gate-p6-security

A project security checkpoint based on a Gate-P6 checklist, which reviews security documents and decides whether the project can receive security approval.

In plain words
What is it for?
Reviewing security and penetration-test records, checking the security architecture, and granting or withholding approval.
Why use it?
It gathers security findings into one approval decision and checks areas such as access control, dependencies, testing, and privacy compliance.

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/gate-p6-security
Clone the repo
git clone --depth 1 https://github.com/jonase47/ccpr
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 1,005 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 $0.01005
Opus 5 $0.00000 $0.00502
Sonnet 5 $0.00000 $0.00201
Haiku 4.5 $0.00000 $0.00101

Measured yesterday against content hash 591fdd11ee44, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gate-p6-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 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/gate-p6-security.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/gate-p6-security – Security Approval Evaluation

Evaluates all security-relevant points of the Gate-P6 checklist and grants Security approval.

Argument: $ARGUMENTS = not applicable

Gate commands accept no arguments.

Prerequisites

  • docs/quality/QA.md (phase index) exists
  • docs/quality/AUDIT.md (sub-index) and its detail files (audit_auth.md, audit_config.md, audit_deps.md, audit_dsgvo.md, audit_sast.md)
  • docs/quality/PENTEST.md (sub-index) and its detail files (pentest_recon.md, pentest_auth.md, pentest_authz.md, pentest_injection.md, pentest_logic.md)
  • docs/architecture/SECURITY.md (P3 sub-index) as reference for the security architecture
  • docs/concept/DSGVO_INITIAL_ASSESSMENT.md (P1 detail file) as compliance benchmark

Agent

  • Type: security-master
  • Model: opus

Pre-Flight

If docs/.gate-preflight-p6.md exists and is less than 10 minutes old, read it as a starting point. Mechanical checks (file existence, sections) are already done – focus on content evaluation.

Context (Orchestrator prepares)

Read the phase and sub-indexes first, then load detail files only when their status row signals an open issue:

  • From docs/quality/QA.md: status, key decisions, open risks (entry point)
  • From docs/quality/AUDIT.md (sub-index): row status of each audit_*.md
  • From docs/quality/PENTEST.md (sub-index): row status of each pentest_*.md
  • From docs/architecture/SECURITY.md: P3 threat model summary (key decisions, open risks)
  • From docs/concept/DSGVO_INITIAL_ASSESSMENT.md: DSGVO requirements (short list)
  • Detail files (audit_dsgvo.md, pentest_authz.md, ...) only when a sub-index row is needs-rework or has an open Critical risk

Prompt Template

Goal: Security approval evaluation for Gate P6.

Security Reports: [inline summaries]

Output Format:

  1. Checklist (max. 6 points): | # | Check Point | Status | Justification | Status: Met / Partial / Not Met

  2. Security Approval:

  • Approved / Conditional Approval / Not Approved
  • Justification (2–3 sentences)
  • Conditions (if conditional, as numbered list)

Constraints:

  • Security evaluation ONLY, NO QA evaluation
  • Evaluation based exclusively on available reports
  • No approval if critical or high security findings are open

Read the full file on GitHub · 79 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 · 79 lines · 0 tokens per session scan A 591fdd11ee44

Subscribe to this mod's changes

gate-p6-security is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,005 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 2026-08-31.