Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/athola/claude-night-marketWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/athola/claude-night-market/abstract)<a href="https://agentmods.dev/plugins/athola/claude-night-market/abstract"><img src="https://agentmods.dev/badge/plugins/athola/claude-night-market/abstract.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
abstract scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "abstract",
"version": "1.9.19",
"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/shared-patterns",
"./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",
"dependenciesWhat it installs
The manifest is a name and a version. 16 skills, 17 commands, 5 agents, 4 hooks travel with it, and installing the plugin installs all of them — 880 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill escalation-governance A 19 tokens
- Skill skill-authoring A 22 tokens
- Skill metacognitive-self-mod A 23 tokens
- Skill development-workflow A 20 tokens
- Skill friction-detector A 20 tokens
- Skill hooks-eval A 18 tokens
- Skill modular-skills A 24 tokens
- Skill skills-eval A 18 tokens
- Skill methodology-curator A 21 tokens
- Skill plugin-review A 23 tokens
- Skill skill-graph-audit A 25 tokens
- Skill rules-eval A 27 tokens
- Skill subagent-testing A 22 tokens
- Skill shared-patterns A 21 tokens
- Skill hook-authoring B 20 tokens
- Skill hook-scope-guide B 25 tokens
- Command create-command A 11 tokens
- Command create-hook A 11 tokens
- Command create-skill A 25 tokens
- Command improve-skills A 17 tokens
- Command make-dogfood A 18 tokens
- Command validate-hook A 13 tokens
- Command aggregate-logs A 19 tokens
- Command context-report A 10 tokens
- Command hooks-eval A 14 tokens
- Command evaluate-skill A 16 tokens
- Command plugin-review A 40 tokens
- Command analyze-skill A 21 tokens
- Command promote-discussions A 20 tokens
- Command rules-eval A 18 tokens
- Command skills-eval A 24 tokens
- Command validate-plugin A 22 tokens
- Command test-skill A 29 tokens
- Agent skill-improver A 60 tokens
- Agent plugin-validator A 37 tokens
- Agent insight-engine A 39 tokens
- Agent skill-auditor A 36 tokens
- Agent meta-architect A 32 tokens
- Hook PreToolUse A not measured
- Hook PostToolUse A not measured
- Hook UserPromptSubmit A not measured
- Hook Stop A not measured
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 78 lines scan A b17ce834b208
abstract is a plugin published in the GitHub repository athola/claude-night-market (335 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
code-architect
Use this agent when you need to design scalable architecture and folder structures for new features or projects. Examples include: when starting a new feature module, refactoring existing code organization, planning microservice boundaries, designing component hierarchies, or establishing project structure conventions.
sound
Code taste as installable rules. Probe a repo's stack, select only the rules its code shows a surface for (evidence-cited per rule), confirm, and scaffold a browsable .claude/sound/ rule map (surfaced by the sound:prime skill). Installed rules are user-owned; re-runs reconcile.
sprint-prioritizer
Use this agent when planning 6-day development cycles, prioritizing features, managing product roadmaps, or making trade-off decisions. This agent specializes in maximizing value delivery within tight timelines. Examples:\n\n \nContext: Planning the next sprint\nuser: "We have 50 feature requests but only 6 day.
prd-specialist
Use this agent when you need to create comprehensive Product Requirements Documents (PRDs) that combine business strategy, technical architecture, and user research. Examples: Context: The user needs to create a PRD for a new feature or product launch. user: "I need to create a PRD for our new user authenticat.
planning-prd-agent
'MUST BE USED PROACTIVELY when user mentions: planning, PRD, product requirements document, project plan, roadmap, specification, requirements analysis, feature breakdown, technical spec, project estimation, milestone planning, or task decomposition. Use IMMEDIATELY when user says "create a PRD", "plan this feature"…
pricing-packaging-specialist
Use this agent when you need to optimize B2B pricing strategies, packaging models, and revenue optimization for enterprise sales. This agent specializes in value-based pricing, usage-based billing, enterprise contract negotiations, and competitive pricing analysis for SaaS platforms. Examples.