By hmbown
Anti-slop harness for keeping LLMs on-task with contracts, evidence, dialectics, verification, and policy evolution.
Run benchmark suites and manage policy evolution — create challengers, compare against champions, promote or rollback policies.
Examine Autodialectics run results, manifests, and stored artifacts. Use after a pipeline run completes or to review past runs.
Re-run a stored Autodialectics pipeline run, optionally with a different policy, to compare outcomes or debug regressions.
Compile and execute an Autodialectics anti-slop pipeline for a task. Covers health checks, runtime init, contract compilation, and full pipeline execution.
Canonical bundle repo for the hunter-bown-marketplace plugin pack.
This repo vendors a curated set of plugin payloads from their upstream source repos and exposes them from one marketplace root for Claude Code and Codex, plus a matching OpenCode MCP configuration shape.
| Plugin | Version | Description |
|---|---|---|
| autodialectics | 0.1.0 | Anti-slop harness with contracts, evidence, dialectics, verification, and policy evolution |
| aleph | 0.9.4 | External memory workflow for large local data — search, peek, compute, and recurse |
| dust | 0.1.1 | Branchable local-first SQL with repo-native MCP access |
.agents/plugins/marketplace.json.claude-plugin/marketplace.jsonplugins/Canonical marketplace name: hunter-bown-marketplace
Each plugin directory contains its own client-specific manifest (.codex-plugin
and/or .claude-plugin) plus the shared skills/, agents/, .mcp.json,
and launcher scripts consumed by both hosts.
Current vendored upstreams:
plugins/autodialectics ← /Volumes/VIXinSSD/autodialectics/plugins/autodialecticsplugins/aleph ← /Volumes/VIXinSSD/aleph/plugins/alephplugins/dust ← /Volumes/VIXinSSD/dust/plugins/dust# Add the marketplace
/plugin marketplace add Hmbown/plugins
# Install a plugin
/plugin install autodialectics@hunter-bown-marketplace
/plugin install aleph@hunter-bown-marketplace
/plugin install dust@hunter-bown-marketplace
Or load directly for a single session:
claude --plugin-dir ./plugins/autodialectics
claude --plugin-dir ./plugins/aleph
claude --plugin-dir ./plugins/dust
Codex reads .agents/plugins/marketplace.json
for the same hunter-bown-marketplace bundle. Each vendored plugin also keeps a
.codex-plugin/plugin.json manifest inside its own directory.
Add the marketplace via Codex plugin settings or point Codex at this repo root as a local marketplace checkout.
OpenCode does not consume Codex or Claude marketplace manifests directly. Use the same vendored payloads as the source of truth and map MCP entries to the shared launchers in this repo:
aleph via /Users/hunterbown/.local/bin/alephautodialectics via plugins/autodialectics/scripts/run-autodialectics-mcp.shdust via plugins/dust/scripts/run-dust-mcp.shuv plus the checkout at /Volumes/VIXinSSD/autodialecticspip install "aleph-rlm[mcp]" (Python >= 3.11)/Volumes/VIXinSSD/dust with either a local
target/debug or target/release binary, or a working Rust/Cargo toolchain
so the launcher can fall back to cargo run -p dust-cli -- mcpUses 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.
npx claudepluginhub hmbown/plugins --plugin autodialecticsMCP server for recursive LLM reasoning over large local data. Load files, repos, and logs into external memory, then search, peek, run code, and recurse without consuming the context window.
Recursive Language Model MCP server for large local data. Keep files, repos, logs, and documents in external memory; search, peek, compute, and recurse without dumping whole contexts into the prompt.
Branchable local-first SQL with repo-native MCP access.
Developer tools for maintaining Claude Code plugins. Upgrade skills, audit structure, and align with latest platform capabilities.
Ultimate plugin management toolkit with 4 auto-invoked Skills for creating, validating, auditing, and versioning plugins in the claude-code-plugins marketplace
Comprehensive toolkit for developing Claude Code plugins. Includes 10 expert skills covering hooks, MCP integration, LSP servers, commands, agents, marketplaces, and best practices, plus a guide skill for navigation. AI-assisted plugin creation and validation.
Automatic discovery of skills, plugins, and MCP servers across 17 sources
Meta-cognitive tools for Claude Code self-improvement. Learn from feedback, optimize configuration, and evolve your AI development workflow.
Complete plugin development toolkit for creating, refactoring, and validating Claude Code plugins and agents. Use when creating new plugins/skills/agents, refactoring existing plugins/skills, validating frontmatter, or restructuring plugin components. Includes specialized agents for assessment, planning, execution, and validation workflows.