A domain-agnostic agent-team scaffold and plugin-spec reference library, built around the Planner → Generator → Evaluator loop. Reusable role agents, a reference workflow, and a runnable minimal example of every plugin primitive (hooks, rules-via-hook, MCP, LSP, output styles, monitors, PATH binaries, userConfig). Local-first; deploys headless to Claude Managed Agents via scripts/cma.
Plugin agent-team from marketplace agentx-plugins in agentx-team/claude-plugins. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.
spec-authoringTurn a short request into a sprint contract with binary, testable acceptance criteria. Use when a Planner needs to decompose an ambiguous ask into an implementable spec. Triggers on "write a spec", "plan this feature", "define acceptance criteria", "sprint contract".
adversarial-reviewAdversarially evaluate an output (a plan or a build) to find failures, not confirm success. Use when issuing a PASS/FAIL or APPROVE/REVISE verdict with scored dimensions. Triggers on "evaluate", "review for failures", "challenge this", "issue a verdict", "find what's broken".
loop-statusReport the current state of the Planner → Generator → Evaluator loop — which stage is active, the last verdict, open issues, and what's blocking. Read-only. Triggers on "loop status", "where are we", "what's blocking", "show progress".
/agent-team:startStart here — clarify what you want delivered, then route into the Planner → Generator → Evaluator loop
/agent-team:statusShow the current state of the Planner → Generator → Evaluator loop — active stage, last verdict, blockers
/agent-team:workflows:deliver-featureDeliver one feature end to end — plan, challenge the plan, build, challenge the build, package for sign-off
team-fsruns: npx -y @modelcontextprotocol/server-filesystem ${CLAUDE_PROJECT_DIR}
bash "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/log-agent.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/log-agent.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/validate-push.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/validate-manifest.sh"
pythonA cloud-native software delivery agent team: seven roles across a Build → Ship → Accept → Promote lifecycle, building proto-first ConnectRPC + SolidJS services from the team scaffold, shipping to Kubernetes, accepting black-box via live URLs, and promoting with cited market material. Follows the agent-team-scaffold reference layout.
45 skills · 8 commands · 1 MCP server · hooks
Bind a Claude Code session to an IM chat room (Matrix / WeChat via AgentX bots): push long-task results to the room on turn end, receive room replies into the session.
1 command · 1 MCP server · hooks
Start-from-scratch session utilities: /scratch:fresh rescans ~/.claude (skills, plugins, agents, commands, MCP) so a new session knows everything available and clones the target project into ./projects/<name>; /scratch:takeover absorbs another directory's session history, moves its files here, and continues the work.
2 commands · hooks
Push Claude Code notifications (turn results, human-in-the-loop alerts) to a shared IM chat room via an AgentX bot. Outbound-only, zero LLM tokens, no Node.js.
1 command · hooks
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
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.