Onboard a user onto the RDL team's Claude Code setup. Use when the user wants to "set up Claude Code", "set up my .claude", "onboard onto the RDL Claude Code setup", "install the forced-eval hook", or "configure Claude Code for the team". Asks whether to configure a project-local `.claude/` or the user's global `~/.claude/`, then installs the team's `forced-eval-hook.sh` (a UserPromptSubmit hook that surfaces available skills as advisory context) and wires it into the chosen scope's `settings.json` idempotently. The minimal first step of RDL Claude Code onboarding — later passes will guide the wider settings surface.
Create a new service desk issue from available templates. Use when creating GitHub issues for the RDL Service Desk repository with data request, enquiry, or ICT request templates.
Curated reusable agent skills and agents packaged as Claude Code plugins. Each subject (a tool, library, language, or workflow) is one plugin: skills are invoked as /<subject>:<facet> (e.g. /go:secure, /gh:send-pr) and agents are delegated as subagents. Canonical skills live under skills/ and agents under agents/; each subject is published as a self-contained plugin under plugins/, listed in the repo-root marketplace manifest (.claude-plugin/marketplace.json).
Claude Code is the only publication target.
# Add the marketplace (once)
/plugin marketplace add nq-rdl/agent-extensions
# Install a single subject
/plugin install go@rdl-agent-extensions
# Onboarding: install the rdl-team plugin
/plugin install rdl-team@rdl-agent-extensions
See docs/bundles.md for the full subject list.
This repo keeps a single source of truth for top-level agent context files:
AGENTS.md — single source of truth for agent contributor guidance.CLAUDE.md → symlink to AGENTS.md. Claude Code loads CLAUDE.md as project context; symlinking keeps the two in sync.This repo is scope-licensed (not an OR dual-license — the license depends on the file, not the user's choice):
SPDX-License-Identifier: MIT. Full text: LICENSE.SPDX-License-Identifier: CC-BY-4.0. Full text: LICENSE-CC-BY-4.0.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.
R — language expertise, package development, CLI apps, CRAN, lifecycle, async, and testing
Go — idiomatic naming and secure error handling
Shiny — modern dashboards with bslib and Bootstrap 5 theming
Writerside — author and build JetBrains Writerside documentation
Defuddle — extract clean Markdown from cluttered web pages
npx claudepluginhub nq-rdl/agent-extensions --plugin rdl-teamHarness-native ECC operator layer - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
AI-powered development tools for code review, research, design, and workflow automation.