ai-rulez 4.14.1 → 4.16.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +11 -9
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -80,12 +80,14 @@ Specialized agents ready to use as subagents:
80
80
 
81
81
  | Agent | Domain | Model | What it does |
82
82
  | -------------------- | ------------- | ------ | -------------------------------------------------------------------------------- |
83
- | **code-reviewer** | ai-governance | sonnet | Reviews changes for correctness, security, and conventions. Reports by severity. |
84
- | **test-writer** | testing | sonnet | Writes tests following strict TDD. Fails first, then implements. |
85
- | **security-auditor** | security | sonnet | Audits dependencies, scans for CVEs, reviews input validation. |
86
- | **docs-writer** | ai-governance | haiku | Writes clear, concise documentation. No fluff. |
87
- | **devops-engineer** | cicd | haiku | CI/CD pipelines, GitHub Actions, Docker, deployment automation. |
88
- | **release-engineer** | cicd | haiku | Version management, changelogs, multi-registry publishing. |
83
+ | **code-reviewer** | ai-governance | sonnet | Reviews changes for correctness, security, and conventions. Reports by severity. |
84
+ | **test-writer** | testing | sonnet | Writes tests following strict TDD. Fails first, then implements. |
85
+ | **security-auditor** | security | sonnet | Audits dependencies, scans for CVEs, reviews input validation. |
86
+ | **docs-writer** | ai-governance | sonnet | Writes clear, concise documentation. No fluff. |
87
+ | **devops-engineer** | cicd | sonnet | CI/CD pipelines, GitHub Actions, Docker, deployment automation. |
88
+ | **release-engineer** | cicd | sonnet | Version management, changelogs, multi-registry publishing. |
89
+ | **ffi-engineer** | polyglot-bindings | sonnet | Native FFI and cross-language binding work. |
90
+ | **polyglot-architect** | polyglot-bindings | opus | Cross-language architecture and binding design. |
89
91
 
90
92
  ### Opt-in Domains
91
93
 
@@ -190,7 +192,7 @@ Accepted values: `low`, `medium`, `high`, `xhigh`, `max`, `inherit`. ai-rulez em
190
192
  - **Codex** — `model_reasoning_effort` in `.codex/config.toml` and `.codex/agents/*.toml`
191
193
  - **Amp** — `amp.anthropic.effort` in `.amp/settings.json` (global)
192
194
  - **Windsurf** — `reasoning_effort` in `.windsurf/agents/*.md` frontmatter (per-agent)
193
- - **Opencode** — `reasoningEffort` in `.opencode/agents/*.md` frontmatter (per-agent)
195
+ - **Opencode** — `variant` in `.opencode/agents/*.md` frontmatter (per-agent); joins the agent's `model` as `model#variant`
194
196
  - **Xum** — `ai.thinkingLevel` in `.xum/agents/*.md` frontmatter (per-agent)
195
197
 
196
198
  Each preset maps the value to its own vocabulary; tools without a documented config surface (Cursor, Copilot, Gemini, etc.) are silently skipped. See [docs/configuration.md](docs/configuration.md#defaults) for the full mapping table.
@@ -304,7 +306,7 @@ Add to `.pre-commit-config.yaml`:
304
306
  ```yaml
305
307
  repos:
306
308
  - repo: https://github.com/Goldziher/ai-rulez
307
- rev: v4.14.1
309
+ rev: v4.16.0
308
310
  hooks:
309
311
  - id: ai-rulez-recursive # generate outputs across the repo
310
312
  - id: ai-rulez-validate # dry-run validation
@@ -326,7 +328,7 @@ repository needs. This requires AI-Rulez 4.9.0+ and Poly 0.14.0+:
326
328
  [[hooks.sources]]
327
329
  id = "ai-rulez"
328
330
  git = "https://github.com/Goldziher/ai-rulez.git"
329
- revision = "v4.14.1"
331
+ revision = "v4.16.0"
330
332
  hooks = ["ai-rulez-recursive", "ai-rulez-plugin-verify"]
331
333
  ```
332
334
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "ai-rulez",
3
- "version": "4.14.1",
3
+ "version": "4.16.0",
4
4
  "description": "Complete AI development workflow for 13 AI coding tools. Ships with builtin rules, agents, and conventions. Generate native configs for Claude, Cursor, Copilot, Windsurf, Gemini, Codex and more from a single source.",
5
5
  "keywords": [
6
6
  "agents",