By kagura-ai
Memory-grounded PLAN-layer skill over Claude Code + Kagura Memory — turns an idea into a recallable, memory-grounded plan doc.
Memory-grounded PLAN-layer CLI over Claude Code + Kagura Memory.
# 1. copy the template (your real config is gitignored, never committed)
cp repo.yaml.example repo.yaml
# 2. edit repo.yaml with your own values:
# memory_cloud_url, workspace_id, context_id
# 3. authenticate the Kagura Memory client (OAuth profile), or set KAGURA_API_KEY
kagura auth login
# 4. verify the dependency chain
kagura-planner doctor
repo.yaml is gitignored so your real workspace_id / context_id stay out of
version control. Point any command at an alternate config with -c/--config
(e.g. kagura-planner plan "..." -c ~/.kagura/planner.yaml).
kagura-planner also ships as a Claude Code plugin (a kagura-planner:plan skill)
that drives the CLI from inside a session.
# 1. add this repo as a marketplace
/plugin marketplace add kagura-ai/kagura-planner
# 2. install the plugin
/plugin install kagura-planner@kagura-planner
# 3. ensure the CLI is installed (the skill shells out to it)
uv tool install kagura-planner # or: pipx install kagura-planner
Then ask Claude to plan an idea — the kagura-planner:plan skill recalls related
past work, produces a memory-grounded plan doc, and remembers it. The skill reads
the CLI's JSON envelope (plan --envelope); it never reimplements planning logic.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimKagura Memory Cloud plugin — session management, memory recall/save, and setup tools
Autonomous coding harness over Claude Code + Kagura Memory — thin skill wrapper around the kagura-engineer CLI (init / doctor / setup / run / review / eval). A Tier-2 Harness: it mutates the repo, creates PRs, spends model budget, and gates on HITL. Skills shell out to the installed CLI; no harness logic is reimplemented.
Cost-free, Ollama-first code-review agent for Claude Code — reviews a git diff in-repo via a multi-angle finder/verify harness and returns a structured, machine-readable report.
npx claudepluginhub kagura-ai/kagura-planner --plugin kagura-plannerReliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,561 supported skills.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.