onboard
claudeWrites Claude tooling for your repo, a project .mcp.json included; offers plugins, installs only the ones you accept.
11 skills · 5 agents
Reviews Claude's changes against the spec and plan they followed and verifies each finding. Never edits code.
Plugin lens from marketplace apurvbazari-plugins in ApurvBazari/claude-plugins. Commands read from the repo's manifest — 11 days ago.
capabilityInternal. An orchestrator's compatibility check: reports the installed lens version and the capabilities it supports.
engineInternal review core called by /lens:review or an orchestrator. Returns review-findings JSON; writes nothing.
render-reviewInternal. Called by an orchestrator to render a review-findings object as HTML via walkthrough:render.
reviewCheck the current session's changes against the spec and plan they were meant to follow, verify each finding, and write a review document. Use when the user runs /lens:review or asks whether the work matches its spec or plan before it ships. Never edits your code; writes only the review document and
correctnessBuilt-in lens finder. Finds bugs, silent failures, edge cases and security issues in the session diff, confirmed against the source. Read-only.
plan-adherenceBuilt-in lens finder. Checks the session diff against its plan: each step followed or deviated, with a finding per deviation. Read-only.
risk-classifyBuilt-in lens finder. Gives each changed file a risk class (auth, data, money, migration, …) and flags risky files with no test or guard. Read-only.
spec-adherenceBuilt-in lens finder. Checks the session diff against its spec: met, partial or missing per item, plus scope creep. Read-only.
test-gapsBuilt-in lens finder. Flags new or changed code paths in the session diff that no test covers. Read-only.
verifierAdversarial skeptic for the lens VERIFY stage. Tries to refute ONE candidate finding against the real source. May run inspection commands such as git diff, grep, or the project's typecheck/tests; never edits.
Writes Claude tooling for your repo, a project .mcp.json included; offers plugins, installs only the ones you accept.
11 skills · 5 agents
Turns a session, plugin or codebase into one interactive HTML page that loads nothing from the network.
4 skills · 2 agents
Saves where a session left off and offers it at the next start. Nothing runs until you choose what to do.
4 skills · hooks
Desktop notifications on macOS and Linux when Claude finishes or needs you, with repo, branch and a cooldown.
4 skills
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives
1 command
Use Alibaba Open Code Review from local Codex.
2 skills
Investigate incidents, review code and execute UAT for release readiness, scan code for vulnerabilities, and run penetration tests with AWS DevOps Agent and AWS Security Agent.
13 skills · 9 commands · 1 MCP server
Your AI development teammate. Turns a story file into a shipped, reviewed, and tested feature via orchestrator → architect → developer → PR reviewer → QA → Playwright.
1 skill · 2 commands · 6 agents
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.