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 alexmond/alexmskills --skill security-auditgit clone --depth 1 https://github.com/alexmond/alexmskillsWrote 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/alexmond/alexmskills/security-audit)<a href="https://agentmods.dev/skills/alexmond/alexmskills/security-audit"><img src="https://agentmods.dev/badge/skills/alexmond/alexmskills/security-audit/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/alexmond/alexmskills/security-audit"><img src="https://agentmods.dev/badge/skills/alexmond/alexmskills/security-audit.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 | $0.00094 | $0.01702 |
| Opus 5.5 | $0.00038 | $0.00681 |
| Sonnet 5.5 | $0.00019 | $0.00340 |
| Haiku 4.5 | $0.00009 | $0.00170 |
Grade B, and why
security-audit scanned grade B with 1 finding 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 8d 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.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
Does the server make an outbound request to a URL or host that comes from input? Verify the target is checked against an allow-list of hosts and schemes, that redirects are not followed blindly, and that internal and met Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Audit
Try it:
/security-audit:security-audit src/— or say "do a security audit of the auth module". The path argument is optional.
A defensive security review. The goal is to find and report vulnerabilities so they can be fixed — never to exploit them. Produce confirmed findings with file:line, severity, and remediation. Do not generate exploit payloads, weaponized proof-of-concept code, or instructions for attacking a live system.
The method is the same in every language; only the sinks differ. So the first step is to find out what the repo is written in.
Step 1 — Identify the languages
Count source files by extension inside the scope (git ls-files | sed 's/.*\.//' | sort | uniq -c | sort -rn | head), and check the manifests (pom.xml, build.gradle, package.json, pyproject.toml, go.mod, Cargo.toml, *.csproj, Gemfile, composer.json). Most repos have more than one: a service plus a front end, plus shell and CI config.
Then read references/sinks.md and use only the sections for the languages actually present. It has the dangerous calls, a grep per check, and the safe form to recommend, for Java/Kotlin, Python, JavaScript/TypeScript, Go, C#/.NET, Ruby, PHP and Rust, plus shell, Dockerfiles and CI workflows. Do not run one language's patterns over another's code: Runtime.getRuntime finds nothing in a Python repo, and a scan that matched nothing because it asked the wrong question must not be reported as clean.
A language that is present but has no section still gets audited: apply the check's concept below and search for that language's equivalent calls. Say in the report that it was done without a pattern set.
Scope
- If
$ARGUMENTSis provided, limit the scan to that file or directory. - Otherwise scan all source code in the repository.
- Exclude generated output, vendored dependencies, and build artifacts (e.g.
target/,build/,dist/,node_modules/,vendor/,.git/). - For secret-style checks, also distinguish production code from test fixtures and report them separately rather than ignoring tests entirely.
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.
- 8d ago Changed · +4 lines f1b6ee0effeb
- 1mo ago First seen · 82 lines · 94 tokens per session scan B b39b7042136d
security-audit is a skill published in the GitHub repository alexmond/alexmskills (9 stars, last pushed 3d ago), licensed MIT. It adds 94 tokens to every session and 1,702 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
safe-refactor
Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.