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 agentmods add skills/casedone/claude-code-security-plugins/security-scannernpx skills add casedone/claude-code-security-plugins --skill security-scannergit clone --depth 1 https://github.com/casedone/claude-code-security-pluginsWhat 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 | $0.00109 | $0.01717 |
| Opus 5 | $0.00055 | $0.00859 |
| Sonnet 5 | $0.00022 | $0.00343 |
| Haiku 4.5 | $0.00011 | $0.00172 |
Grade A, and why
security-scanner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Scanner
Runs four complementary automated security tools against a target path and assembles a structured markdown report for LLM consumption. Full tool output is always included — do not truncate or summarize tool output before writing the report.
Tools
| Tool | Purpose |
|---|---|
| Bandit | Python SAST — injection, pickle, subprocess, weak crypto |
| Semgrep | Multi-language SAST — OWASP Top 10 + Python-specific rules |
| Trivy | Dependencies, IaC misconfigs, secrets, container images |
| TruffleHog | Secrets in git history with live API verification |
Step 1: Determine Scan Target
If the calling agent or user specified a path, use it. Otherwise default to the current working directory. Confirm with a brief message:
Scan target: <resolved absolute path>
Step 2: Pre-flight Tool Check
Before running anything, check availability and version of all four tools:
for tool in bandit semgrep trivy trufflehog; do
if command -v "$tool" &>/dev/null; then
echo "OK $tool $($tool --version 2>&1 | head -1)"
else
echo "MISSING $tool"
fi
done
If any tools are missing
List the missing tools clearly and ask the user:
"The following tools are not installed: [list]
How would you like to proceed?
- Skip — continue without them (coverage will be incomplete; I'll note the gap in the report)
- Install — I'll attempt to install the missing tools before scanning"
Do not proceed until the user responds. Wait for an explicit choice.
If the user chooses Install
Use these install commands (macOS with Homebrew assumed; adapt if on Linux):
| Tool | Install command |
|---|---|
| Bandit | pip install bandit |
| Semgrep | pip install semgrep |
| Trivy | brew install trivy |
| TruffleHog | brew install trufflehog |
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.
- 2d ago First seen · 241 lines · 109 tokens per session scan A 1a9a3bf87db4
security-scanner is a skill published in the GitHub repository casedone/claude-code-security-plugins (4 stars, last pushed 5mo ago), licensed MIT. It adds 109 tokens to every session and 1,717 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…