claude

harness-plugin

A collection of harness configuration guide skills (how Claude Code works, settings scopes, hooks, rules, commands, workflows, memory)

0 on GitHubby cawcaw253MITupdated 2 months agosecurity
/

Plugin harness-plugin from marketplace cawcaw253-plugins in cawcaw253/claude-plugins. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (7)

  • agent-memory

    Guides you through Claude Code's auto memory and MEMORY.md. Covers how it differs from CLAUDE.md, storage location (~/.claude/projects/<project>/memory/), load rules (200 lines/25KB), enabling/disabling, auditing/editing (/memory), and the autoMemoryDirectory/autoMemoryEnabled settings. Use when the

  • agentic-loop

    Explains how Claude Code works internally (agentic loop, tools, context window, sessions, checkpoints/permissions). A foundational skill that helps you understand "where you can intervene" before building a harness. Use when the user asks about "how Claude Code works", "agent loop", "agentic loop",

  • harness-hooks

    Helps configure a harness that constrains AI work scope using Claude Code hooks. Guides hook lifecycle events, matcher/if condition setup, exit code and JSON output control, and the settings.json schema, and writes actual hook scripts. Use when the user asks for things like "block a specific command

  • project-rules

    Explains how to configure project rules and instructions with CLAUDE.md and .claude/rules/. Covers file locations and load order, path-specific rules (paths frontmatter), @import, writing effective instructions, the limitation that "rules are context, not enforcement", and pairing rules with hooks.

  • settings-scopes

    Guides you through the scopes, precedence, file locations, and key options of Claude Code settings (settings.json). Helps you decide which scope harness policies (permissions, hooks, env) should live in. The Managed (organization-level) scope is out of scope for this repo's harness configuration and

  • slash-commands

    Explains how to write and place custom slash commands (= skills). Covers the relationship between .claude/commands and .claude/skills, frontmatter (description, disable-model-invocation, allowed-tools, argument-hint, model, etc.), arguments ($ARGUMENTS/$N), dynamic context injection (!`cmd`), and fi

  • workflows

    Explains Claude Code's dynamic workflows (orchestrating many subagents with a script). Covers when to use a workflow (compared to subagents/skills/agent teams), how to run and approve them, the ultracode keyword, storage locations (.claude/workflows), script structure (meta, agent, pipeline), execut

View source on GitHub

More from cawcaw253/claude-plugins

All 2 plugins →

claude-harness-builder

claude

Interactive wizard that builds a harness in your project (settings.json, CLAUDE.md, hooks, custom commands) with confirm-before-write steps and resume support

0

Similar plugins

CMEM Pro

claude

CMEM Pro for the Claude app - hooks stream tool use to cmem.ai and inject observations into new sessions and agents

3 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

mempalace

claudecodex

AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.

3 skills · 6 commands · 1 MCP server · hooks

MemPalace/mempalace 60,536

cli-anything

claude

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

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

prowler

claude

Connect Claude to Prowler Cloud through the Prowler MCP server. Reads providers, scans, findings, compliance results and resources for AWS, Azure, GCP, Kubernetes, Microsoft 365, GitHub and the other providers listed at https://registry.prowler.com, and returns remediation guidance for failed checks. Writes are limited to Prowler Cloud itself: triggering scans, finding triage, mute rules and the mutelist, providers and integrations. Your cloud resources are not changed by the connector.

1 skill · 1 MCP server

prowler-cloud/prowler 15,234

worktrunk

claudecodex

Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.

2 skills · hooks

max-sixty/worktrunk 12,481

Maintain harness-plugin?

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 plugins2 plugins