chore: add Apache-2.0 license, contributing, code of conduct and data-handling docs, CI and release workflows

.claude-plugin/marketplace.json

@@ -1,7 +1,11 @@
 {
   "name": "datasqrl",
   "description": "Build DataSQRL data pipelines from your coding agent, using the Dockerized DataSQRL Code Agent.",
-  "owner": { "name": "DataSQRL" },
+  "owner": {
+    "name": "DataSQRL",
+    "email": "contact@datasqrl.com",
+    "url": "https://datasqrl.com"
+  },
   "plugins": [
     {
       "name": "datasqrl",

.claude-plugin/plugin.json

@@ -1,7 +1,22 @@
 {
   "name": "datasqrl",
-  "version": "0.2.0",
+  "displayName": "DataSQRL",
+  "version": "0.3.0",
   "description": "Plan and implement DataSQRL data pipelines with the Dockerized DataSQRL Code Agent.",
-  "author": { "name": "DataSQRL" },
-  "homepage": "https://datasqrl.com"
+  "author": {
+    "name": "DataSQRL",
+    "email": "contact@datasqrl.com",
+    "url": "https://datasqrl.com"
+  },
+  "homepage": "https://datasqrl.com",
+  "repository": "https://github.com/DataSQRL/datasqrl-plugin",
+  "license": "Apache-2.0",
+  "keywords": [
+    "datasqrl",
+    "sqrl",
+    "data-pipelines",
+    "streaming",
+    "flink",
+    "graphql"
+  ]
 }

.codex-plugin/plugin.json

@@ -1,6 +1,40 @@
 {
   "name": "datasqrl",
-  "version": "0.2.0",
+  "version": "0.3.0",
   "description": "Plan and implement DataSQRL data pipelines with the Dockerized DataSQRL Code Agent.",
-  "skills": "./skills/"
+  "author": {
+    "name": "DataSQRL",
+    "email": "contact@datasqrl.com",
+    "url": "https://datasqrl.com"
+  },
+  "homepage": "https://datasqrl.com",
+  "repository": "https://github.com/DataSQRL/datasqrl-plugin",
+  "license": "Apache-2.0",
+  "keywords": [
+    "datasqrl",
+    "sqrl",
+    "data-pipelines",
+    "streaming",
+    "flink",
+    "graphql"
+  ],
+  "skills": "./skills/",
+  "interface": {
+    "displayName": "DataSQRL",
+    "shortDescription": "Plan, build and deploy DataSQRL data pipelines",
+    "longDescription": "Describe a data pipeline in plain English. The plugin turns it into a requirements document, runs the Dockerized DataSQRL Code Agent to plan it, waits for your review, then implements, compiles, tests and verifies it. Small changes to an existing project go straight to a patch run, and finished projects deploy to DataSQRL Cloud.",
+    "developerName": "DataSQRL",
+    "category": "Developer Tools",
+    "capabilities": [
+      "Interactive",
+      "Read",
+      "Write"
+    ],
+    "websiteURL": "https://datasqrl.com",
+    "defaultPrompt": [
+      "I want a pipeline that ingests our order events and reports daily revenue.",
+      "Plan a DataSQRL pipeline from my requirements document.",
+      "Is my DataSQRL run still going?"
+    ]
+  }
 }

.cursor-plugin/plugin.json

@@ -1,6 +1,21 @@
 {
   "name": "datasqrl",
-  "version": "0.2.0",
+  "version": "0.3.0",
   "description": "Plan and implement DataSQRL data pipelines with the Dockerized DataSQRL Code Agent.",
-  "author": { "name": "DataSQRL" }
+  "author": {
+    "name": "DataSQRL",
+    "email": "contact@datasqrl.com"
+  },
+  "homepage": "https://datasqrl.com",
+  "repository": "https://github.com/DataSQRL/datasqrl-plugin",
+  "license": "Apache-2.0",
+  "keywords": [
+    "datasqrl",
+    "sqrl",
+    "data-pipelines",
+    "streaming",
+    "flink",
+    "graphql"
+  ],
+  "skills": "./skills/"
 }

.github/check-plugin.sh

@@ -0,0 +1,94 @@
+#!/bin/bash
+# SPDX-License-Identifier: Apache-2.0
+#
+# Checks that this repository installs as a working plugin. CI runs it on every pull request and
+# before every release; run it locally before opening a pull request.
+#
+# Usage, from the repository root:
+#   .github/check-plugin.sh              # every check
+#   .github/check-plugin.sh --tag 1.2.3  # also require the tag to match the manifest version
+#
+# Needs bash, python3 and, when installed, shellcheck. Without shellcheck the lint step is skipped
+# with a notice; CI always has it.
+
+set -euo pipefail
+
+cd "$(dirname "${BASH_SOURCE[0]}")/.."
+
+TAG=""
+if [ "${1:-}" = "--tag" ]; then
+    TAG="${2:?--tag needs a value such as 1.2.3}"
+fi
+
+failures=0
+fail() {
+    echo "FAIL: $*" >&2
+    failures=$((failures + 1))
+}
+
+# 1. Scripts: real files, executable, valid bash, and clean under shellcheck. A plugin host copies
+#    the plugin into a cache on install, so a symlink would arrive empty and every skill would fail
+#    to find its script.
+scripts=(scripts/datasqrl-agent.sh scripts/datasqrl-cloud.sh install-skills.sh .github/check-plugin.sh)
+for f in "${scripts[@]}"; do
+    if [ ! -e "$f" ]; then fail "$f is missing"; continue; fi
+    [ -L "$f" ] && fail "$f is a symlink; it must be a real file"
+    [ -x "$f" ] || fail "$f is not executable (git update-index --chmod=+x $f)"
+    bash -n "$f" || fail "$f is not valid bash"
+done
+if command -v shellcheck >/dev/null 2>&1; then
+    shellcheck -S error "${scripts[@]}" || fail "shellcheck reported errors"
+else
+    echo "NOTICE: shellcheck is not installed; skipping the lint step." >&2
+fi
+
+# 2. Manifests: each host reads its own, so each must parse, and all must carry one version.
+manifests=(.claude-plugin/marketplace.json .claude-plugin/plugin.json .codex-plugin/plugin.json .cursor-plugin/plugin.json)
+for m in "${manifests[@]}"; do
+    [ -f "$m" ] || { fail "$m is missing"; continue; }
+    python3 -c 'import json,sys; json.load(open(sys.argv[1]))' "$m" || fail "$m is not valid JSON"
+done
+versions=$(python3 - <<'EOF'
+import json
+for m in (".claude-plugin/plugin.json", ".codex-plugin/plugin.json", ".cursor-plugin/plugin.json"):
+    try:
+        print(m, json.load(open(m)).get("version", "<none>"))
+    except Exception:
+        print(m, "<unreadable>")
+EOF
+)
+VERSION=$(echo "$versions" | awk 'NR==1{print $2}')
+if [ "$(echo "$versions" | awk '{print $2}' | sort -u | wc -l | tr -d ' ')" != "1" ]; then
+    fail "the manifests disagree on the version:"$'\n'"$versions"
+fi
+
+# 3. The Claude manifest keeps the default skills/ scan; a skills key would hide every skill it omits.
+python3 -c 'import json,sys; sys.exit("skills" in json.load(open(".claude-plugin/plugin.json")))' \
+    || fail ".claude-plugin/plugin.json declares a skills key, which hides every skill it does not list"
+
+# 4. Skills: every directory has a SKILL.md whose name matches the directory.
+shopt -s nullglob
+skill_dirs=(skills/*/)
+[ "${#skill_dirs[@]}" -ge 1 ] || fail "no skills found under skills/"
+for d in "${skill_dirs[@]}"; do
+    s=$(basename "$d")
+    if [ ! -f "$d/SKILL.md" ]; then fail "skills/$s/SKILL.md is missing"; continue; fi
+    grep -qx "name: $s" "$d/SKILL.md" || fail "skills/$s/SKILL.md has no 'name: $s' line"
+done
+
+# 5. Skills reach users exactly as written, so maintainer notes belong in CONTRIBUTING.md. An HTML
+#    comment is invisible when rendered but is read by the agent as plain text.
+if grep -rn '<!--' skills/; then
+    fail "an HTML comment is in skills/; move maintainer notes to CONTRIBUTING.md"
+fi
+
+# 6. Release only: the tag is the manifest version, plain SemVer with no "v" prefix.
+if [ -n "$TAG" ] && [ "$TAG" != "$VERSION" ]; then
+    fail "tag $TAG does not match the manifest version $VERSION (expected $VERSION)"
+fi
+
+if [ "$failures" -gt 0 ]; then
+    echo "$failures check(s) failed." >&2
+    exit 1
+fi
+echo "All checks passed (version $VERSION, ${#skill_dirs[@]} skills)."

.github/pull_request_template.md

@@ -0,0 +1,24 @@
+## What does this change?
+
+<!-- One or two sentences. Link the issue it fixes, e.g. "Fixes #12". -->
+
+## Area
+
+- [ ] Skills
+- [ ] Launcher (`scripts/datasqrl-agent.sh`)
+- [ ] Cloud client (`scripts/datasqrl-cloud.sh`)
+- [ ] Manifests
+- [ ] CI
+- [ ] Docs
+
+## How did you test it?
+
+<!-- For example: installed from your clone in Claude Code and ran the plan skill on a sample project. -->
+
+## Checklist
+
+- [ ] The PR title starts with a type such as `feat:`, `fix:` or `docs:`
+- [ ] `.github/check-plugin.sh` passes
+- [ ] Skills contain no SQRL and no HTML comments
+- [ ] A launcher change that needs a new agent image option waits until that image is published
+- [ ] README or DATA_HANDLING.md is updated if behavior or data handling changed

.github/workflows/ci.yml

@@ -0,0 +1,20 @@
+name: CI
+
+on:
+  pull_request:
+  push:
+    branches: [main]
+
+permissions:
+  contents: read
+
+jobs:
+  # The DataSQRL organization ruleset requires a status check named "build" on main.
+  build:
+    name: build
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    steps:
+      - uses: actions/checkout@v4
+      # ubuntu-latest ships shellcheck, so the lint step always runs here.
+      - run: .github/check-plugin.sh

.github/workflows/lint-pr-title.yml

@@ -0,0 +1,28 @@
+name: Lint PR Title
+
+on:
+  pull_request_target:
+    types: [opened, reopened, edited, synchronize]
+
+jobs:
+  validate:
+    runs-on: ubuntu-slim
+    permissions:
+      pull-requests: read
+    if: github.actor != 'dependabot[bot]'
+    steps:
+      - uses: amannn/action-semantic-pull-request@v6
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          types: |
+            feat
+            fix
+            chore
+            test
+            docs
+            refactor
+            ci
+            build
+            perf
+            revert

.github/workflows/release.yml

@@ -0,0 +1,36 @@
+name: Release
+
+# Runs when a release is published on the GitHub Releases page. It checks the plugin, confirms the
+# release tag is the manifest version, and attaches both scripts, so that
+#   https://github.com/DataSQRL/datasqrl-plugin/releases/latest/download/datasqrl-agent.sh
+# always serves the launcher of the newest release.
+
+on:
+  release:
+    types: [published]
+
+permissions:
+  contents: write
+
+jobs:
+  release:
+    name: Attach scripts to the release
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.release.tag_name }}
+
+      - name: Check the plugin and the tag
+        env:
+          TAG: ${{ github.event.release.tag_name }}
+        run: .github/check-plugin.sh --tag "$TAG"
+
+      - name: Attach the scripts
+        env:
+          GH_TOKEN: ${{ github.token }}
+          TAG: ${{ github.event.release.tag_name }}
+        run: |
+          gh release upload "$TAG" \
+            scripts/datasqrl-agent.sh scripts/datasqrl-cloud.sh --clobber

CODE_OF_CONDUCT.md

@@ -0,0 +1,83 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our community a harassment-free experience for everyone, regardless of age, body size, visible or invisible disability, ethnicity, sex characteristics, gender identity and expression, level of experience, education, socio-economic status, nationality, personal appearance, race, caste, color, religion, or sexual identity and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming, diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes, and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of acceptable behavior and will take appropriate and fair corrective action in response to any behavior that they deem inappropriate, threatening, offensive, or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct, and will communicate reasons for moderation decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when an individual is officially representing the community in public spaces. Examples of representing our community include using an official e-mail address, posting via an official social media account, or acting as an appointed representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be reported to the community leaders responsible for enforcement at [community@datasqrl.com](mailto:community@datasqrl.com). All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing clarity around the nature of the violation and an explanation of why the behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No interaction with the people involved, including unsolicited interaction with those enforcing the Code of Conduct, for a specified period of time. This includes avoiding interactions in community spaces as well as external channels like social media. Violating these terms may lead to a temporary or permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public communication with the community for a specified period of time. No public or private interaction with the people involved, including unsolicited interaction with those enforcing the Code of Conduct, is allowed during this period. Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community standards, including sustained inappropriate behavior, harassment of an individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 2.1, available at [https://www.contributor-covenant.org/version/2/1/code_of_conduct.html][v2.1].
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct enforcement ladder][Mozilla CoC].
+
+For answers to common questions about this code of conduct, see the FAQ at [https://www.contributor-covenant.org/faq][FAQ]. Translations are available at [https://www.contributor-covenant.org/translations][translations].
+
+[homepage]: https://www.contributor-covenant.org
+[v2.1]: https://www.contributor-covenant.org/version/2/1/code_of_conduct.html
+[Mozilla CoC]: https://github.com/mozilla/diversity
+[FAQ]: https://www.contributor-covenant.org/faq
+[translations]: https://www.contributor-covenant.org/translations