kagura-engineer
SolidAutonomous coding harness over Claude Code + Kagura Memory. Ships a doctor (dependency-chain diagnostics) and setup (one-command environment bootstrap) CLI; task pipeline in progress.
Install
Plugins install via a marketplace, in two steps.
This plugin isn't listed in a marketplace we've indexed. Install it directly from its GitHub repository — the README has the setup steps.
View on GitHubBundles
Everything this plugin ships — skills, agents, commands, hooks, and MCP servers it bundles.
Skills (7)
doctor
Use before any kagura-engineer run/review/goal, or when the harness reports a blocked environment — diagnoses the local setup (git, claude, gh, ollama, memory backend, gh-issue-driven plugin) by shelling out to `kagura-engineer doctor` and reports what must be fixed.
eval
Use to measure whether memory grounding actually improves PR quality — shells out to `kagura-engineer eval <issues...>`, running the SAME fixed issue set in two arms (recall ON vs OFF) and printing an A/B table. HARNESS — high cost; it runs the full loop twice per issue and mutates the repo. Confirm with the user before launching.
goal
Use to drive every open issue in a GitHub milestone to a pull request with the kagura-engineer harness — shells out to `kagura-engineer goal <milestone>`, running each issue through the run loop. HARNESS — high cost; it mutates the repo and creates multiple PRs. Confirm with the user before launching.
init
Use to bootstrap a fresh checkout for the kagura-engineer harness — scaffolds a commented repo.yaml template and adds it to .gitignore by shelling out to `kagura-engineer init`. Run this before setup/run/review/goal when no repo.yaml exists yet. Idempotent and never overwrites.
review
Use to review a git diff, branch, or PR with the cost-free kagura-engineer reviewer — shells out to `kagura-engineer review [target]`, returning a structured verdict and findings. With `--fix` it is a HARNESS that edits files and commits; without `--fix` it is read-only.
run
Use to drive a single GitHub issue to a pull request with the kagura-engineer harness — shells out to `kagura-engineer run <issue>` (guard → recall → worktree → start → implement → ship → persist). HARNESS — this mutates the repo, creates a PR, and spends model budget; confirm with the user before launching.
setup
Use when kagura-engineer:doctor reports a blocked or failing environment — installs and authenticates the harness prerequisites (git, claude, gh, ollama models, memory-cloud auth) by shelling out to `kagura-engineer setup`, then re-checks with doctor.
Quality Score: 71/100
Details
- Author
- kagura-ai
- Repository
- kagura-ai/kagura-engineer
- Created
- 1 months ago
- Last Updated
- 2 days ago
- Language
- Python
- License
- Apache-2.0