Multi-phase code review with auto-maintained project conventions
Run fully autonomous code review in CI — no user interaction required. Performs ephemeral setup if needed, runs all review phases, and posts results to the PR.
Run multi-phase code review on current branch changes
Onboard a project for code review — analyzes codebase and generates reference docs
Read-only code review agent that critiques architecture, correctness, security, API compatibility, and edge cases. Use when dispatching the adversarial review phase. <example> Context: Full review pipeline dispatching all phases user: "/code-reviewer:review" assistant: "I'll dispatch the adversarial-reviewer agent with the full-scope brief." <commentary> The adversarial reviewer gets the full-scope brief covering all review units. </commentary> </example> <example> Context: Single-phase adversarial review user: "/code-reviewer:review:adversarial" assistant: "I'll dispatch the adversarial-reviewer agent for a focused adversarial review." <commentary> Single-phase invocation still runs triage first to build the brief. </commentary> </example>
Read-only code review agent that enforces project style conventions from the generated style guide. Use when dispatching the style review phase. <example> Context: Full review pipeline dispatching all phases user: "/code-reviewer:review" assistant: "I'll dispatch the style-reviewer agent with the unit-scoped brief." <commentary> The style reviewer gets a unit-scoped brief plus the style guide reference doc. </commentary> </example> <example> Context: Single-phase style review user: "/code-reviewer:review:style" assistant: "I'll dispatch the style-reviewer agent for a focused style review." <commentary> Single-phase invocation still runs triage first to build the brief. </commentary> </example>
Read-only code review agent that evaluates test coverage, test quality, and adherence to testing practices. Use when dispatching the testing review phase. <example> Context: Full review pipeline dispatching all phases user: "/code-reviewer:review" assistant: "I'll dispatch the testing-reviewer agent with the unit-scoped brief." <commentary> The testing reviewer gets a unit-scoped brief plus the testing practices reference doc. </commentary> </example> <example> Context: Single-phase testing review user: "/code-reviewer:review:testing" assistant: "I'll dispatch the testing-reviewer agent for a focused testing review." <commentary> Single-phase invocation still runs triage first to build the brief. </commentary> </example>
Use when performing adversarial code review — critiques architecture, correctness, security, API compatibility, edge cases, and YAGNI violations. Receives the full-scope brief across all review units.
Use when merging reports from multiple review subagents into a single consolidated output with deduplication, structured ID assignment, cross-unit findings, and a final verdict.
Use when considering whether review findings or engineer responses suggest the project's living reference docs need updating. Proposes changes explicitly and requires engineer confirmation before writing.
Non-interactive project onboarding for CI environments. Delegates to the setup command logic but auto-accepts all conventions without engineer confirmation.
Use when performing style review — enforces project conventions from the generated style guide. Only flags violations of documented rules, not personal preferences.
Uses power tools
Uses Bash, Write, or Edit tools
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 claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Shared utilities to standardize and simplify build, test, and deployment pipelines for the OSSM team.
This repository is a Claude Code skills marketplace. Team members can install plugins into any project to get AI-powered utilities as slash commands.
Available plugins:
ossm-ci — CI utilities: release confidence scoring, E2E test generation, AWS resource inventory, and Prow CI metricscode-reviewer — Multi-phase code review with auto-maintained project conventionscodebase-scribe — Generate, enrich, and maintain agentic development documentation for any codebasePlugins hosted on GitHub must be added as a marketplace first, then installed individually.
/plugin marketplace add openshift-service-mesh/ci-utils
This registers the repo as a marketplace using the name field from its .claude-plugin/marketplace.json. The marketplace is registered as ci-utils.
/plugin install ossm-ci@ci-utils
/plugin install code-reviewer@ci-utils
/plugin install codebase-scribe@ci-utils
/reload-plugins
What does NOT work
Command Why it fails /plugin install ossm-ci@openshift-service-mesh/ci-utilsThe org/repoformat is not a registered marketplace name/plugin install openshift-service-mesh/ci-utilsTreated as a plugin name, not a marketplace The target GitHub repo must contain
.claude-plugin/marketplace.jsonwith apluginsarray listing available plugins.
/ossm-ci:confidenceCalculates a data-driven release confidence score (1–10) for an OSSM build by analyzing test results from Report Portal. Determines the required test scope (FULL/CORE/BASIC), validates test matrix coverage across platforms and environments, and provides a scored breakdown with a GO/NO-GO release recommendation.
Requires: Report Portal MCP server configured in Claude Code.
/ossm-ci:generate-e2e-testsGenerates production-ready Go E2E tests using BDD Ginkgo from a project's documentation. Validates documentation quality against a scoring threshold (7/10 minimum), extracts hidden tags for retry/timeout/validation logic, and produces organized test files with helpers.
Run from the root of the target project. Copy the config template to get started:
cp <ci-utils>/plugins/ossm-ci/skills/generate-e2e-tests/documentation-e2e-generator.yaml ./documentation-e2e-generator.yaml
/ossm-ci:aws-scanGives you the exact commands to download and run the audited inventory script yourself. The script outputs two tables directly in your terminal: potentially dangling resources and a complete inventory. Claude does not execute anything — you run the script, you see the results.
curl -O https://raw.githubusercontent.com/openshift-service-mesh/ci-utils/main/scripts/aws-scan-audited.sh
bash aws-scan-audited.sh
Requires: AWS CLI configured with valid credentials. See scripts/aws-scan-audited.sh for the full read-only script.
/ossm-ci:prow-metricsCollects and presents Prow CI execution data for OSSM repositories (istio, proxy, sail-operator, ztunnel). Shows summary statistics, median execution times by job type, infrastructure usage, failed/pending jobs, and exports a TSV file for Excel import. Fetches directly from the Prow API — works from any project.
Requires: python3 available in PATH.
/code-reviewer:setupOnboard a project for code review. Analyzes your codebase, discovers existing standards and patterns, and interactively generates reference docs (style guide, testing practices, etc.). Run this once before your first review.
/code-reviewer:reviewRun a multi-phase code review pipeline on your current branch changes. Dispatches three specialized review subagents in parallel (adversarial, style, testing), consolidates findings with deduplication, and produces a verdict.
Supports phase-specific variants:
/code-reviewer:review # Full pipeline — all three phases
/code-reviewer:review:adversarial # Adversarial phase only
/code-reviewer:review:style # Style phase only
/code-reviewer:review:testing # Testing phase only
npx claudepluginhub openshift-service-mesh/ci-utils --plugin code-reviewerOSSM CI utilities: release confidence scoring, E2E test generation, AWS resource inventory, and Prow CI metrics
Generate, enrich, and maintain agentic development documentation for any codebase. Produces AGENTS.md + topic files with progressive disclosure, drift detection, and SME-directed enrichment.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
AI-powered development tools for code review, research, design, and workflow automation.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.