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 JasminGuberinic/code-security-mcp --skill code-security-reviewgit clone --depth 1 https://github.com/JasminGuberinic/code-security-mcpWrote 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/jasminguberinic/code-security-mcp/code-security-review)<a href="https://agentmods.dev/skills/jasminguberinic/code-security-mcp/code-security-review"><img src="https://agentmods.dev/badge/skills/jasminguberinic/code-security-mcp/code-security-review/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/jasminguberinic/code-security-mcp/code-security-review"><img src="https://agentmods.dev/badge/skills/jasminguberinic/code-security-mcp/code-security-review.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 | $0.00101 | $0.01050 |
| Opus 5.5 | $0.00040 | $0.00420 |
| Sonnet 5.5 | $0.00020 | $0.00210 |
| Haiku 4.5 | $0.00010 | $0.00105 |
Grade A, and why
code-security-review 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 today.
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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security review while the code is written
Most security tooling runs after the fact, in CI, on a whole repository, and reports a generic pattern match. This runs now, on what is being written, and each language is analyzed by the tool that language's own community trusts.
| Language | Analyzer |
|---|---|
| Kotlin | detekt, 216-rule ruleset aware of Spring, WebFlux, Ktor, Quarkus, Micronaut, Vert.x |
| Java | SpotBugs + FindSecBugs, filtered to security findings only |
| Python | Bandit |
| C# | Roslyn security analyzers |
| JavaScript / TypeScript | ESLint + eslint-plugin-security |
A directory containing several languages is routed per file.
Requires the MCP server
This skill drives the code-security-mcp server. Without it the tools below do
not exist. Install it once, then restart the agent:
pipx install code-security-mcp
pipx inject code-security-mcp bandit # Python analysis
code-security-mcp-setup # Kotlin + Java analyzers
Add --with-dotnet or --with-eslint for C# and JS/TS. Everything lands in an
isolated cache and the script prints the command that registers the server.
Nothing global is touched.
Source and full setup: https://github.com/JasminGuberinic/code-security-mcp
If a tool call fails with "No analyzer configured", the server is installed but no analyzer is reachable — say so plainly and point at the setup script rather than silently skipping the check.
Which tool, and when
Before writing anything involving cookies, sessions, secrets, signing keys,
tokens, TLS, CORS or random values on the JVM, call secure_pattern first. It
returns an insecure/secure pair with the reason and CWE. Writing the safe
version immediately is cheaper than writing the unsafe one and fixing it.
Search with a short noun phrase, not a sentence: session cookie works
better than how do I create a session cookie. Naming a framework is safe — if
no pattern is written for it the search widens automatically and the response
carries a note saying the advice comes from another stack. Adapt the snippet
when you see that note; the principle holds, the API names will not.
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.
- today First seen · 96 lines · 101 tokens per session scan A 63542d73790f
code-security-review is a skill published in the GitHub repository JasminGuberinic/code-security-mcp (0 stars, last pushed today), licensed MIT. It adds 101 tokens to every session and 1,050 once invoked, about $0.0004 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 2026-10-16.
Other skills, from other repositories
trace-form
Trace how an Oracle Forms screen actually works — which form opens a modal, where a button's code really lives when its body looks empty, what a :GLOBAL carries back into a field. Use when asked how a Forms form, block, item, button, modal window or LOV behaves, where a value comes from, what calls what, or when a…
telegram-inbox-assistant
Summarize unread Telegram conversations, identify messages awaiting a reply, and find conversation context using telegram-mcp-tdlib. Use for read-only personal inbox triage; requires a connected, locally authorized Telegram MCP server.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
dcc-blender-assembly-pitfalls
Read this BEFORE writing any Blender geometry code through MCP, whenever you are about to (1) create or size mesh primitives - bpy.ops.mesh.primitivecubeadd, primitivecylinderadd, primitiveuvsphereadd, primitiveconeadd - or set scale / dimensions on a part; (2) orient a part with rotationeuler or rotationquaternion…
linkding
Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.
kotlin-expert
Expert-level Kotlin development, Android, coroutines, and multiplatform. Use when the user mentions Android, coroutines, multiplatform, or JVM, or when the task involves Kotlin Fundamentals, Android Development, Kotlin Multiplatform, or Kotlin Style.