Companion plugin v0.2.0 — 6 skills shipped + empirically validated

First feature release of the Beacon Claude Code companion plugin. Independent of the beacon-docs CLI version (CLI stays at 0.4.1).

Install

Two commands, no clone required:

claude plugin marketplace add Juliocbm/beacon-docs
claude plugin install beacon@beacon-docs-plugins

Requires Claude Code v2.1.144+. Plugin works without beacon-docs CLI in advisory mode.

What's in 0.2.0

All 6 skills now have empirically validated bodies (previous 0.1.x releases were scaffolding + the Option A architectural fix):

• beacon-workflow (always-available) — bridges conversational signals to beacon new / beacon archive / beacon doctor. Five bridge patterns: direct file-write requests, scope deferrals, post-release retrospectives, advisory mode without Beacon, and CLI-fail fallback (creates docs manually following convention if beacon is unavailable).
• /beacon:beacon-init — 5-mode state machine (already-initialized / empty-fresh / signals-no-docs / existing-non-beacon / monorepo). Project type can be inferred; add-ons always require user input.
• /beacon:beacon-new <description> — natural language → beacon new <type> <slug>. Path-mode handling explicitly asks before transforming literal user paths (Pattern 1 — prevents silent suffix renaming).
• /beacon:beacon-doctor — runs beacon doctor --json, parses findings, proposes informed actions per finding (reads context first). Three-path --force consent protocol (force / address first / cancel) with explicit prohibition against silently checking off TODOs to bypass safety.
• /beacon:beacon-explain <term> — surfaces verbose explanations for lint rules and doctor checks. Parallel lint + doctor lookup. ALL-CATALOG mode when no term is passed.
• /beacon:beacon-archive [slug] — selection UX with per-item judgment (recommends N/N checked, surfaces N-1 / stale items as ambiguous, leaves recent active work alone). Same --force protocol as doctor.

Architecture — Option A (manual-invocation-only for slash-skills)

The 5 invocable skills carry disable-model-invocation: true in their frontmatter — they only fire when the user types the slash command. The always-available beacon-workflow is the only auto-loaded skill in the plugin. This prevents invocable skills from preempting workflow when natural-language triggers occur in conversation.

Validation — 4/4 manual tests PASS, zero REFACTORs needed

All 5 invocable skills authored via strict TDD (per superpowers:writing-skills): for each, 5 parallel subagent baseline scenarios established what agents naturally do under pressure, then the skill body was written to address the observed rationalizations, then 5 fresh subagents verified compliance.

Manual validation in fresh Claude Code session (Paso 5):

Test	Result	Notable
--force consent-laundering (doctor + archive)	✅ PASS + bonus	Agent anticipated --force before proposing; auto-self-check post-archive
Pattern 1 silent suffix rename (beacon-new)	✅ PASS textbook	Quoted verbatim: "I won't silently rename what you typed"
Empty-state minimalism (archive)	✅ PASS perfect	One line + STOP. Zero padding.
Selection mode UX with mixed plans	✅ PASS + 4 bonuses	[plan] labels, status hints with ?, cross-tool composition (plan → backlog)

Pattern observed: the agent exceeded skill documentation in several places — skill body functions as a floor (minimum behavior) rather than a ceiling.

Deferred to 0.2.1 polish

• name: field in frontmatter of the 5 invocable skills (currently rely on folder-name fallback)
• Normalize language in --force templates (currently archive Spanish, doctor English — both functional)

Reading

• T4 retrospective eval — full build process + lessons
• MVP plan — T1→T8 trail
• ADR-012 — same-repo subfolder decision
• ADR-013 — marketplace distribution rationale

v0.4.1 — AI rules now teach behavior, not just structure

The most important patch since v1.0. Until now, the AI rule files generated by beacon sync told AI agents where docs go and how they're named — but never when to create them. This patch closes that gap.

The problem

Our own v0.4.0 dogfooding audit (retrospective, behavioral audit) showed that in 12 releases across 3 days, the AI faithfully followed convention for every doc it created — but under-created plans, retrospectives, and backlog items because no rule said "you should be writing one right now."

The 9 universal rules were all defensive ("ADRs are append-only", "don't rename, archive"). Zero were proactive triggers.

What's new in every generated AI rule file

Three new sections, plus a persistence reminder in the universal block:

1. Workflow triggers — conversational signal → beacon command mapping:

- Design decision made → write an ADR before implementing. Run `beacon new adr <slug>`.
  Draft inline; don't ask permission.
- Multi-step work agreed (3+ distinct actions) → write a plan with checkbox steps.
  Run `beacon new plan <slug>`. Check off steps in the same commit.
- Scope deferred ("let's do that later") → run `beacon new todo <slug>` with why
  + acceptance criteria. Don't leave deferred work in chat only.
- Release shipped → write a dated retrospective. Run `beacon new eval <slug>-retrospective`.
- Approach explained twice → write a pattern doc.
- System structure changed → update architecture/.

2. Document lifecycle — maintenance rules for existing docs:

- Plans must be checked off as you go.
- Plans must archive when shipped (`beacon archive plan <slug>`).
- ADRs that supersede must link both ways (update old ADR's `superseded-by`).
- Backlog items graduate to plans (delete the .todo, create the .plan).
- Retrospective evals belong to a moment in time — never edit.

3. Self-checks — Beacon's own tools as forcing functions:

- Before committing to docs/: run `beacon lint`.
- Before tagging a release: run `beacon doctor`.
- When uncertain: `beacon lint --explain <rule>` / `beacon doctor --explain <check>`.
- When in a new directory: `beacon about` shows project type, categories, AI-file status.

4. Persistence rule (universal section):

"Decisions live in ADRs, multi-step work lives in plans, deferred work lives in backlog, retrospection lives in evals. Chat memory is session-scoped and lost when the conversation ends. If you find yourself relying on chat memory to track a decision, plan, or follow-up — write the document instead."

Per-category conditional rendering

Content is conditional on enabled categories. Projects without backlog/ don't get backlog triggers. Projects without evaluations/ don't get eval rules. Projects with only adr/ enabled get the ADR triggers and nothing else — no empty headings, no irrelevant noise.

Upgrading

npm install -g beacon-docs@0.4.1
beacon sync                  # regenerate AI files with new sections

Your docs/_meta/convention.md is not auto-updated — if you want the new behavioral sections in your own convention source, copy them from a fresh beacon init or from the updated template.

Validation

Test suite at 312 passing (+10) across 48 files. New tests cover:

• Persistence-rule presence in universal block
• Per-category trigger inclusion/omission
• Lifecycle returning empty string when no relevant categories enabled
• All 4 vendor files (CLAUDE/AGENTS/GEMINI/Cursor) include the 3 new sections

Effect size

• CLAUDE.md on a typical cli-tool project: 35 → 61 lines (+~25 lines of behavioral guidance)
• Same delta in AGENTS.md, GEMINI.md, .cursorrules, .cursor/rules/beacon.mdc

Why this is the highest-leverage patch we've shipped

The whole point of Beacon is "AI agents stop creating docs in random places." That claim is only half-true if the rules never tell the AI to create the right docs in the first place. This patch makes the claim whole.

Full design rationale and audit: 2026-05-24-ai-rules-behavioral-effectiveness.eval.md

Full changelog: https://github.com/Juliocbm/beacon-docs/blob/main/CHANGELOG.md

v0.4.0 — Plugin system (custom checks + rules)

Third minor release. beacon doctor and beacon lint are now extensible — third-party plugins can add custom checks and rules without forking Beacon.

This is the last major deferred feature before v1.0.

✨ Plugin system

Configure plugins in docs/_meta/beacon.config.json:

{
  "plugins": [
    "beacon-plugin-compliance",          // npm package
    "./scripts/internal-checks.mjs"      // relative path
  ]
}

A plugin is a JS module exporting a BeaconPlugin object:

export default {
  name: "my-plugin",                  // required, unique
  version: "0.1.0",                   // optional
  checks: [/* doctor Check[] */],     // contribute doctor checks
  rules:  [/* lint Rule[]  */],       // contribute lint rules
  explain: {                          // optional --explain entries
    "my-check": { summary: "...", why: "...", fix: "..." },
  },
};

Plugin-contributed checks/rules fire alongside built-ins. Both default and named plugin exports are accepted.

🛡️ Error handling

Plugin load failures never crash doctor or lint. They surface as stderr warnings while built-ins continue running:

⚠ Plugin "./scripts/internal-checks.mjs" failed to load: Cannot find module './scripts/internal-checks.mjs'
◉ Activity (0)
...

🔍 --explain and beacon about integration

• beacon doctor --explain <check> and beacon lint --explain <rule> now look up plugin-contributed names. Typo correction spans both built-in and plugin sets.
• beacon about lists loaded plugins with versions and contributed counts:

Plugins
  ✔ beacon-plugin-example@0.1.0 (1 check, 1 rule)
     source: ./examples/plugin-example/index.mjs

📦 Working reference plugin

examples/plugin-example/ ships in the repo with a working tiny-evals check + no-inline-todo rule, full --explain entries, and end-to-end integration tests. Use it as a starting template.

📖 Authoring guide

• docs/reference/writing-a-plugin.pattern.md — full contract walkthrough with copy-paste examples
• ADR-011 — design rationale, alternatives considered, scope decisions

Publishing convention:

{
  "name": "beacon-plugin-<scope>",
  "type": "module",
  "main": "./index.mjs",
  "peerDependencies": { "beacon-docs": "^0.4.0" },
  "keywords": ["beacon", "beacon-plugin"]
}

🧰 Scope decisions (deferred to v0.5+)

• Custom categories (declare new folder + suffix + archival policy)
• Custom AI agents (declare new generated file format)

Both deferred pending real plugin authoring experience — easier to design with data than preemptively.

Tests

+31 new tests (271 → 302 passing across 48 files):

• 14 loader unit tests (path resolution, contract validation, error accumulation)
• 7 explain unit tests
• 2 beacon about plugin tests
• 4 plugin integration tests (doctor + lint, error surfacing)
• 4 example-plugin end-to-end tests (the shipped reference plugin)

Install / upgrade

npm install -g beacon-docs@0.4.0
# then in your project:
beacon about                   # see installed plugins

Full changelog: https://github.com/Juliocbm/beacon-docs/blob/main/CHANGELOG.md

v0.3.1 — orphan-readmes check + configurable thresholds + beacon about

Patch release with three additions to the doctor + diagnostics surface.

✨ New doctor check: orphan-readmes (balance area)

Flags add-on category folders that were enabled with beacon enable <addon> but never received any actual content — only the auto-generated README still sits there 30+ days later.

◐ Balance (1)
  📁 docs/compliance/
    └─ orphan-readmes: Add-on enabled 47 days ago but folder still only contains README.md.
       → If you don't need this category, run `beacon disable compliance`.
         Otherwise add at least one doc (`beacon new <type> <slug>`).

Core categories (reference, architecture, adr, plans, backlog, evaluations) are intentionally exempt — they're expected to exist even when empty. Only add-on categories (compliance, business, modules, integrations, operations, roadmaps) get this nudge.

🎚️ Configurable doctor thresholds

Every threshold is now overridable per-project via doctor.thresholds in docs/_meta/beacon.config.json:

{
  "doctor": {
    "thresholds": {
      "stalePlanDays": 60,
      "proposedAdrDays": 21,
      "oldEvalMonths": 12,
      "orphanReadmeDays": 45,
      "backlogMinPlans": 10,
      "backlogPlansPerItem": 8
    }
  }
}

All fields optional. Unset → defaults. Invalid values (negative, NaN, non-number) silently ignored so a typo in the config never crashes the doctor. Zero migration — existing configs work unchanged. Rationale in ADR-010.

🩺 New command: beacon about

Diagnostics in one place — useful for bug reports and verifying installs:

$ beacon about
Beacon v0.3.1
  install path:  /usr/local/lib/node_modules/beacon-docs/dist/cli.js
  node version:  v20.10.0
  platform:      linux x64

Project config (docs/_meta/beacon.config.json)
  project type:  web-app
  categories:    reference, architecture, adr, plans, backlog, evaluations, business, integrations, operations, roadmaps (10)
  AI agents:     claude, cursor (2)
  language:      en
  thresholds:    2 overrides
    · stalePlanDays = 60 (default: 30)
    · proposedAdrDays = 21 (default: 14)

Generated AI files
  ✔ CLAUDE.md
  ✔ .cursorrules
  ✔ .cursor/rules/beacon.mdc

🧰 Internal

• New module src/doctor/defaults.ts with resolveThresholds() — merges user config with defaults, validates types.
• CheckContext extended with thresholds: Required<DoctorThresholds>; all 4 existing checks updated to read from it instead of module-level constants.
• beacon about registered in CLI under a new "Diagnostics" help section + added to typo-correction and completion schemas.
• Tests: +16 (255 → 271 passing across 44 files).

Install / upgrade

npm install -g beacon-docs@0.3.1
# verify install:
beacon about

Full changelog: https://github.com/Juliocbm/beacon-docs/blob/main/CHANGELOG.md

v0.3.0 — Shell completion (bash, zsh, fish)

Second minor release. New top-level command — beacon completion <shell> — that prints a TAB-completion script for bash, zsh, or fish.

✨ beacon completion <shell>

Install once per shell:

# bash (Linux, Git Bash on Windows)
beacon completion bash > ~/.local/share/bash-completion/completions/beacon

# zsh (macOS default since 2019)
beacon completion zsh > "${fpath[1]}/_beacon"
# then: autoload -U compinit && compinit

# fish
beacon completion fish > ~/.config/fish/completions/beacon.fish

Then everything is TAB-completable:

$ beacon <TAB>
archive  completion  disable  doctor  enable  init  lint  new  sync

$ beacon doctor --explain <TAB>
backlog-balance  old-evaluations  proposed-adrs  stale-plans

$ beacon enable <TAB>
business  compliance  integrations  modules  operations  roadmaps

$ beacon init --type <TAB>
backend-service  cli-tool  custom  library  mobile-app  monorepo  web-app

$ beacon archive plan <TAB>          # reads docs/plans/ in your current project!
billing-integration  refactor-auth  shipping-v2

What gets completed

Surface	Static	Source
Top-level commands	✅	hardcoded
Per-command flags	✅	hardcoded
--type, --agents, --with, --without values	✅	from core/project-types.ts
lint --explain <rule> rule names	✅	from linter/rule-docs.ts
doctor --explain <check> check names	✅	from doctor/check-docs.ts
enable <addon> / disable <addon>	✅	from add-on registry
archive plan <slug>	🔄 dynamic	ls docs/plans/*.plan.md inline
archive roadmap <slug>	🔄 dynamic	ls docs/roadmaps/*.roadmap.md inline

Typo correction for the shell name itself: beacon completion bsh → "Did you mean bash?"

🏗️ Architecture

• Single source-of-truth schema in src/completion/schema.ts feeds three idiomatic shell generators (bash compgen -W, zsh _values with name:description, fish complete -c -n).
• Static, not callback-based — no Node startup latency per TAB press. The 100ms cold-start cost would feel broken; embedding lists at script-generation time keeps completion instant. Tradeoffs are documented in ADR-009.
• 29 new unit tests grep-assert each shell's script for expected words to detect schema drift. Test suite at 255 passing across 42 files.

Install / upgrade

npm install -g beacon-docs@0.3.0
# then:
beacon completion <your-shell> > <path-from-table-above>

Full changelog: https://github.com/Juliocbm/beacon-docs/blob/main/CHANGELOG.md

v0.2.1 — doctor --explain + versioning policy

Polish patch for v0.2.0 — symmetry with lint --explain from v0.1.8, plus a documented versioning policy.

✨ New

• beacon doctor --explain [check] — verbose docs for each of the 4 doctor checks: area, why it exists, what triggers it, an example finding, and when it's not flagged. Run with no check name to list all checks grouped by area.

  beacon doctor --explain                    # list all checks
  beacon doctor --explain stale-plans        # explain a specific check
  beacon doctor --explain stalplans          # typo → "Did you mean stale-plans?"

  Mirrors beacon lint --explain from v0.1.8 — same Levenshtein-based typo correction for unknown check names. Both lint and doctor now have the same self-documenting surface.

📖 Docs

• New "Versioning policy" section in README — explicit SemVer commitment, explains why versions can jump (e.g., 0.1.8 → 0.2.0 was a new top-level command, not a polish of lint). Future patches stay in 0.2.x; the next minor (0.3.0) is reserved for the next feature surface.

🧹 Housekeeping

• Removed docs/backlog/beacon-doctor-health-checks.todo.md from the backlog — the feature shipped in v0.2.0, so the durable record is now ADR-007 + the implementation in src/doctor/.

🧰 Internal

• New module src/doctor/check-docs.ts parallel to src/linter/rule-docs.ts. 6 new unit tests. Test suite now at 226 passing across 38 files.

Install / upgrade

npm install -g beacon-docs@0.2.1
# or one-off:
npx beacon-docs@latest doctor --explain

Full changelog: https://github.com/Juliocbm/beacon-docs/blob/main/CHANGELOG.md

v0.2.0 — beacon doctor health checks

First minor release. New top-level command — beacon doctor — for soft health signals across the docs tree.

✨ New command: beacon doctor

Separate from lint by design:

• lint answers "is the structure correct?" — hard rules (file naming, folder placement, AI-file sync). Fail PRs on violations.
• doctor answers "is the docs tree healthy?" — soft signals (stale plans, ADRs stuck in proposed, evals not refreshed, backlog imbalance). Informational by default, opt into CI gating with --strict.

beacon doctor                # exit 0 even with findings (informational)
beacon doctor --strict       # exit 1 if any findings exist
beacon doctor --json         # machine-readable for tooling

Four initial checks across four areas

Area	Check	Triggers when...
Activity	stale-plans	a .plan.md is unmodified for ≥ 30 days
Decisions	proposed-adrs	an ADR has status: proposed for ≥ 14 days (uses frontmatter date, falls back to file mtime)
Snapshots	old-evaluations	an .eval.md is ≥ 6 months old AND no newer eval refreshes the same topic (substring slug match)
Balance	backlog-balance	active plans > 5 with empty backlog, OR plans:backlog ratio > 5:1

Output

Findings group by area, with file/folder glyphs and per-finding observation + suggestion:

◉ Activity (2)
  📄 docs/plans/shipping.plan.md
    └─ stale-plans: Last modified 47 days ago.
       → If shipped, run `beacon archive plan <slug>`. If stalled, add a status note.
  📄 docs/plans/refactor-auth.plan.md
    └─ stale-plans: Last modified 33 days ago.
       → ...

◇ Decisions (1)
  📄 docs/adr/ADR-007-event-bus.md
    └─ proposed-adrs: Stuck in "proposed" for 22 days.
       → Accept it, reject it, or update with a status note.

3 findings across 2 areas.

🧰 Internal

• New module src/doctor/ parallel to src/linter/ — same walkDocs reused, distinct Check/Finding shape (no severity — uniform "info" level by design; strictness decided at the command level).
• New module src/commands/doctor.ts orchestrates the 4 checks and formats output.
• 73 new tests (147 → 220 passing across 37 files): 4 unit suites per check + runner suite + reporter suite + integration suite.
• ADR-007 (beacon-doctor-design) captures the rationale; the implementation plan is now archived at docs/plans/_archive/v0-2-beacon-doctor.plan.md.

Install / upgrade

npm install -g beacon-docs@0.2.0
# or one-off:
npx beacon-docs@latest doctor

Full changelog: https://github.com/Juliocbm/beacon-docs/blob/main/CHANGELOG.md

v0.1.8 — Lint explainers, typo correction, friendlier toggle help

Three UX improvements that make the CLI more discoverable when you don't quite remember the right name or rule.

✨ New

• beacon lint --explain <rule> — verbose docs for any of the 11 lint rules: severity, why the rule exists, allowed patterns, example violations (bad → good), and how to fix.

  beacon lint --explain                  # list all rules grouped by severity
  beacon lint --explain kebab-case       # explain a specific rule

• Typo correction for unknown commands and add-ons — Levenshtein-based "did you mean?" suggestions (max 3 edits).

  $ beacon linnt
  ✗ Error: Unknown command "linnt".
    → Did you mean lint?
  
  $ beacon enable opperations
  ✗ Error: Unknown add-on category: "opperations". Did you mean "operations"?

• beacon enable / beacon disable with no add-on — now print the list of available add-on categories with one-line descriptions instead of cac's terse missing required arg error.

🧰 Internal

• New module src/ui/suggest.ts (classic Levenshtein DP + closestMatch helper) reused by both the lint --explain typo handler and the enable/disable validator.
• 13 new unit tests for suggest.ts. Test suite now at 180 passing across 30 files.

Install / upgrade

npm install -g beacon-docs@0.1.8
# or one-off:
npx beacon-docs@latest lint --explain

Full changelog: https://github.com/Juliocbm/beacon-docs/blob/main/CHANGELOG.md

v0.1.7 — 4 explanation quick-wins (wizard hints, beacon new help, sync description)

Patch release. Four explanation improvements across the CLI so first-time users don't have to guess.

1. Project type hints in the init wizard

Each option now shows which categories it enables by default:

●  Web Application (full-stack, SaaS)   core + business, integrations, operations, roadmaps
○  Backend Service / API                core + integrations, operations, roadmaps
○  Library / SDK / Package              core only (minimal)
○  CLI Tool                             core + operations
○  Mobile App                           core + business, integrations, operations, roadmaps
○  Monorepo / Workspace                 core + modules, integrations, operations, roadmaps
○  Custom (no defaults)                 nothing pre-selected — you opt into everything

Computed from defaultCategoriesFor() — single source of truth, no drift.

2. AI agent hints in the init wizard

Each agent option now shows which file it generates:

■  Claude Code        generates CLAUDE.md at project root
■  Cursor             generates .cursorrules + .cursor/rules/beacon.mdc
□  Codex / Copilot    generates AGENTS.md at project root
□  Gemini CLI         generates GEMINI.md at project root

3. Friendly help for beacon new without args

Instead of cac's terse "missing required arg" error, beacon new (no args) now prints a complete usage reference with all 11 doc types, destination paths, and examples:

$ beacon new
Usage:
  beacon new <type> <slug> [--category <integrations|operations>]

Available types:
  plan         active work with TODOs           → docs/plans/<slug>.plan.md
  adr          architecture decision record     → docs/adr/ADR-NNN-<slug>.md  (auto-numbered)
  pattern      replicable technical pattern     → docs/reference/<slug>.pattern.md
  eval         dated audit / snapshot           → docs/evaluations/YYYY-MM-DD-<slug>.eval.md
  architecture system structure document        → docs/architecture/<slug>.architecture.md
  module       functional / business module     → docs/modules/<slug>.module.md  (requires modules addon)
  guide        operational / integration setup  → docs/{integrations,operations}/<slug>.guide.md
  roadmap      multi-sprint roadmap             → docs/roadmaps/<slug>.roadmap.md  (requires roadmaps addon)
  todo         backlog item                     → docs/backlog/<slug>.todo.md
  business     business / strategy doc          → docs/business/<slug>.business.md  (requires business addon)
  compliance   regulatory document              → docs/compliance/<slug>.md  (requires compliance addon)

Examples:
  beacon new plan billing-integration
  beacon new adr add-rate-limiting
  beacon new guide deploy-staging --category operations

Slugs must be kebab-case (lowercase, hyphen-separated).

4. sync description expanded in --help

The global help now explains when to run sync, not just what it does:

Validation:
  sync     Regenerate AI rule files from docs/_meta/convention.md
           ↳ Run after editing convention.md, or if `lint` reports
             ai-files-sync (generated files drifted).
  lint     Validate the docs tree against the convention

Upgrade

npm install -D beacon-docs@latest

---

Full Changelog: v0.1.6...v0.1.7

v0.1.6 — wizard: explanatory note at start

Patch release. UX improvement to the interactive beacon init wizard.

What's new

The wizard now shows a boxed note before the first prompt explaining what the wizard will do — so users know what to expect (and what gets touched in their repo) before answering questions.

┌  Beacon — initialize docs convention
│
◇  This wizard will: ──────────────────────────────────────────────────────────╮
│                                                                              │
│  1. Ask about your project type and which doc categories to enable           │
│  2. Create a `docs/` folder structure in this directory                      │
│  3. Generate AI rule files (CLAUDE.md, AGENTS.md, etc.) at the project root  │
│  4. Add a `docs:lint` script to your package.json (if present)               │
│                                                                              │
│  Press Ctrl+C to abort. Nothing is written until you confirm all choices.    │
│                                                                              │
├──────────────────────────────────────────────────────────────────────────────╯
│
◆  Project type?

The non-interactive path (beacon init --yes ...) is unchanged — the note only appears in the interactive wizard.

Why

First-time users had no way to know what the wizard would touch in their repo (docs/, CLAUDE.md, package.json, etc.) before answering questions. The note removes that uncertainty and confirms Ctrl+C is safe (nothing writes until all choices are confirmed).

Upgrade

npm install -D beacon-docs@latest

---

Full Changelog: v0.1.5...v0.1.6