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.
npx skills add oxbshw/LLM-Agents-Ecosystem-Handbook --skill mcp-security-reviewergit clone --depth 1 https://github.com/oxbshw/LLM-Agents-Ecosystem-HandbookWrote 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/skills/oxbshw/llm-agents-ecosystem-handbook/mcp-security-reviewer)<a href="https://agentmods.dev/skills/oxbshw/llm-agents-ecosystem-handbook/mcp-security-reviewer"><img src="https://agentmods.dev/badge/skills/oxbshw/llm-agents-ecosystem-handbook/mcp-security-reviewer/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/skills/oxbshw/llm-agents-ecosystem-handbook/mcp-security-reviewer"><img src="https://agentmods.dev/badge/skills/oxbshw/llm-agents-ecosystem-handbook/mcp-security-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.00391 |
| Opus 5 | $0.00017 | $0.00196 |
| Sonnet 5 | $0.00007 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
mcp-security-reviewer 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 12d 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
MCP Security Reviewer
When to use
- A new MCP server is being added to an agent
- An MCP server version is being bumped
- An incident triggered a re-review
Inputs
| Name | Type | Required | Notes |
|---|---|---|---|
repo_url |
string | yes | the MCP server's source |
version |
string | yes | tag or commit SHA being adopted |
intended_use |
string | yes | one paragraph: what we'll let it do |
Workflow
- Source review: clone at the pinned version; check for unexpected files / scripts
- Capabilities: list every tool and resource exposed; map to risk levels (
references/mcp-risk-matrix.md) - Network: identify outbound endpoints; document and assess each
- Permissions: minimum required scopes / tokens; document over-permissions
- Output handling: confirm the agent treats tool output as untrusted (sanitization, no execution)
- Approvals: define which tools require human approval
- Produce filled
MCP_SERVER.mdinmcp/<server>.md
References
Success criteria
- All tools labelled by risk
- High/Critical tools gated by approval
- Pinned version (no
latest/ floating refs) - Documented network egress
Failure modes
- Source unavailable / un-pinnable → reject
- Discovered hidden tool not in docs → reject and report upstream
What ships with it
1 file beside SKILL.md 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.
- 12d ago First seen · 42 lines · 34 tokens per session scan A 698e80acf561
mcp-security-reviewer is a skill published in the GitHub repository oxbshw/LLM-Agents-Ecosystem-Handbook (546 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 391 once invoked, about $0.0002 per session on Opus 5. 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 skills, from other repositories
implementing-llms-litgpt
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
llama-factory
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support.
together-ai-inference
Serverless inference, fine-tuning, embeddings, image generation, and batch processing on 200+ open-source models via an OpenAI-compatible API. Use when you need fast, cost-effective access to open-source LLMs without managing infrastructure.
tinker-fine-tuning
Provides guidance for fine-tuning LLMs using the Tinker cloud training API from Thinking Machines Lab. Use when running supervised fine-tuning, reinforcement learning (GRPO/PPO), or LoRA training on cloud GPUs via Tinker's managed infrastructure instead of local compute.
tinker-training-cost
Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.
transformers
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning…