claude

maxey0-loops

The Loop plane, alone. Route a task against 16 concepts, 83 skills, 67 agents and 84 hardened loops, and get the formation already built for it instead of an improvised maker/checker pair. Holds no window state at all, so it runs against a fixed context scheme with nothing else installed. 10 tools.

0 on GitHubby mmc7676v0.3.4Apache-2.0updated 1 month agoagents
/

Plugin maxey0-loops from marketplace maxey0 in mmc7676/Maxey0. Commands read from the repo's manifest — 26 days ago.

This plugin runs code on your machine — it starts local MCP servers. The exact commands are listed below; read them before installing.

What it installs

Skills (16)

  • agentic-loops

    Agentic Loops — an architecture concept covering loop, chain, pipeline, scw, partition. Use when the user's task concerns agentic loops, or matches: loop, chain, pipeline, scw, partition, isolation, battery, hardening. Route with loops_route first — this concept's 2 skills and 0 loops are listed in

  • claim-verification

    Claim Verification — a reasoning concept covering claim, provenance, citation, lineage, evidence. Use when the user's task concerns claim verification, or matches: claim, provenance, citation, lineage, evidence, hallucination. Route with loops_route first — this concept's 4 skills and 8 loops are li

  • context-management

    Context Management — an architecture concept covering context, scw, packing, lineage, boundary. Use when the user's task concerns context management, or matches: context, scw, packing, lineage, boundary, token-budget, structured-context-window. Route with loops_route first — this concept's 5 skills

  • evaluation

    Evaluation — an observability concept covering evaluation, score, drift, shadow, benchmark. Use when the user's task concerns evaluation, or matches: evaluation, score, drift, shadow, benchmark, kpi. Route with loops_route first — this concept's 4 skills and 7 loops are listed in reference/, and a c

  • governance

    Governance — a governance concept covering governance, policy, constraint, egress, compliance. Use when the user's task concerns governance, or matches: governance, policy, constraint, egress, compliance, constitution. Route with loops_route first — this concept's 5 skills and 12 loops are listed in

  • infrastructure

    Infrastructure — an architecture concept covering infrastructure, runtime, sandbox, container, execution. Use when the user's task concerns infrastructure, or matches: infrastructure, runtime, sandbox, container, execution, isolation, deploy. Route with loops_route first — this concept's 5 skills an

  • io-contract

    I/O Contract — a protocol concept covering io, contract, schema, endpoint, negotiation. Use when the user's task concerns i/o contract, or matches: io, contract, schema, endpoint, negotiation, api. Route with loops_route first — this concept's 5 skills and 5 loops are listed in reference/, and a coh

  • knowledge-graph

    Knowledge Graph — a knowledge concept covering graph, node, edge, okf, link. Use when the user's task concerns knowledge graph, or matches: graph, node, edge, okf, link, ontology. Route with loops_route first — this concept's 9 skills and 13 loops are listed in reference/, and a coherent hit often n

  • latent

    Latent Space — a research concept covering latent, embedding, anchor, subspace, disclosed-approximation. Use when the user's task concerns latent space, or matches: latent, embedding, anchor, subspace, disclosed-approximation, trilateration, sae. Route with loops_route first — this concept's 9 skill

  • memory

    Memory — an architecture concept covering memory, tier, promotion, lifecycle, consolidation. Use when the user's task concerns memory, or matches: memory, tier, promotion, lifecycle, consolidation, episodic, working, persistent, semantic. Route with loops_route first — this concept's 8 skills and 14

  • observability

    Observability — an observability concept covering observability, trace, telemetry, span, audit. Use when the user's task concerns observability, or matches: observability, trace, telemetry, span, audit, monitor. Route with loops_route first — this concept's 4 skills and 9 loops are listed in referen

  • orchestration

    Orchestration — an architecture concept covering orchestrate, route, delegate, hierarchy, plan. Use when the user's task concerns orchestration, or matches: orchestrate, route, delegate, hierarchy, plan, swarm. Route with loops_route first — this concept's 5 skills and 14 loops are listed in referen

  • protocol

    Protocol — a protocol concept covering protocol, a2a, mcp, handoff, envelope. Use when the user's task concerns protocol, or matches: protocol, a2a, mcp, handoff, envelope, schema. Route with loops_route first — this concept's 4 skills and 5 loops are listed in reference/, and a coherent hit often n

  • reasoning

    Reasoning — a reasoning concept covering reasoning, frame, anchor, context, recursion. Use when the user's task concerns reasoning, or matches: reasoning, frame, anchor, context, recursion, meta. Route with loops_route first — this concept's 8 skills and 17 loops are listed in reference/, and a cohe

  • registry

    Registry — an architecture concept covering registry, agents, roster, capability, repo. Use when the user's task concerns registry, or matches: registry, agents, roster, capability, repo, index. Route with loops_route first — this concept's 1 skills and 0 loops are listed in reference/, and a cohere

  • superposition

    Superposition — an architecture concept covering superposition, tick, mirror, parallel, arbitration. Use when the user's task concerns superposition, or matches: superposition, tick, mirror, parallel, arbitration, shared-state, actor-critic. Route with loops_route first — this concept's 5 skills and

Slash commands (4)

  • /maxey0-loops:crosswindow

    Run a cross-window topology: one separate subagent call per participant, zero shared context

  • /maxey0-loops:doctor

    What is up, what is down, and what is missing — connectors, ledger, Gate, runtime provenance

  • /maxey0-loops:menu

    The Maxey0 control surface — every plane, connector, tool, command and view, rendered from the registry

  • /maxey0-loops:route

    Route a task against the Maxey0 library and report the decision — binds nothing

MCP servers (1)

  • maxey0-loops

    runs: python ${CLAUDE_PLUGIN_ROOT}/server/loops_server.py

View source on GitHub maxey0.com

More from mmc7676/Maxey0

All 5 plugins →

maxey0

claude

Most agent infrastructure primarily adds capability to the execution plane. Maxey0 makes the contextual environment surrounding agentic execution an independently structured, routable, partitionable, and observable plane, while providing an engineering plane that can observe and tune both. The full stack: all three planes, ten slash commands, the role-agent slate, the Gate, and the Studio. Start here unless you know you want one plane.

17 skills · 10 commands · 5 agents · 3 MCP servers · hooks

0

The Context plane, alone. Partition the context window into typed, policy-enforced regions and bind each role to one — the runtime decides what it can read, not the prompt. 32 tools, a hash-chained ledger that replays to an identical window, and four assertions that test containment by attempting a real read. No library, no Gate, no agents.

1 skill · 4 commands · 1 MCP server

0

The Observatory plane, alone. The Gate stands at every tool call, attributes it to the role that made it, and refuses the ones reaching outside that role's declared scope — global workspace semantics for any session, with no window and no library required. 8 tools, a separately chained journal, and the Studio.

2 commands · 1 MCP server · hooks

0

Research tooling, not part of the product. The spec-driven experiment harness: workload specs, conditions, leak probes, and reports. Install this only if you are running a study — nothing in the three planes depends on it.

1 command

0

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

context7

claudecodex

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

upstash/context7 64,709

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

pensyve

claude

Universal memory runtime for Claude Code with cross-session memory, entity-aware recall, lifecycle hooks, skills, commands, and memory-curator agents

7 skills · 7 commands · 2 agents · hooks

wshobson/agents 42,461

Maintain maxey0-loops?

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.

claude & codex plugins5 plugins