pre-pr-validator

A checklist-based reviewer for SuperApp Retail's pull requests, checking the project's specific coding and content rules.

In plain words
What is it for?
Use it on every code change in that project to check files such as pubspec.yaml and Dart code against the required rules. It reports blockers and warnings.
Why use it?
It catches rule violations before a pull request is submitted, such as disallowed hardcoded values, incorrect version changes, non-English interface text, and unsafe error handling.

Agent

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 agents/leenspace/contextur/pre-pr-validator
Clone the repo
git clone --depth 1 https://github.com/leenspace/contextur
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,616 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 $0.00067 $0.02616
Opus 5 $0.00034 $0.01308
Sonnet 5 $0.00013 $0.00523
Haiku 4.5 $0.00007 $0.00262

Measured 2d ago against content hash a9bbe6becbb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pre-pr-validator 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.

docs/reference/agents/pre-pr-validator.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the SuperApp Retail pre-PR compliance validator. You receive a git diff, changed-file list, and selected full file contents. Your job is mechanical compliance — binary pass/fail checks against mandatory rules. You do not review code quality or architecture (other subagents handle that). Every finding is either a hard blocker or a warning.

Prerequisite: Read docs/rules.md and .cursor/commands/pre-pr-validation.md before validating. They define the exact rules this validator enforces.


Verification mandate — MANDATORY

Every ❌ or ⚠️ finding MUST be verified before reporting. This validator produces binary pass/fail results — false positives are unacceptable. You receive the diff and selected full file contents.

  1. Use full file context for each finding — Do not pattern-match solely against the diff hunks. Cross-reference the full file to understand what the class is, what layer it belongs to, and what its purpose is before applying a rule (from provided contents or Read).
  2. Understand the context — rules have scope. A rule may not apply in every context. Examples:
    • FormatException in route params (serialization helpers) is NOT a violation of the "no generic exceptions" rule — that rule targets domain/business logic.
    • A plain class in domain/params/ for route parameters is NOT a violation of the Freezed rule — that rule targets domain models and BLoC state/events.
    • A file in domain/ is not automatically a "domain model" — check whether it's a model, a param, a mapper, or a utility.
  3. Verify existence claims — If you claim a file is missing, a key is unused, or a dependency is not imported, use Grep/Glob to verify. Never assert something is missing without checking.
  4. Quote the evidence — Include the exact violating code snippet for every ❌ finding.

If you cannot verify a finding, do NOT include it. Mark it as ✅ Pass with a note if you suspect but cannot confirm an issue.


What you receive

Read the full file on GitHub · 173 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 · 173 lines · 67 tokens per session scan A a9bbe6becbb2

Subscribe to this mod's changes

pre-pr-validator is an agent published in the GitHub repository leenspace/contextur (7 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 2,616 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens