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/conjure)<a href="https://agentmods.dev/plugins/athola/claude-night-market/conjure"><img src="https://agentmods.dev/badge/plugins/athola/claude-night-market/conjure/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/athola/claude-night-market/conjure"><img src="https://agentmods.dev/badge/plugins/athola/claude-night-market/conjure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
conjure 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 20d 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.
What it actually says
{
"name": "conjure",
"version": "1.9.21",
"description": "Intelligent delegation framework for routing tasks to external LLM services while retaining strategic oversight",
"skills": [
"./skills/delegation-core",
"./skills/gemini-delegation",
"./skills/minimax-delegation",
"./skills/qwen-delegation",
"./skills/glm-delegation",
"./skills/muse-delegation",
"./skills/codex-delegation",
"./skills/opencode-delegation",
"./skills/agent-teams",
"./skills/glimmer-delegation",
"./skills/provider-setup"
],
"keywords": [
"delegation",
"llm",
"gemini",
"qwen",
"minimax",
"glm",
"muse",
"codex",
"opencode",
"orchestration",
"routing",
"agent-teams",
"multi-agent",
"coordination"
],
"author": {
"name": "Alex Thola",
"url": "https://github.com/athola"
},
"license": "MIT",
"dependencies": [
"leyline"
]
}
What it installs
The manifest is a name and a version. 11 skills travel with it, and installing the plugin installs all of them — 416 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill agent-teams A 30 tokens
- Skill delegation-core A 46 tokens
- Skill glm-delegation A 44 tokens
- Skill minimax-delegation A 37 tokens
- Skill provider-setup A 33 tokens
- Skill qwen-delegation A 36 tokens
- Skill gemini-delegation A 35 tokens
- Skill opencode-delegation A 38 tokens
- Skill codex-delegation C 40 tokens
- Skill glimmer-delegation C 36 tokens
- Skill muse-delegation C 41 tokens
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.
- 20d ago Changed ba1edeea7518
- 1mo ago Changed b9f96120b54f
- 1mo ago First seen · 43 lines scan A 1a1132e2b8a4
conjure is a plugin published in the GitHub repository athola/claude-night-market (343 stars, last pushed today), 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 2026-09-03.
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.
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.
create-worktrees
Creates git worktrees for all open PRs or specific branches, handling branches with slashes, cleaning up stale worktrees, and supporting custom branch creation for development.