ARCH antipatterns: architecture theater, paper-tiger, cargo-cult cloud-native
-- Worked Stack decision examples with flip-point analysis
-- Roadmap anti-examples: Gantt theater, feature-factory output, shelf roadmaps
-
-See [HAVE-NOTS.md](../HAVE-NOTS.md) for the canonical failure-mode catalog.
+Use these references when reviewing or generating Tier 1 artifacts. Pair them
+with [HAVE-NOTS.md](../HAVE-NOTS.md) for the canonical failure-mode catalog.

package/references/shipping/README.md

@@ -4,15 +4,16 @@ Per-tier reference content for Tier 3 (Deploy, Observe, Launch, Harden).
 
 ## Files
 
-- (placeholder)
+- `DEPLOY-PATTERNS.md`: deployment promotion patterns and release safety checks.
+- `DEPLOY-ANTIPATTERNS.md`: deployment failure modes and operational shortcuts.
+- `OBSERVE-SLO-EXAMPLES.md`: SLO, alerting, and error-budget examples.
+- `OBSERVE-ANTIPATTERNS.md`: observability gaps, noisy alerts, and weak signals.
+- `LAUNCH-ANTIPATTERNS.md`: launch readiness, messaging, and adoption failure modes.
+- `HARDEN-OWASP-WORKSHEETS.md`: security review worksheets based on OWASP categories.
+- `HARDEN-ANTIPATTERNS.md`: hardening gaps and security theater patterns.
 
-## Planned content
+## Use
 
-- Same-artifact promotion patterns and anti-patterns
-- SLO worked examples with error budget policies
-- Symptom-vs-cause alerting catalog
-- OWASP Top 10 manual review worksheets
-- Launch copy substitution-test calibration set
-- D-7 to D+7 runbook templates
-
-See [HAVE-NOTS.md](../HAVE-NOTS.md) for the canonical failure-mode catalog.
+Use these references when preparing production releases, observability plans,
+launch plans, and hardening reviews. Pair them with
+[HAVE-NOTS.md](../HAVE-NOTS.md) for the canonical failure-mode catalog.

package/skills/god-doctor.md

@@ -48,7 +48,7 @@ GODPOWERS DOCTOR
 Install: claude (~/.claude/)
   [OK] 106 skills installed
   [OK] 39 agents installed
-  [OK] VERSION matches (1.6.0)
+  [OK] VERSION matches (1.6.2)
   [WARN] routing/god-doctor.yaml exists but skill file did not until now
 
 Project: /Users/.../my-project/.godpowers/

package/skills/god-version.md

@@ -14,7 +14,7 @@ Print version and a short capability summary.
 ## Output
 
 ```
-Godpowers v1.6.0
+Godpowers v1.6.2
 Install: /Users/.../.claude/  (matches package.json)
 Surface: 106 skills, 39 agents, 13 workflows, 36 recipes
 Schema: intent.v1, state.v1, events.v1, workflow.v1, routing.v1, recipe.v1