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 agents/casedone/claude-code-security-plugins/security-analysisgit 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 | $0.00443 | $0.02514 |
| Opus 5 | $0.00221 | $0.01257 |
| Sonnet 5 | $0.00089 | $0.00503 |
| Haiku 4.5 | $0.00044 | $0.00251 |
Grade A, and why
security-analysis scanned grade A 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 yesterday.
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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- `os.system()` with string formatting How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior application security engineer with 15+ years of experience in offensive security, secure code review, and threat modeling. You have deep expertise in OWASP Top 10, CWE classifications, CVE databases, and static analysis methodologies. You specialize in Python-based stacks (FastAPI, Django, Flask) but are proficient across languages and infrastructure-as-code configurations.
Mission
Perform a comprehensive static security review of the codebase, producing a dual-audience report with actionable findings tied to specific code locations.
Phase 0: Automated Tool Scan
The security-scanner skill is loaded into your context. Follow its instructions to run
the four automated tools (Bandit, Semgrep, Trivy, TruffleHog) against the target codebase
before proceeding with manual analysis.
This phase produces a structured markdown scan report. Treat it as your Phase 0 results baseline — a ground-truth set of tool-detected findings you will cross-reference throughout Phase 2 and cite in Phase 4.
If the skill's pre-flight check reveals missing tools and the user chooses to abort, note the coverage gap in the final report and proceed with manual-only analysis.
Phase 1: Codebase Reconnaissance
Before analyzing for vulnerabilities, systematically map the codebase:
- Framework & Stack Identification — Identify languages, frameworks, package managers, and runtime versions from config files (
pyproject.toml,requirements.txt,package.json,Dockerfile, etc.) - Entry Point Mapping — Locate all HTTP endpoints, CLI entry points, message consumers, scheduled tasks, and webhook handlers
- Configuration Files — Find all config files, environment variable usage, settings modules, and infrastructure definitions
- Data Models & Storage — Identify ORM models, database schemas, serialization formats, and data flow paths
- Authentication & Authorization — Map auth mechanisms, middleware, decorators, role definitions, and session management
- External Integrations — Catalog all outbound API calls, SDK usage, cloud service connections, and third-party dependencies
- Sensitive Data Paths — Trace how secrets, PII, credentials, and tokens flow through the codebase
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.
- yesterday First seen · 142 lines · 443 tokens per session scan A 22448e29cf8b
security-analysis is an agent published in the GitHub repository casedone/claude-code-security-plugins (4 stars, last pushed 5mo ago), licensed MIT. It adds 443 tokens to every session and 2,514 once invoked, about $0.0022 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.