p3-sec-auth

p3-sec-auth is a command for coding agents from jonase47/ccpr. It costs 0 tokens per session (897 once invoked), scanned A, original, MIT.

A plan for authentication, authorization, and session management: proving who a user is, deciding what they can access, and controlling logged-in sessions.

In plain words
What is it for?
Use it to choose an authentication method and define roles, access rights, session behavior, and password policy.
Why use it?
It turns user roles and security risks into rules for sign-in, permissions, sessions, and passwords when needed.

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-auth
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-auth

README.md
[![agentmods](https://agentmods.dev/badge/commands/jonase47/ccpr/p3-sec-auth.svg)](https://agentmods.dev/commands/jonase47/ccpr/p3-sec-auth)
Your own site
<a href="https://agentmods.dev/commands/jonase47/ccpr/p3-sec-auth"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p3-sec-auth.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 897 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 $0.00897
Opus 5 $0.00000 $0.00449
Sonnet 5 $0.00000 $0.00179
Haiku 4.5 $0.00000 $0.00090

Measured yesterday against content hash 3566df9168d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

p3-sec-auth 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-auth.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/p3-sec-auth – Auth & Authorization Concept

Defines the authentication and authorization concept including session management.

Argument: $ARGUMENTS = [Auth method, e.g. "JWT", "Session", "OAuth", "none"]

If provided: Use the method as a starting point. If not provided: Recommend based on architecture and requirements.

Prerequisites

  • ARCHITECTURE.md and threat model exist

Agent

  • Type: system-architekt
  • Model: sonnet

Context (Orchestrator prepares)

Orchestrator reads beforehand and delivers inline:

  • From ARCHITECTURE.md: Components with access control
  • From SECURITY.md: Threat model (spoofing/elevation rows)
  • From CONCEPT.md: User roles and permissions (if defined)

Prompt Template

Goal: Design auth & authorization concept. Method: $ARGUMENTS

Context: [inline from ARCHITECTURE.md, SECURITY.md]

Output Format:

  1. Auth method with justification (1-2 sentences)
  2. Roles table: | Role | Description | Access Rights |
  3. Session management: timeout, token rotation, logout
  4. Password policy (if password-based)

Constraints:

  • ONLY auth concept, NO threat model, NO API security
  • If no auth needed: explicitly justify and leave section empty
  • MFA only if relevant for the project type

Orchestrator Checkpoint

  • Auth method justified?
  • Roles cover all user types mentioned in the concept?

Write Detail File

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

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

Body sections: ## Auth Method (with justification), ## Roles (the table Role / Description / Access Rights), ## Session Management (timeout, token rotation, logout), ## Password Policy (if password-based), ## MFA (if relevant).

Update Sub-Index

Update docs/architecture/SECURITY.md:

  • Set **Last Updated:** <DD.MM.YYYY>.
  • In its Detail Files table: ensure a row for [AUTH.md](AUTH.md) with status complete.
  • Lift the headline auth decision into Key Decisions of the sub-index (e.g. - Auth: JWT with 15-min access + 7-day refresh → see AUTH.md).
  • Do not edit ARCHITECTURE.md directly — /p3-security rolls the sub-index up.

Read the full file on GitHub · 87 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 · 87 lines · 0 tokens per session scan A 3566df9168d0

Subscribe to this mod's changes

p3-sec-auth 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 897 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.