diff --git a/README.md b/README.md index 6ec4e04..de11a2c 100644 --- a/README.md +++ b/README.md @@ -8,7 +8,11 @@

+<<<<<<< HEAD License: MIT and Apache-2.0 +======= + License: MIT and Apache-2.0 +>>>>>>> origin/main GitHub stars Last commit GitHub issues @@ -24,7 +28,16 @@ Credits

+<<<<<<< HEAD ## Why This Exists +======= +

+ Built on top of anthropics/claude-plugins-official, + anthropics/skills, + anthropics/claude-code-security-review, + and obra/superpowers. See Acknowledgments. +

+>>>>>>> origin/main OpenCode reads `SKILL.md` natively, but many valuable Claude Code workflows originated as Claude-specific commands and agents. Copying those artifacts directly does not preserve their orchestration, permissions, or subagent behavior. @@ -48,7 +61,68 @@ It complements [obra/superpowers](https://github.com/obra/superpowers), which pr | Project memory | `agents-md-improver` | Audit project rules and propose targeted improvements | | Project memory | `agents-md-revise` | Capture durable session learnings in project rules | +<<<<<<< HEAD `code-explorer`, `code-architect`, and `code-reviewer` are available both as standalone skills and as least-privilege subagents used by `feature-dev`. +======= +--- + +## What's inside + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
CategorySkillSourcePurpose
Reviewcode-reviewadapted · claude-plugins-official/code-reviewMulti-agent PR review with confidence-filtered cross-checks and reproduction scenarios
security-reviewadapted · claude-code-security-reviewOWASP-bucketed, three-stage filtering, requires concrete attack PoC per finding
Feature devfeature-devported · claude-plugins-official/feature-devSeven-phase guided workflow: discovery → exploration → questions → architecture → impl → review → summary
code-explorerported · claude-plugins-official/feature-devDeep codebase analysis sub-task — traces a feature end-to-end
code-architectported · claude-plugins-official/feature-devDecisive architecture blueprint sub-task with file-level implementation map
code-reviewerported · claude-plugins-official/feature-devTwo-pass adversarial review sub-task with explicit edge-case checklist
Designfrontend-designadapted · claude-plugins-official/frontend-designDistinctive, production-grade UI generation that avoids generic AI aesthetics
Authoringmcp-builderadapted · anthropics/skills/mcp-builderBuild high-quality MCP servers (Python or TypeScript)
skill-creatoradapted · skills/skill-creatorAuthor new SKILL.md files with progressive-disclosure structure
Project memoryagents-md-improveradapted · plugins/claude-md-managementAudit and update AGENTS.md / CLAUDE.md against the current codebase
agents-md-revisetranslated · claude-md-management/commandsCapture session learnings into project rules — complement to improver
+ +--- +>>>>>>> origin/main ## Installation @@ -71,7 +145,17 @@ To pin a published release, append its tag: opencode plugin --global "opencode-power-pack@git+https://github.com/waybarrios/opencode-power-pack.git#" ``` +<<<<<<< HEAD ### Install From A Local Clone +======= +To pin a specific published tag: + +```jsonc +"opencode-power-pack@git+https://github.com/waybarrios/opencode-power-pack.git#" +``` + +You still need a local copy of the repo for **step 2** (the slash command files live there). Clone it next to wherever you keep code: +>>>>>>> origin/main ```bash git clone https://github.com/waybarrios/opencode-power-pack.git ~/code/opencode-power-pack @@ -97,7 +181,13 @@ For a GitHub installation: opencode plugin --global --force "opencode-power-pack@git+https://github.com/waybarrios/opencode-power-pack.git" ``` +<<<<<<< HEAD Restart OpenCode after the command finishes. For a pinned installation, update the tag first. Local-clone users should run `git pull` in the clone and reinstall with the same `git+file://` spec. +======= +If you pinned a version in `opencode.json`, bump the tag in the JSON before restarting, otherwise OpenCode keeps using the pinned commit. + +--- +>>>>>>> origin/main ## Uninstalling @@ -171,10 +261,19 @@ The packaged agents deny edits, external network access, and nested tasks. `code | In scope | Out of scope | |---|---| +<<<<<<< HEAD | Portable Claude Code workflow methodology | Claude Code hook contracts | | OpenCode-native skills, commands, and subagents | Proprietary or non-redistributable plugins | | Licensed adaptations with immutable provenance | Automatic trust of third-party skill catalogs | | Explicit permission boundaries and regression tests | Supporting OpenCode versions older than 1.18.7 | +======= +| Porting Claude Code skills where the methodology is portable | Claude Code slash commands ported as Claude-Code-style commands | +| Translating commands and agents into SKILL.md format | Claude Code hooks | +| Licensed adaptations of upstream skills with immutable provenance | Claude Code output styles | +| OpenCode-native slash commands generated from skills | Anything that breaks if you also use Claude Code | + +--- +>>>>>>> origin/main ## Contributing @@ -205,10 +304,15 @@ Every skill must use a lowercase hyphenated directory/name, provide a trigger-sp ## Acknowledgments +<<<<<<< HEAD The bundled skills are modified upstream works. This repository contributes their OpenCode adaptation, packaging, additional workflow guidance, tests, and compatibility layer. +======= +**The bundled skills are modified upstream works.** Most content in `skills/` is adapted from skills, commands, or agent definitions written by **Anthropic**, plus an adaptation of the OpenCode plugin pattern from **Jesse Vincent (obra)**. This repository contributes the OpenCode port, packaging, and additional workflow guidance. Exact sources and Git blobs are recorded in [`UPSTREAMS.json`](UPSTREAMS.json). +>>>>>>> origin/main | Upstream | Pinned source | Used for | |---|---|---| +<<<<<<< HEAD | Anthropic | [`claude-plugins-official@bdca23e8`](https://github.com/anthropics/claude-plugins-official/tree/bdca23e8e46f8832d0030c05804ae207786ae37f) | Code review, feature development, frontend design, and project memory | | Anthropic | [`skills@5128e186`](https://github.com/anthropics/skills/tree/5128e1865d670f5d6c9cef000e6dfc4e951fb5b9) | MCP Builder and Skill Creator | | Anthropic | [`claude-code-security-review@0c6a49f1`](https://github.com/anthropics/claude-code-security-review/tree/0c6a49f1fa56a1d472575da86a94dbc1edb78eda) | Security Review | @@ -219,3 +323,28 @@ See [`UPSTREAMS.json`](UPSTREAMS.json) for exact source paths and Git blobs. See ## License The wrapper code and original project material are MIT-licensed under [LICENSE](LICENSE). Modified skills derived from Anthropic's official plugins and skills are Apache-2.0, except `security-review`, whose upstream is MIT. See [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md), [UPSTREAMS.json](UPSTREAMS.json), and [LICENSES/](LICENSES/) for exact terms. +======= +| Anthropic | [`claude-plugins-official/code-review`](https://github.com/anthropics/claude-plugins-official/tree/bdca23e8e46f8832d0030c05804ae207786ae37f/plugins/code-review) | The confidence-filtered parallel-review methodology adapted as `code-review` | +| Anthropic | [`claude-plugins-official/feature-dev`](https://github.com/anthropics/claude-plugins-official/tree/bdca23e8e46f8832d0030c05804ae207786ae37f/plugins/feature-dev) | The seven-phase workflow and three specialist roles | +| Anthropic | [`claude-plugins-official/frontend-design`](https://github.com/anthropics/claude-plugins-official/tree/bdca23e8e46f8832d0030c05804ae207786ae37f/plugins/frontend-design) | The base `frontend-design` methodology, substantially extended here | +| Anthropic | [`claude-code-security-review`](https://github.com/anthropics/claude-code-security-review/tree/0c6a49f1fa56a1d472575da86a94dbc1edb78eda) | The MIT security-review command, translated and extended | +| Anthropic | [`anthropics/skills/mcp-builder`](https://github.com/anthropics/skills/tree/5128e1865d670f5d6c9cef000e6dfc4e951fb5b9/skills/mcp-builder) | The base `mcp-builder` workflow, adapted without its original resources | +| Anthropic | [`anthropics/skills/skill-creator`](https://github.com/anthropics/skills/tree/5128e1865d670f5d6c9cef000e6dfc4e951fb5b9/skills/skill-creator) | The `skill-creator` workflow, adapted without its original eval tooling | +| Anthropic | [`claude-plugins-official/claude-md-management`](https://github.com/anthropics/claude-plugins-official/tree/bdca23e8e46f8832d0030c05804ae207786ae37f/plugins/claude-md-management) | The base project-memory workflows, expanded to cover AGENTS.md | +| Jesse Vincent (obra) | [`obra/superpowers`](https://github.com/obra/superpowers) | The OpenCode plugin pattern (`config.skills.paths.push(...)`) used in `.opencode/plugins/opencode-power-pack.js` | + +### What this repo actually contributes + +- The translation of Claude-Code-only artifacts (commands and agents) into the SKILL.md format OpenCode reads natively +- Renaming and adapting `claude-md-improver` / `revise-claude-md` to cover both `AGENTS.md` (OpenCode-native) and `CLAUDE.md` (compatibility) +- Deepening the review skills (`code-review`, `code-reviewer`, `security-review`) with extra reviewers, multi-pass adversarial analysis, mandatory category coverage, and concrete-PoC requirements — the originals were already strong; the ports try to compensate for the smaller models people sometimes run under OpenCode by being more directive +- Bundling everything as a one-line OpenCode plugin, plus generating physical slash command files that inline each skill's full content + +Each `SKILL.md` and generated command marks itself as modified and names its license. See [`THIRD_PARTY_NOTICES.md`](THIRD_PARTY_NOTICES.md) for attribution and `UPSTREAMS.json` for immutable provenance. + +If you are one of the upstream authors and you'd like the attribution worded differently — or removed — open an issue and we'll fix it. + +## License + +The wrapper code and original project material are MIT-licensed under [LICENSE](LICENSE). Modified skills and command prompts derived from Anthropic's official plugins and skills are Apache-2.0, except `security-review`, whose upstream is MIT. See [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md), [UPSTREAMS.json](UPSTREAMS.json), and [LICENSES/](LICENSES/) for exact terms and sources. +>>>>>>> origin/main diff --git a/THIRD_PARTY_NOTICES.md b/THIRD_PARTY_NOTICES.md index 34d1201..a6fde65 100644 --- a/THIRD_PARTY_NOTICES.md +++ b/THIRD_PARTY_NOTICES.md @@ -4,10 +4,17 @@ The repository wrapper, plugin integration, packaging, tests, and original documentation are licensed under the root MIT `LICENSE` unless a file states otherwise. +<<<<<<< HEAD The skills are modified derivatives of the sources recorded in `UPSTREAMS.json`. They are not represented as original work. Every entry records the immutable upstream commit, source path, Git blob, license, and adaptation type reviewed for this distribution. +======= +The skills and generated command prompts are modified derivatives of the +sources recorded in `UPSTREAMS.json`. They are not represented as original +work. Every entry records the immutable upstream commit, source path, Git blob, +license, and adaptation type reviewed for this distribution. +>>>>>>> origin/main ## Anthropic Official Plugins