Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add qte77/claude-code-plugins/plugin install security-auditWrote 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/qte77/claude-code-plugins/auditing-code-security)<a href="https://agentmods.dev/skills/qte77/claude-code-plugins/auditing-code-security"><img src="https://agentmods.dev/badge/skills/qte77/claude-code-plugins/auditing-code-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/qte77/claude-code-plugins/auditing-code-security"><img src="https://agentmods.dev/badge/skills/qte77/claude-code-plugins/auditing-code-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 | $0.00030 | $0.01231 |
| Opus 5.5 | $0.00012 | $0.00492 |
| Sonnet 5.5 | $0.00006 | $0.00246 |
| Haiku 4.5 | $0.00003 | $0.00123 |
Grade A, and why
auditing-code-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 16d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OWASP Top 10 Code Security Audit
Scope: $ARGUMENTS
When to Use
- Security review before release or merge
- Auditing new features for vulnerability exposure
- Periodic security posture assessment
- Compliance-driven code review
Workflow
- Identify scope — files, modules, or full codebase
- Scan each OWASP category using the checklist below
- Record findings in the output table
- Assign severity (Critical / High / Medium / Low / Info)
- Propose remediation for each finding
Workflow Mode (full-codebase scope)
When auditing a whole codebase or many modules and the Workflow tool is available, fan the ten OWASP categories out in parallel instead of scanning them one after another:
Workflow({
scriptPath: "${CLAUDE_PLUGIN_ROOT}/workflows/audit-owasp.js",
args: { scope: "<dir>",
skillPath: "${CLAUDE_PLUGIN_ROOT}/skills/auditing-code-security/SKILL.md" }
})
args reaches the script as a JSON string (the script parses it). One read-only
agent scans the scope per category (A01–A10) and returns structured findings;
render them with the Output Format below. Fall back to the inline per-category
scan (steps 1–5) when the Workflow tool is unavailable. The agents are
read-only, so the only permission to pre-grant is the Workflow tool.
OWASP Top 10 Checklist
A01: Injection
- SQL queries use parameterized statements (no string concatenation)
- OS command execution uses allowlists, not user input
- LDAP queries use proper escaping
- XPath queries parameterized
- ORM queries avoid raw SQL where possible
A02: Broken Authentication
- Passwords hashed with bcrypt/scrypt/argon2 (not MD5/SHA1)
- Session tokens are cryptographically random
- Session expiration and rotation implemented
- Multi-factor authentication available for sensitive operations
- Account lockout or rate limiting on login
A03: Cross-Site Scripting (XSS)
- Output encoding applied for HTML, JS, CSS, URL contexts
- Reflected input never rendered without sanitization
- Stored user content sanitized before display
- DOM manipulation uses safe APIs (textContent, not innerHTML)
- Content-Security-Policy headers configured
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.
- 16d ago Changed 2e81c7df331c
- 1mo ago First seen · 144 lines · 30 tokens per session scan A ae075463168e
auditing-code-security is a skill published in the GitHub repository qte77/claude-code-plugins (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,231 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 2026-09-03.
Other skills, from other repositories
android-kotlin-compose
Android development with Kotlin and Jetpack Compose. Use when user mentions "Compose", "Jetpack Compose", "Material3", "Hilt", "Room", "ViewModel", or needs to build Android UI, implement MVVM architecture, manage Compose state, or integrate Jetpack libraries (Navigation, Room, Hilt, ViewModel). Triggers on…
android-kotlin-coroutines
Android development with Kotlin Coroutines and Flow. Use when user mentions "coroutines", "suspend", "Flow", "StateFlow", "SharedFlow", "viewModelScope", "lifecycleScope", or needs to implement async programming, handle structured concurrency, integrate coroutines with Retrofit/Room/WorkManager, or write coroutine…
codex-advisor
Advisory consultation skill for architectural reviews, design decisions, code analysis, and technology evaluation. Codex provides recommendations without making code changes. Invoked by phrases like "consult Codex", "get Codex's opinion", "ask Codex about", "have Codex review", "Codex analysis", "validate this…
ast-grep
Structural code search and rewriting using AST patterns. Use when user mentions "ast-grep", "sg", or needs to search codebases using Abstract Syntax Tree patterns, find specific code structures, perform complex queries beyond text search, or rewrite code at scale. Triggers on requests for pattern matching, code…
github-cli
This skill should be used when working with GitHub CLI (gh) for repository management, pull requests, issues, API access, GitHub Actions, or automation workflows. Provides comprehensive guidance on gh command patterns, security considerations, and best practices.
android-analysis
Expert Android and Java reverse engineering for APK/AAR/JAR decompilation and inspection. Use when user mentions "decompile", "jadx", "apktool", "reverse engineer", or needs to analyze Android binaries, unpack libraries, understand obfuscated apps, or extract resources from compiled artifacts.