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 ersinkoc/security-check --skill sc-ai-securitygit clone --depth 1 https://github.com/ersinkoc/security-checkWrote 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/ersinkoc/security-check/sc-ai-security)<a href="https://agentmods.dev/skills/ersinkoc/security-check/sc-ai-security"><img src="https://agentmods.dev/badge/skills/ersinkoc/security-check/sc-ai-security/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/ersinkoc/security-check/sc-ai-security"><img src="https://agentmods.dev/badge/skills/ersinkoc/security-check/sc-ai-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00024 | $0.01874 |
| Opus 5.5 | $0.00010 | $0.00750 |
| Sonnet 5.5 | $0.00005 | $0.00375 |
| Haiku 4.5 | $0.00002 | $0.00187 |
Grade A, and why
sc-ai-security 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 1mo 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SC: AI and Agent Security
Purpose
Find trust-boundary failures in applications that assemble model context, retrieve untrusted content, persist memory, call tools, delegate to agents, expose MCP capabilities, or render model output. Prompt injection by itself is not a finding: prove an unauthorized action, cross-principal disclosure, integrity loss, or meaningful operator-cost impact.
Activation
Run when reconnaissance finds an LLM SDK, prompt templates, RAG or embeddings, vector stores, tool/function calling, MCP clients or servers, autonomous agents, persistent conversation memory, model-generated code execution, or model output reaching an active sink.
Phase 1: Discovery
Context and instruction sources
Search for system/developer prompts, user content, retrieved documents, web results, file contents, tool results, memory summaries, examples, and model-generated context. Record precedence, delimiters, truncation, filtering, and which principal can write each source.
Capability map
Inventory every model-visible tool, resource, prompt, subagent, shell, browser, filesystem, database, messaging, deployment, and external-service capability. For each capability record:
- execution identity and credential;
- deterministic allowlist or policy gate;
- argument schema and post-parse validation;
- confirmation or approval binding;
- tenant, user, workspace, and resource scope;
- retry, resume, queued, batch, and delegated variants.
Memory and retrieval map
Trace who can write each conversation store, vector collection, cache, knowledge base, profile, preference, or durable memory record and which later principal reads it. Include ingestion pipelines, document updates, deletion, re-indexing, namespace selection, metadata filters, and fallback search paths.
Output destinations
Find model output sent to HTML/Markdown renderers, URLs, commands, code evaluators, templates, SQL, logs, emails, issue trackers, MCP messages, or other models. Determine whether the destination interprets active content and which encoder or policy applies at the final sink.
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.
- 1mo ago First seen · 156 lines · 24 tokens per session scan A 86054bcb4cdd
sc-ai-security is a skill published in the GitHub repository ersinkoc/security-check (83 stars, last pushed 17d ago), licensed MIT. It adds 24 tokens to every session and 1,874 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-16.
Other skills, from other repositories
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.