matematic-patron-pr-review-pl

matematic-patron-pr-review-pl is a skill for Claude Code from matematicsolutions/awesome-matematic-skills-pl. It costs 302 tokens per session (5,603 once invoked), scanned A, original, MIT.

A code-review checklist for pull requests and diffs in the PATRON legal-technology repository. It looks for project-specific security and data-isolation problems that general linting may miss.

In plain words
What is it for?
Use it before merging or pushing changes, after large refactors, or when auditing authentication, webhooks, WebSockets, database access, audit logs, and other security-critical components.
Why use it?
Generic code checks may not detect one organization accessing another’s data, publicly reachable routes, unsafe database changes, or broken synchronization. This review focuses on those repository-specific failure modes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions AGENTS.md.

Part of the dev-mcp plugin — 4 skills shipped together

Good fit Use it before merging or pushing changes, after large refactors, or when auditing authentication, webhooks, WebSockets, database access, audit logs, and other security-critical components.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/matematicsolutions/awesome-matematic-skills-pl/matematic-patron-pr-review-pl
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.

Any agent
npx skills add matematicsolutions/awesome-matematic-skills-pl --skill matematic-patron-pr-review-pl
Clone the repo
git clone --depth 1 https://github.com/matematicsolutions/awesome-matematic-skills-pl

Made for: Claude Code.

Or install dev-mcp, the plugin that ships this one along with the rest of its 4 skills.

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 matematic-patron-pr-review-pl

README.md
[![agentmods](https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/matematic-patron-pr-review-pl/github.svg)](https://agentmods.dev/skills/matematicsolutions/awesome-matematic-skills-pl/matematic-patron-pr-review-pl)
Your own site
<a href="https://agentmods.dev/skills/matematicsolutions/awesome-matematic-skills-pl/matematic-patron-pr-review-pl"><img src="https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/matematic-patron-pr-review-pl/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for matematic-patron-pr-review-pl

Your own site · 80×15
<a href="https://agentmods.dev/skills/matematicsolutions/awesome-matematic-skills-pl/matematic-patron-pr-review-pl"><img src="https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/matematic-patron-pr-review-pl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 302 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,603 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00302 $0.05603
Opus 5 $0.00151 $0.02802
Sonnet 5 $0.00060 $0.01121
Haiku 4.5 $0.00030 $0.00560

Measured 12d ago against content hash 30a26a4c9d27, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

matematic-patron-pr-review-pl 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 12d 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.

dev-mcp/skills/matematic-patron-pr-review-pl/SKILL.md · 362 lines

How it starts

The opening of the file, as written. The whole thing — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.

matematic-patron-pr-review-pl

Recenzent PR/diffow PATRON - polskiego LegalTech AI agenta dla kancelarii. Cherry-pick struktury z dograh v1.31.0 review-pr (BSD-2, 286 linii), zaadaptowane pod kontekst MateMatic.

Komplementarny do:

  • Wewnetrzny pipeline QA MateMatic dla tresci PL (artykuly, copy LI, BW) - ocena czytelnosci i poprawnosci. Ten skill ocenia diff kodu.
  • matematic-konstytucja-ai (w tym hubie) - dokument governance dla klienta. Ten chroni kod produktu.
  • Self-review pre-commit (6 zasad MateMatic) - poprzedza ten skill, sprawdza ogolne, ten skill nad nimi sprawdza repo-specific risks.

Kiedy uzywac

  • Recenzja PR przed merge do main w repo PATRON / KGLF / matematicsolutions MCP serwery
  • Pre-commit audit wlasnego diffu w PATRONie
  • Audyt zmian w komponentach krytycznych: mcp-security-gateway, audit_log, ring-policy, auth
  • Po duzej refaktoryzacji - sweep pod katem regresji
  • Przed pushem do origin po sesji 3+ commitow

Glowne tryby awarii w repo PATRON

  1. Multi-tenant - brak org scoping na request-reachable read/write (kancelaria A widzi sprawe kancelarii B)
  2. Authless route lub websocket - silently public endpoint
  3. Webhook bez signature verification lub trust w unsigned fields
  4. SQL pisany poza lib/db/*_client.ts - inkasacja warstwy
  5. Cache per-worker bez worker sync - stale state w innych procesach
  6. UI bypassuje generated SDK - direct fetch('/api/v1/...') zamiast typed client
  7. Migracja niebezpieczna na produkcji - NOT NULL bez backfilla, brak downgrade()
  8. MCP tool reimplementuje auth zamiast authenticate_mcp_request() (patrz matematic-mcp-fastmcp-instructions-pl w tym hubie)
  9. PII/cytat prawniczy w logach - naruszenie RODO + tajemnica adwokacka (art. 6 ust. 1 PrAdw + art. 3 ust. 3 RadcPrU)
  10. Brak audit_log entry dla operacji decyzyjnej (AI Act art. 12 record-keeping)

Read the full file on GitHub · 362 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. 12d ago First seen · 362 lines · 302 tokens per session scan A 30a26a4c9d27

Subscribe to this mod's changes

matematic-patron-pr-review-pl is a skill published in the GitHub repository matematicsolutions/awesome-matematic-skills-pl (6 stars, last pushed 19d ago), licensed MIT. It adds 302 tokens to every session and 5,603 once invoked, about $0.0015 per session on Opus 5. 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.