Agent Plugins Marketplace
← All plugins

abstract

v1.9.21

Meta-skills infrastructure for Claude Code plugin ecosystem - skill authoring, hook development, modular design patterns, and evaluation frameworks

Claude Code14 Skills

By Alex TholaLicense: MIT341 GitHub starsUpdated 2 weeks ago

Directory evidence

Runtimes
Claude Code
Parsed components
14 skill or MCP entries
Source updated
Oct 6, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install abstract for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install abstract@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/athola/claude-night-market

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/abstract/.

Plugin files

plugins/abstract/
├── .claude-plugin/plugin.json
├── skills/escalation-governance/SKILL.md
├── skills/friction-detector/SKILL.md
├── skills/hook-authoring/SKILL.md
├── skills/hook-scope-guide/SKILL.md
├── skills/hooks-eval/SKILL.md
├── skills/metacognitive-self-mod/SKILL.md
├── skills/methodology-curator/SKILL.md
├── skills/modular-skills/SKILL.md
├── skills/plugin-review/SKILL.md
├── skills/rules-eval/SKILL.md
├── skills/skill-authoring/SKILL.md
├── skills/skill-graph-audit/SKILL.md
├── skills/skills-eval/SKILL.md
└── skills/subagent-testing/SKILL.md

Included Skills14

escalation-governanceskills/escalation-governance/SKILL.md

Assess whether to escalate models. Use when evaluating reasoning depth.

friction-detectorskills/friction-detector/SKILL.md

Detect friction signals; graduate patterns into rules. Use for session retrospectives.

hook-authoringskills/hook-authoring/SKILL.md

Guide creating Claude Code hooks with security-first design. Use for validation and enforcement.

hook-scope-guideskills/hook-scope-guide/SKILL.md

Select hook scope (plugin, project, global) by audience. Use when authoring a hook.

hooks-evalskills/hooks-eval/SKILL.md

Evaluate hook security, performance, and SDK compliance. Use for audits.

metacognitive-self-modskills/metacognitive-self-mod/SKILL.md

Analyze and improve the improvement process. Use for detecting regressions and meta-optimization.

methodology-curatorskills/methodology-curator/SKILL.md

Surface expert frameworks. Use when creating or evaluating skills, hooks, or agents.

modular-skillsskills/modular-skills/SKILL.md

Build composable skill modules with hub-and-spoke loading. Use when token budget is tight.

plugin-reviewskills/plugin-review/SKILL.md

Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.

rules-evalskills/rules-eval/SKILL.md

Evaluate Claude Code rules in .claude/rules/. Use for frontmatter, globs, and quality audits.

skill-authoringskills/skill-authoring/SKILL.md

Guide creating Claude Code skills with TDD and persuasion principles. Use for new skill development.

skill-graph-auditskills/skill-graph-audit/SKILL.md

Audit Skill() refs; detect hubs, isolates, and dangling targets. Use when auditing skills.

skills-evalskills/skills-eval/SKILL.md

Evaluate Claude skill quality through auditing. Use when reviewing or auditing skills.

subagent-testingskills/subagent-testing/SKILL.md

Test skills via TDD in fresh subagents. Use when validating behavior or preventing bias.

Plugin manifests1

plugins/abstract/.claude-plugin/plugin.json
{
  "name": "abstract",
  "version": "1.9.21",
  "description": "Meta-skills infrastructure for Claude Code plugin ecosystem - skill authoring, hook development, modular design patterns, and evaluation frameworks",
  "commands": [
    "./commands/aggregate-logs.md",
    "./commands/analyze-skill.md",
    "./commands/context-report.md",
    "./commands/create-command.md",
    "./commands/create-hook.md",
    "./commands/create-skill.md",
    "./commands/evaluate-skill.md",
    "./commands/hooks-eval.md",
    "./commands/improve-skills.md",
    "./commands/make-dogfood.md",
    "./commands/plugin-review.md",
    "./commands/promote-discussions.md",
    "./commands/rules-eval.md",
    "./commands/skills-eval.md",
    "./commands/test-skill.md",
    "./commands/validate-hook.md",
    "./commands/validate-plugin.md"
  ],
  "skills": [
    "./skills/escalation-governance",
    "./skills/friction-detector",
    "./skills/hook-authoring",
    "./skills/hook-scope-guide",
    "./skills/hooks-eval",
    "./skills/metacognitive-self-mod",
    "./skills/methodology-curator",
    "./skills/modular-skills",
    "./skills/plugin-review",
    "./skills/rules-eval",
    "./skills/skill-authoring",
    "./skills/skill-graph-audit",
    "./skills/skills-eval",
    "./skills/subagent-testing"
  ],
  "agents": [
    "./agents/meta-architect.md",
    "./agents/plugin-validator.md",
    "./agents/skill-auditor.md",
    "./agents/skill-evaluator.md",
    "./agents/skill-improver.md",
    "./agents/insight-engine.md"
  ],
  "hooks": [],
  "keywords": [
    "meta-skills",
    "infrastructure",
    "patterns",
    "evaluation",
    "modular",
    "framework",
    "agent-sdk",
    "performance",
    "optimization",
    "hooks",
    "scope",
    "authoring",
    "tdd",
    "validation",
    "security",
    "bulletproofing",
    "persuasion"
  ],
  "author": {
    "name": "Alex Thola",
    "url": "https://github.com/athola"
  },
  "license": "MIT",
  "dependencies": [
    "leyline"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[abstract on Agent Plugins Marketplace](https://pluginsmp.com/plugins/abstract)