claude

maxey0-context

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.

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

Plugin maxey0-context 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 (1)

  • scw

    Make Structured Context Windows the default way multi-step and multi-agent work is organized in this project. Use when a task needs several roles, when reference material must not be editable by whatever consumes it, when something must be verified by something that did not produce it, when the cont

Slash commands (4)

  • /maxey0-context:assert

    Test containment by attempting a real read, rather than asserting it from the region graph

  • /maxey0-context:run

    Route a task, bind its partition, dispatch every role, and close out with what the evidence supports

  • /maxey0-context:scw-deploy

    Create the default SCW for the current task and report its address, constitution, child-SCW plan, and observability contract before any governed loop runs

  • /maxey0-context:window

    Inspect or partition this session's Structured Context Window — regions, scopes, bridges, disjointness, and the audit chain

MCP servers (1)

  • maxey0-context

    runs: python ${CLAUDE_PLUGIN_ROOT}/server/context_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 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.

16 skills · 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

agent-teams

claudecodex

Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams

6 skills · 7 commands · 4 agents

wshobson/agents 42,461

Maintain maxey0-context?

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