pr-code-review

A repeatable process for reviewing a pull request, which is a proposed set of code changes, together with its related Jira work item. It gathers context first, then runs several code-quality and standards checks and produces review comments in tables.

In plain words
What is it for?
Use it to review pull requests for functional intent, bugs, Java and Spring Boot practices, architecture, SOLID design, scenarios, testing, and issues already recorded in the project.
Why use it?
It prevents reviewers from judging code without understanding the requested change or its acceptance criteria. It also keeps the review focused on reported findings and avoids changing or committing code automatically by default.

Cursor rule for Cursor

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 rules/pallerana/agentic-loop-engineering-kit/pr-code-review
Clone the repo
git clone --depth 1 https://github.com/pallerana/agentic-loop-engineering-kit

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 6,028 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 $0.06028
Opus 5 $0.00000 $0.03014
Sonnet 5 $0.00000 $0.01206
Haiku 4.5 $0.00000 $0.00603

Measured yesterday against content hash 318f98054b11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pr-code-review 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.

.cursor/rules/pr-code-review.mdc · 426 lines

How it starts

The opening of the file, as written. The whole thing — 426 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Loop PR Code Review (your-service-*)

On-demand workflow for reviewing pull requests. Complements service-quality-drill.mdc (build/JaCoCo/CI/fix) — this rule owns context → review → humanized comment tables.

Also apply java-springboot-standards.mdc for all Java/Spring Boot patterns.

Invoke: @pr-code-review + PR URL/number, or "review this PR using our code review rule".

Default mode: report-only — do not auto-apply fixes or commit unless the user explicitly asks.

Workflow overview

Phase 0 (PR + Jira + type + feedback registry) → Pass 1 → Pass 2 → Pass 3 (routed by pr_type) → synthesize → net-new table

Phase 0 — Functional context (mandatory first)

Do not start ce-code-review or Bugbot until Phase 0 is complete.

0a. PR metadata and discussion

gh pr view <n-or-url> --json title,body,baseRefName,headRefName,url,comments,reviews
gh pr view <n-or-url> --comments   # when thread detail is needed

Write a Functional Context block (3–8 bullets):

  • Intent — what the PR claims to deliver.
  • Acceptance signals — must/should language, checklists in description.
  • Review thread themes — unresolved or recently resolved comments defining expected behavior.
  • Out of scope — explicit deferrals.

If no PR exists, use commit messages + linked docs; note context_source: branch-only.

0b. Jira ticket discovery and fetch

Scan PR title, body, commits, and review comments for keys: [A-Z][A-Z0-9]+-\d+ (e.g. PROJ-123).

For each unique key:

  1. Fetch via Atlassian MCP getJiraIssue (preferred).
  2. Fallback: Glean search or compiled jira-backlog.md if MCP unavailable — note jira_context: partial|unavailable in header.

Capture: summary, status, type, description/AC, parent epic, edge cases/NFRs.

Append Jira scope (key → requirement) and requirements trace (files/methods → AC). If fetch fails, add P2 row for missing context and continue.

Read the full file on GitHub · 426 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 · 426 lines · 0 tokens per session scan A 318f98054b11

Subscribe to this mod's changes

pr-code-review is a cursor rule published in the GitHub repository pallerana/agentic-loop-engineering-kit (4 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 6,028 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.