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/sigistry/marketplaceWrote 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/sigistry/marketplace/llm-app-hardener)<a href="https://agentmods.dev/plugins/sigistry/marketplace/llm-app-hardener"><img src="https://agentmods.dev/badge/plugins/sigistry/marketplace/llm-app-hardener.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
llm-app-hardener 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 4d 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": "llm-app-hardener",
"version": "1.0.0",
"description": "A repo-native toolchain for LLM apps: scaffolds eval suites, red-teams for prompt injection, hardens structured-output reliability, and audits token cost, riding promptfoo/DeepEval/Pydantic rather than replacing them.",
"author": {
"name": "Sigistry LLM App Hardener",
"url": "https://github.com/Sigistry/marketplace/tree/main/plugins/llm-app-hardener"
},
"license": "MIT"
}
What it installs
The manifest is a name and a version. 4 skills, 4 commands, 2 agents travel with it, and installing the plugin installs all of them — 440 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill structured-output A 89 tokens
- Skill prompt-versioning-hygiene A 75 tokens
- Skill eval-authoring A 96 tokens
- Skill owasp-llm-top10 A 97 tokens
- Command structured-output-doctor A 23 tokens
- Command eval-scaffold A 24 tokens
- Command token-cost-audit A 20 tokens
- Command rag-tune A 16 tokens
- Agent token-cost-optimizer A 0 tokens
- Agent prompt-injection-auditor B 0 tokens
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.
- 4d ago First seen · 11 lines scan A c883f446d108
llm-app-hardener is a plugin published in the GitHub repository sigistry/marketplace (3 stars, last pushed 4d ago), 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
fuse-prompt-engineer
Expert Prompt Engineer with Context Engineering, Meta-Prompting, Chain-of-Thought, Few-Shot, Agent Design, 50+ Template Library, and A/B Testing.
data
Data science and data engineering agents for visualization (D3, Highcharts), notebooks (Jupyter, Google Colab), R, and Python data engineering.
prompt-optimizer
Clarify and optimize prompts for GPT-6 Astra, GPT-5.6, Claude, Gemini, Kimi, GLM, and DeepSeek-V4, plus Astra Skills/AGENTS.md audits.
prompt-studio
Prompt engineering workbench with a Lean persona layer that cuts LLM output size, cost, and latency. Injects the Lean ruleset every session via SessionStart + SubagentStart hooks.
dev
Developer tooling suite — BAML (typed LLM functions), Jinja2 templates (HuggingFace chat templates, Ansible), GNU Make best practices, and HuggingFace transformers config/tokenizer preflight (vLLM/sglang engine bridge).
prompt-utils
Prompt-crafting utilities: /expertify rewrites a lay prompt with the precise professional role and domain terminology, /interview probes until your real intent is clear, /thought captures surprising model answers, /repo-scout breaks down any GitHub repo into reusable parts.