p3-sec-threats

p3-sec-threats is a command for coding agents from jonase47/ccpr. It costs 0 tokens per session (883 once invoked), scanned A, original, MIT.

A security review that uses the STRIDE model, a framework for finding common types of system threats, and pairs each threat with a countermeasure.

In plain words
What is it for?
Use it to review the whole system or focus on an API, database, frontend, or another named area.
Why use it?
It turns an architecture and technology list into a focused record of realistic security risks, their severity, and whether they have been addressed.

Command

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/jonase47/ccpr/p3-sec-threats
Clone the repo
git clone --depth 1 https://github.com/jonase47/ccpr

Wrote 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.

agentmods badge for p3-sec-threats

README.md
[![agentmods](https://agentmods.dev/badge/commands/jonase47/ccpr/p3-sec-threats.svg)](https://agentmods.dev/commands/jonase47/ccpr/p3-sec-threats)
Your own site
<a href="https://agentmods.dev/commands/jonase47/ccpr/p3-sec-threats"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p3-sec-threats.svg" alt="Measured on agentmods" height="20"></a>
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 883 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 5.1 $0.00000 $0.00883
Opus 5 $0.00000 $0.00441
Sonnet 5 $0.00000 $0.00177
Haiku 4.5 $0.00000 $0.00088

Measured yesterday against content hash 73707a748ab0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

p3-sec-threats 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 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.

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.

commands/p3-sec-threats.md · 86 lines

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.

/p3-sec-threats – Create STRIDE Threat Model

Analyzes the system according to the STRIDE model and identifies threats with countermeasures.

Argument: $ARGUMENTS = [Focus area, e.g. "API", "Database", "Frontend"]

If provided: Focus STRIDE on the named area. If not provided: Analyze the entire system.

Prerequisites

  • ARCHITECTURE.md with component diagram exists
  • TECH_STACK.md exists

Agent

  • Type: security-master
  • Model: opus

Context (Orchestrator prepares)

Orchestrator reads beforehand and delivers inline:

  • From ARCHITECTURE.md: Component diagram and data flows
  • From TECH_STACK.md: Technologies in use (short list)

Prompt Template

Goal: STRIDE threat model for: $ARGUMENTS

Architecture: [inline from ARCHITECTURE.md]

Output Format: Table: | STRIDE Category | Threat | Affected Component | Severity | Countermeasure | Status | Severity: Critical / High / Medium / Low Status: open / addressed

Constraints:

  • ONLY threat model, NO auth concept, NO checklists
  • Max. 12 threats
  • Focus on realistic threats for the project type

Orchestrator Checkpoint

  • All 6 STRIDE categories covered?
  • Severity levels plausible?

Write Detail File

Write the result to docs/architecture/THREATS.md (overwrite if it exists). Start with this YAML frontmatter:

---
phase: P3
subskill: sec-threats
status: active
last_updated: <DD.MM.YYYY>
---

Body sections: ## STRIDE Threat Model (the table STRIDE Category / Threat / Component / Severity / Countermeasure / Status), ## Critical Threats Summary (the open Critical/High items called out for the gate).

Update Sub-Index

Update docs/architecture/SECURITY.md (the security sub-index, created by /p3-security if missing):

  • Set **Last Updated:** <DD.MM.YYYY>.
  • In its Detail Files table: ensure a row for [THREATS.md](THREATS.md) with status complete.
  • Lift any open Critical threat into Open Risks / Open Questions of the sub-index (e.g. - Critical: <threat> still open → see THREATS.md).
  • Do not edit the phase-level ARCHITECTURE.md directly — /p3-security rolls the sub-index summary up to the phase index.

Read the full file on GitHub · 86 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. yesterday First seen · 86 lines · 0 tokens per session scan A 73707a748ab0

Subscribe to this mod's changes

p3-sec-threats is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 883 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 2026-09-03.