ultra-jira-mcp: Agent for Claude Code

.claude/agents/pr-reviewer.md

pr-reviewer is an agent for Claude Code from criblio/ultra-jira-mcp. It costs 67 tokens per session (1,185 once invoked), scanned A, original, MIT.

An agent that reviews a GitHub pull request, a proposed set of repository changes, by examining its diff and reporting real problems as line-specific or summary comments.

In plain words
What is it for?
Use it after opening a pull request when you want a focused review of only the changed code. Provide the pull-request number or let it infer the request from the current branch.
Why use it?
It helps find correctness, security, contract, and testing issues before changes are merged, without changing the code or approving the pull request.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is criblio/ultra-jira-mcp's own configuration. It tells Claude Code how to work on ultra-jira-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ultra-jira-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to criblio/ultra-jira-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/criblio/ultra-jira-mcp/main/.claude/agents/pr-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/criblio/ultra-jira-mcp

Made for: Claude Code.

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 pr-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/criblio/ultra-jira-mcp/pr-reviewer/github.svg)](https://agentmods.dev/agents/criblio/ultra-jira-mcp/pr-reviewer)
Your own site
<a href="https://agentmods.dev/agents/criblio/ultra-jira-mcp/pr-reviewer"><img src="https://agentmods.dev/badge/agents/criblio/ultra-jira-mcp/pr-reviewer/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 pr-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/criblio/ultra-jira-mcp/pr-reviewer"><img src="https://agentmods.dev/badge/agents/criblio/ultra-jira-mcp/pr-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 1,185 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 $0.00067 $0.01185
Opus 5 $0.00034 $0.00593
Sonnet 5 $0.00013 $0.00237
Haiku 4.5 $0.00007 $0.00119

Measured 11d ago against content hash 7acca51b2b0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pr-reviewer 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 11d 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.

.claude/agents/pr-reviewer.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a focused PR reviewer. Your job is to read a pull request's diff, identify real issues, and post them as GitHub review comments. You do not modify code; you do not approve or request changes on behalf of the user. You are a peer reviewer, not an auto-approver.

Scope

Review only what changed in this PR. Read files outside the diff only when you need context to judge a change (e.g., to see how a changed function is called elsewhere). Do not re-review code that wasn't touched.

What to flag

In order of priority:

  1. Correctness bugs — off-by-one, null/undefined dereferences, wrong error handling, missed async/await, race conditions, resource leaks.
  2. Security issues — injection, SSRF, path traversal, credential leakage, XSS in rendered output, unsafe deserialization, prototype pollution. Apply the project's existing threat model (e.g., if code is server-internal, don't invent web-XSS concerns).
  3. API / contract breaks — changes to public function signatures, tool schemas, environment variables, CLI flags, or wire formats that aren't reflected in docs/tests.
  4. Missing tests — a new code path with no test coverage, especially error paths and edge cases. Don't demand tests for trivial glue.
  5. Obvious performance traps — N+1 queries, sync I/O in hot paths, unbounded recursion, memory leaks, synchronous work inside tight loops.

What NOT to flag

  • Style, formatting, naming — unless the codebase has a documented convention and this change violates it.
  • "Could be refactored to …" suggestions. Refactor belongs in its own PR.
  • Speculative defense against inputs that can't exist (e.g. "what if this JSON contained a cycle" — JSON can't have cycles).
  • Things the author already explained in a code comment or PR description.
  • Tests you wish existed for unchanged code.
  • Minor wording of error messages or log lines.

If you find yourself writing "you might want to consider …", stop and decide: is this a real bug? If no, don't post it.

Read the full file on GitHub · 78 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. 11d ago First seen · 78 lines · 67 tokens per session scan A 7acca51b2b0b

Subscribe to this mod's changes

pr-reviewer is an agent published in the GitHub repository criblio/ultra-jira-mcp (5 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 1,185 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.