Document OpenCode 2 support and the humanizer skill

This commit is contained in:
Wayner Barrios
2026-10-19 10:06:07 -04:00
parent d263639d8c
commit 510f18941b
7 changed files with 127 additions and 34 deletions
+2 -2
View File
@@ -5,12 +5,12 @@
"name": "Wayner Barrios",
"url": "https://github.com/waybarrios"
},
"description": "Portable software-development skills for Claude Code, Codex, OpenCode, and Pi.",
"description": "Skills for Claude Code, Codex, OpenCode 1 and 2, and Pi.",
"plugins": [
{
"name": "opencode-power-pack",
"source": "./",
"description": "Fifty-five workflows for review, security, feature development, frontend work, authoring, and ML tooling.",
"description": "Fifty-five workflows for review, security, feature development, frontend work, writing, authoring, and ML tools.",
"category": "productivity",
"tags": [
"software-development",
+2 -2
View File
@@ -3,12 +3,12 @@
"name": "opencode-power-pack",
"displayName": "OpenCode Power Pack",
"version": "0.5.0",
"description": "Fifty-five software-development workflows for Claude Code, Codex, OpenCode, and Pi.",
"description": "Fifty-five workflows for Claude Code, Codex, OpenCode 1 and 2, and Pi.",
"author": {
"name": "Wayner Barrios",
"url": "https://github.com/waybarrios"
},
"homepage": "https://github.com/waybarrios/opencode-power-pack",
"homepage": "https://skills.waybarrios.com",
"repository": "https://github.com/waybarrios/opencode-power-pack",
"license": "MIT AND Apache-2.0",
"keywords": [
+4 -4
View File
@@ -1,12 +1,12 @@
{
"name": "opencode-power-pack",
"version": "0.5.0",
"description": "Fifty-five software-development workflows for Claude Code, Codex, OpenCode, and Pi.",
"description": "Fifty-five workflows for Claude Code, Codex, OpenCode 1 and 2, and Pi.",
"author": {
"name": "Wayner Barrios",
"url": "https://github.com/waybarrios"
},
"homepage": "https://github.com/waybarrios/opencode-power-pack",
"homepage": "https://skills.waybarrios.com",
"repository": "https://github.com/waybarrios/opencode-power-pack",
"license": "MIT AND Apache-2.0",
"keywords": [
@@ -25,8 +25,8 @@
"skills": "./skills/",
"interface": {
"displayName": "Cross-Agent Power Pack",
"shortDescription": "Fifty-five workflows for Claude Code, Codex, OpenCode, and Pi",
"longDescription": "Review code, audit security, design and implement features, build MCP servers, and maintain project guidance with reusable workflows for Claude Code, Codex, OpenCode, and Pi.",
"shortDescription": "55 workflows for Claude Code, Codex, OpenCode 1 and 2, and Pi",
"longDescription": "Review code, check security, build features and MCP servers, edit English and Spanish copy, and maintain project guidance. Supports Claude Code, Codex, OpenCode 1 and 2, and Pi.",
"developerName": "Wayner Barrios",
"category": "Productivity",
"capabilities": [
+53 -24
View File
@@ -2,10 +2,10 @@
<img src="assets/logo.svg" alt="opencode-power-pack" width="100%" />
</p>
<h1 align="center">OpenCode Power Pack for Claude Code, Codex, OpenCode + Pi</h1>
<h1 align="center">OpenCode Power Pack for Claude Code, Codex, OpenCode 1 + 2, and Pi</h1>
<p align="center">
<i>Fifty-five portable workflows for Claude Code, Codex, OpenCode, and Pi.<br/>
<i>Fifty-five portable workflows for Claude Code, Codex, OpenCode 1 and 2, and Pi.<br/>
Code review, security audit, feature development, frontend design, project memory, and authoring tools.</i>
</p>
@@ -24,6 +24,8 @@
<p align="center">
<a href="#installation"><b>Install</b></a> ·
<a href="https://skills.waybarrios.com/docs/"><b>Documentation</b></a> ·
<a href="#opencode-2-and-humanizer"><b>OpenCode 2</b></a> ·
<a href="#selective-install-with-npm"><b>Select Skills</b></a> ·
<a href="#claude-code-quick-install"><b>Claude Code</b></a> ·
<a href="#codex-quick-install"><b>Codex Quick Install</b></a> ·
@@ -35,7 +37,25 @@
<a href="#acknowledgments"><b>Credits</b></a>
</p>
## New in v0.5.0: Lightweight Native Sandboxes
## OpenCode 2 and humanizer
The current `main` branch supports OpenCode 2 and keeps OpenCode 1.18.7 support. Both hosts load all 55 skills and the three feature-development specialists. Smoke tests cover OpenCode 1.18.7, 2.0.14, and 2.0.32, including effective read-only permissions on V2.
Install the current plugin in OpenCode 2:
```bash
opencode plugin add "opencode-power-pack@git+https://github.com/waybarrios/opencode-power-pack.git"
```
The new `humanizer` skill rewrites English and Spanish copy in a direct, natural voice. It keeps facts, names, numbers, and code intact. The `authoring` profile now includes `humanizer`, `mcp-builder`, `paper-summarizer`, and `skill-creator`.
Invoke it with `$humanizer` in Codex, `/humanizer` in OpenCode, or `/opencode-power-pack:humanizer` in Claude Code.
**Use the Git installation for these additions.** The published npm package and tag `v0.5.0` still contain 54 skills and the V1-only plugin. They do not include `humanizer` or the OpenCode 2 plugin port. The npm selective installer can still copy its released skills into `.agents/skills` for OpenCode 2.
For host commands, update steps, and the current catalog, see the [documentation](https://skills.waybarrios.com/docs/) and [skill reference](https://skills.waybarrios.com/docs/skills/). The [OpenCode compatibility guide](docs/opencode-compatibility.md) covers source selection and V2 permissions.
## Native sandboxes in v0.5.0
OpenCode Power Pack now includes an opt-in, fail-closed sandbox runner for safer command execution from **Codex, OpenCode, Claude Code, and Pi**. It gives all four agents one portable capability contract with four least-privilege profiles, while using native Seatbelt isolation on macOS and Bubblewrap on Linux.
@@ -160,11 +180,20 @@ Maintainers publish the mirror with the `Publish GitHub Package` workflow. Relea
| `frontend` | Frontend implementation and anti-generic design critique |
| `security` | Security review, threat modeling, static analysis, validation, and reporting |
| `huggingface` | Model discovery, local inference, training, evaluation, Spaces, and AWS deployment |
| `authoring` | Skill and MCP authoring plus technical-paper summarization |
| `authoring` | Skills, MCP servers, technical-paper summaries, and natural copy editing on `main` |
| `project-memory` | Audit and maintain durable project guidance |
Profiles automatically include required companion skills and can be combined with individual skill names. The default destination is `~/.agents/skills`; `--project` finds the current Git root and installs into its `.agents/skills` directory. Existing directories are skipped unless `--force` is provided, and replacements are staged with rollback plus per-skill locking. Every copied skill retains its provenance, third-party notices, and license texts. Use `--dry-run` to preview or `--all` to install the complete catalog.
The commands above use the published npm catalog. To selectively install `humanizer` or the four-skill `authoring` profile from current source:
```bash
npx --package=git+https://github.com/waybarrios/opencode-power-pack.git opencode-power-pack install humanizer --dry-run
npx --package=git+https://github.com/waybarrios/opencode-power-pack.git opencode-power-pack install humanizer
```
Use `install --profile authoring` instead of `install humanizer` for all four authoring skills. These commands install into `~/.agents/skills`. For a project-local install, run the same command from the target repository with `--project`.
The npm installer and the full Claude Code/Codex/OpenCode plugins are alternative activation paths. Claude Code users should prefer the namespaced plugin because the selective installer currently targets the portable `.agents/skills` location used by Codex, OpenCode, and Pi. If a full plugin is already active, selectively copying the same skills does not reduce that plugin's loaded catalog.
## Sandbox Capability Contract
@@ -261,7 +290,7 @@ It complements [obra/superpowers](https://github.com/obra/superpowers), which pr
| Review | `fp-check` | Systematically verify a suspected security bug to a TRUE/FALSE POSITIVE verdict |
| Review | `vuln-report` | Draft a single-vulnerability disclosure report in GitHub advisory style |
| Review | `agentic-actions-auditor` | Audit GitHub Actions workflows for prompt-injection risk in AI agent integrations |
| Review | `security-threat-model` | Repository-grounded threat modeling — trust boundaries, assets, abuse paths |
| Review | `security-threat-model` | Model threats using repository evidence, trust boundaries, assets, and abuse paths |
| Review | `differential-review` | Security-focused differential review of a diff/PR with blast-radius analysis |
| Review | `variant-analysis` | Find similar vulnerabilities/bugs across a codebase from one initial pattern |
| Review | `sarif-parsing` | Parse, filter, dedupe, and convert SARIF output from CodeQL/Semgrep/other scanners |
@@ -281,30 +310,30 @@ It complements [obra/superpowers](https://github.com/obra/superpowers), which pr
| Authoring | `humanizer` | Rewrite AI-generated copy in ES/EN into direct, natural prose without inventing facts |
| Authoring | `mcp-builder` | Design and build MCP servers in TypeScript or Python |
| Authoring | `skill-creator` | Create, test, and improve reusable `SKILL.md` workflows |
| Hugging Face | `hf-cli` | Core `hf` CLI usage — auth, cache, repos, jobs, papers, Spaces, and more |
| Hugging Face | `hf-cli` | Use the `hf` CLI for auth, cache, repos, jobs, papers, and Spaces |
| Hugging Face | `hf-mem` | Estimate memory needed to load Safetensors/GGUF weights for inference |
| Hugging Face | `huggingface-best` | Find and compare the best model for a task via official benchmark leaderboards |
| Hugging Face | `huggingface-datasets` | Dataset Viewer API workflows — metadata, pagination, search, filters |
| Hugging Face | `huggingface-datasets` | Dataset Viewer API workflows for metadata, pagination, search, and filters |
| Hugging Face | `huggingface-papers` | Look up and analyze Hugging Face / arXiv paper pages via the papers API |
| Hugging Face | `huggingface-paper-publisher` | Publish and manage research papers on the Hub, including research-article templates |
| Hugging Face | `huggingface-tool-builder` | Build reusable scripts/tools around the Hugging Face API |
| Hugging Face | `huggingface-local-models` | Select and run GGUF models locally with llama.cpp (CPU/Metal/CUDA/ROCm) |
| Hugging Face — Training | `huggingface-llm-trainer` | Fine-tune LLMs (TRL: SFT/DPO/GRPO, or Unsloth) on Hugging Face Jobs |
| Hugging Face — Training | `huggingface-vision-trainer` | Fine-tune object detection, image classification, and SAM/SAM2 segmentation models |
| Hugging Face — Training | `train-sentence-transformers` | Train bi-encoder/cross-encoder/sparse embedding models |
| Hugging Face — Training | `trl-training` | TRL CLI training — SFT, DPO, GRPO, KTO, RLOO, reward modeling |
| Hugging Face — Training | `huggingface-community-evals` | Run local evaluations with inspect-ai / lighteval |
| Hugging Face — Training | `huggingface-trackio` | Track and visualize ML training experiments with Trackio |
| Hugging Face — Spaces | `huggingface-spaces` | Build, deploy, and debug Gradio/Docker/static Spaces |
| Hugging Face — Spaces | `huggingface-gradio` | Build Gradio web UIs and demos in Python |
| Hugging Face — Spaces | `huggingface-lora-space-builder` | Build and publish a Gradio Space demo for a user-provided LoRA |
| Hugging Face — Spaces | `huggingface-zerogpu` | Write/debug ZeroGPU-constrained Gradio Space code |
| Hugging Face — Cloud | `hf-cloud-aws-context-discovery` | Discover the user's local AWS context before any AWS work |
| Hugging Face — Cloud | `hf-cloud-python-env-setup` | Set up an isolated Python env for SageMaker/AWS work |
| Hugging Face — Cloud | `hf-cloud-sagemaker-deployment-planner` | Entry point for planning a SageMaker model deployment |
| Hugging Face — Cloud | `hf-cloud-sagemaker-iam-preflight` | Ensure a usable SageMaker execution role exists before deploying |
| Hugging Face — Cloud | `hf-cloud-serving-image-selection` | Pick the right SageMaker serving container image |
| Hugging Face — Cloud | `hf-cloud-sagemaker-production-defaults` | Create a SageMaker endpoint with autoscaling, alarms, and tagging by default |
| Hugging Face training | `huggingface-llm-trainer` | Fine-tune LLMs (TRL: SFT/DPO/GRPO, or Unsloth) on Hugging Face Jobs |
| Hugging Face training | `huggingface-vision-trainer` | Fine-tune object detection, image classification, and SAM/SAM2 segmentation models |
| Hugging Face training | `train-sentence-transformers` | Train bi-encoder/cross-encoder/sparse embedding models |
| Hugging Face training | `trl-training` | Train with the TRL CLI using SFT, DPO, GRPO, KTO, RLOO, and reward modeling |
| Hugging Face training | `huggingface-community-evals` | Run local evaluations with inspect-ai / lighteval |
| Hugging Face training | `huggingface-trackio` | Track and visualize ML training experiments with Trackio |
| Hugging Face Spaces | `huggingface-spaces` | Build, deploy, and debug Gradio/Docker/static Spaces |
| Hugging Face Spaces | `huggingface-gradio` | Build Gradio web UIs and demos in Python |
| Hugging Face Spaces | `huggingface-lora-space-builder` | Build and publish a Gradio Space demo for a user-provided LoRA |
| Hugging Face Spaces | `huggingface-zerogpu` | Write/debug ZeroGPU-constrained Gradio Space code |
| Hugging Face cloud | `hf-cloud-aws-context-discovery` | Discover the user's local AWS context before any AWS work |
| Hugging Face cloud | `hf-cloud-python-env-setup` | Set up an isolated Python env for SageMaker/AWS work |
| Hugging Face cloud | `hf-cloud-sagemaker-deployment-planner` | Entry point for planning a SageMaker model deployment |
| Hugging Face cloud | `hf-cloud-sagemaker-iam-preflight` | Ensure a usable SageMaker execution role exists before deploying |
| Hugging Face cloud | `hf-cloud-serving-image-selection` | Pick the right SageMaker serving container image |
| Hugging Face cloud | `hf-cloud-sagemaker-production-defaults` | Create a SageMaker endpoint with autoscaling, alarms, and tagging by default |
| JavaScript | `transformers-js` | Run Hugging Face models directly in JS/TS (browser or Node/Bun/Deno) |
| Project memory | `agents-md-improver` | Audit project rules and propose targeted improvements |
| Project memory | `agents-md-revise` | Capture durable session learnings in project rules |
@@ -376,7 +405,7 @@ Restart OpenCode after installation. One plugin adapts to the host version: Open
The compatibility smoke tests cover OpenCode **1.18.7, 2.0.14, and 2.0.32**. The `SKILL.md` format stays the same across these hosts.
To pin a published release, append its tag to the same spec:
To pin a release, append its tag to the same spec. Choose a release that includes the V2 port when using OpenCode 2; `v0.5.0` predates it:
```bash
opencode plugin add "opencode-power-pack@git+https://github.com/waybarrios/opencode-power-pack.git#<tag>"
+62
View File
@@ -0,0 +1,62 @@
# OpenCode 1 and 2 support
The `main` branch supports OpenCode 2.0 and keeps OpenCode 1.18.7 support. Both hosts load all 55 skills and three feature-development specialists.
## Choose the right source
| Source | Skills | OpenCode plugin | Humanizer |
|---|---|---|---|
| Git `main` | 55 | OpenCode 1 and 2 | Included |
| npm `0.5.0` and tag `v0.5.0` | 54 | OpenCode 1 only | Not included |
The npm selective installer can copy its released skills into `.agents/skills` for OpenCode 2. It does not register the three named specialist agents. Use the Git plugin for the full V2 integration.
## Install the current plugin
OpenCode 2:
```sh
opencode plugin add "opencode-power-pack@git+https://github.com/waybarrios/opencode-power-pack.git"
```
OpenCode 1:
```sh
opencode plugin --global "opencode-power-pack@git+https://github.com/waybarrios/opencode-power-pack.git"
```
Restart OpenCode after installation. Invoke a skill by name, such as `/code-review`, `/feature-dev`, or `/humanizer`.
## Verify the installation
On OpenCode 2, run `opencode debug agents`. The output should include `code-explorer`, `code-architect`, and `code-reviewer` as subagents. Check the skill picker for the 55 workflows.
On OpenCode 1, run `opencode debug skill` and `opencode debug agent code-explorer`.
The three bundled specialists cannot edit files, access the network, or create nested subagents. The reviewer can run a limited set of Git inspection commands. OpenCode 2 enforces these restrictions when it evaluates permission requests, even with permissive global rules. The agent listing can still show the host's base permissions.
A user-defined agent with a different system prompt or primary mode replaces the bundled role and keeps the host's permission defaults. Explicit user denials and approval prompts still apply to bundled agents.
## Update or remove the plugin
Use the exact package specification stored in your configuration.
```sh
# OpenCode 2 update
opencode plugin update "opencode-power-pack@git+https://github.com/waybarrios/opencode-power-pack.git"
# OpenCode 2 removal
opencode plugin remove "opencode-power-pack@git+https://github.com/waybarrios/opencode-power-pack.git"
```
On OpenCode 1, update by reinstalling with `plugin --global`. To remove the plugin, delete its entry from the `plugin` array and restart.
If you installed from a local `git+file://` clone, pull the latest source and then update or reinstall using that same specification. Pulling the clone alone does not refresh the installed package.
## What the checks cover
Smoke tests cover OpenCode 1.18.7, 2.0.14, and 2.0.32. Each host loads 55 skills and three specialists. Both V2 checks load the package directory, read the final catalogs, and test actual permission requests under a global allow rule. They make no model calls.
The behavioral evaluation runner uses the V2 session API. It accepts text only from successful turns and preserves optional `provider/model#variant` model references. Live runs need provider environment credentials because the isolated runtime does not copy OpenCode 2's credential database. See the [evaluation guide](../evals/behavioral/README.md).
The sandbox runner remains a separate npm CLI. It contains a selected command and its descendants on supported macOS and Linux systems. It does not isolate every host tool. See the [sandbox compatibility guide](sandbox-compatibility.md).
+3 -1
View File
@@ -13,7 +13,9 @@ Locally inspected host versions:
The repository smoke tests retain their separately pinned minimum versions. Host APIs evolve, so adapter tests and this matrix must be updated together.
OpenCode plugin compatibility is additionally verified by model-free smoke tests on 1.18.7, 2.0.14, and 2.0.32 (2026-10-19). V2 checks load the real package directory, inspect the final catalogs, and evaluate specialist permission requests with permissive global rules. This checks plugin permissions, not whole-agent sandbox isolation.
The `main` branch passes model-free OpenCode plugin smoke tests on 1.18.7, 2.0.14, and 2.0.32 (2026-10-19). V2 checks load the package directory, inspect the final catalogs, and evaluate specialist permission requests with permissive global rules. These checks cover plugin permissions. They do not test whole-agent sandbox isolation.
Install from Git `main` for the OpenCode 2 plugin. The published npm package and tag `v0.5.0` contain the earlier V1-only plugin. The sandbox runner remains available in npm `0.5.0` and can be called from either OpenCode version.
## Compatibility Levels
+1 -1
View File
@@ -1,7 +1,7 @@
{
"name": "@waybarrios/opencode-power-pack",
"version": "0.5.0",
"description": "Fifty-five software-development workflows for Claude Code, Codex, OpenCode, and Pi: code review, feature development, security review, frontend design, authoring, and project memory.",
"description": "Fifty-five workflows for Claude Code, Codex, OpenCode 1 and 2, and Pi: code review, security, feature development, writing, and project guidance.",
"type": "module",
"main": ".opencode/plugins/opencode-power-pack.js",
"bin": {