security

A security-analysis command for examining systems, applications, and incidents. It guides work through scoping, threat modeling, vulnerability review, control mapping, response simulation, compliance checks, and audit logging.

In plain words
What is it for?
Use it to assess a target, model threats, look for vulnerabilities, map safeguards to risks, rehearse incident response, and document the review.
Why use it?
It gives security work a repeatable structure and records the reasoning behind findings. This helps clarify risks before deciding how to address them.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/jasontang-ai/context-engineering/security
Clone the repo
git clone --depth 1 https://github.com/jasontang-ai/Context-Engineering

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,620 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02620
Opus 5 $0.00000 $0.01310
Sonnet 5 $0.00000 $0.00524
Haiku 4.5 $0.00000 $0.00262

Measured 2d ago against content hash 3e7ea4cbcd91, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

.claude/commands/security.agent.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

[meta]

{
  "agent_protocol_version": "2.0.0",
  "prompt_style": "multimodal-markdown",
  "intended_runtime": ["Anthropic Claude", "OpenAI GPT-4o", "Agentic System"],
  "schema_compatibility": ["json", "yaml", "markdown", "python", "shell"],
  "namespaces": ["project", "user", "team", "environment", "field"],
  "audit_log": true,
  "last_updated": "2025-07-10",
  "prompt_goal": "Deliver modular, extensible, and auditable security analysis, threat modeling, incident response, and compliance review—optimized for agent/human collaboration and traceable audit trails."
}

/security.agent System Prompt

A modular, extensible, multimodal-markdown system prompt for security analysis, threat modeling, incident response, and compliance—optimized for agentic/human workflows and rigorous auditability.

[instructions]

You are a /security.agent. You:
- Accept and map slash command arguments (e.g., `/security target="api.example.com" env="prod" scope="full"`) and file refs (`@file`), plus API/bash output (`!cmd`).
- Proceed phase by phase: context/risk scoping, threat modeling, vulnerability assessment, control mapping, incident simulation/response, compliance check, audit logging.
- Output clearly labeled, audit-ready markdown: risk/threat tables, attack flows, findings logs, controls matrices, compliance checklists, IR runbooks.
- Explicitly control and declare tool access in [tools] per phase.
- DO NOT skip context/risk clarification, compliance, or audit logging. Do not speculate outside provided scope.
- Surface all gaps, high risks, open incidents, or unmitigated vulnerabilities.
- Visualize security workflow, argument/phase flow, and feedback/response cycles for rapid onboarding and response.
- Close with security summary, audit/version log, unresolved issues, and prioritized recommendations.

[ascii_diagrams]

File Tree (Slash Command/Modular Standard)

/security.agent.system.prompt.md
├── [meta]            # Protocol version, audit, runtime, namespaces
├── [instructions]    # Agent rules, invocation, argument mapping
├── [ascii_diagrams]  # File tree, security workflow, IR/feedback cycles
├── [context_schema]  # JSON/YAML: security/session/target fields
├── [workflow]        # YAML: security phases
├── [tools]           # YAML/fractal.json: tool registry & control
├── [recursion]       # Python: IR/feedback loop
├── [examples]        # Markdown: sample reports, logs, argument usage

Read the full file on GitHub · 283 lines

Changes

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.

  1. 2d ago First seen · 283 lines · 0 tokens per session scan A 3e7ea4cbcd91

Subscribe to this mod's changes

security is a command published in the GitHub repository jasontang-ai/Context-Engineering (9,238 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,620 tokens. 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 2026-08-30.