jira-dev-mcp: Skill for Claude Code

.agents/skills/code-review/SKILL.md

code-review is a skill for Claude Code from nianyi778/jira-dev-mcp. It costs 28 tokens per session (3,018 once invoked), scanned A, original, MIT.

A code-review skill for checking repository changes, reviewing pull requests, and assessing code quality. A pull request is a proposed set of changes for others to review before merging.

In plain words
What is it for?
Use it to review the current branch against another branch, perform a self-review, or review a pull request by number.
Why use it?
It gives developers a defined process for finding problems in their own changes or in someone else’s proposed changes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; names the TodoWrite tool; installed under .agents/ (shared by several agents).

This is nianyi778/jira-dev-mcp's own configuration. It tells Claude Code how to work on jira-dev-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 jira-dev-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nianyi778/jira-dev-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/nianyi778/jira-dev-mcp/main/.agents/skills/code-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/nianyi778/jira-dev-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 code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/nianyi778/jira-dev-mcp/code-review/github.svg)](https://agentmods.dev/skills/nianyi778/jira-dev-mcp/code-review)
Your own site
<a href="https://agentmods.dev/skills/nianyi778/jira-dev-mcp/code-review"><img src="https://agentmods.dev/badge/skills/nianyi778/jira-dev-mcp/code-review/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 code-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/nianyi778/jira-dev-mcp/code-review"><img src="https://agentmods.dev/badge/skills/nianyi778/jira-dev-mcp/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,018 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 $0.00028 $0.03018
Opus 5.5 $0.00011 $0.01207
Sonnet 5.5 $0.00006 $0.00604
Haiku 4.5 $0.00003 $0.00302

Measured 2mo ago against content hash 465d942588a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 2mo 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.

.agents/skills/code-review/SKILL.md · 366 lines

How it starts

The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Skill

Comprehensive code review skill that combines PR review, self-review, and quality checks.

Usage

/code-review                # Self-review: current branch vs main
/code-review <branch>       # Self-review: current branch vs specified branch
/code-review pr <number>    # PR review: review the specified PR

The argument is available as $ARGUMENTS.

Argument Parsing

$ARGUMENTS parsing:
- Empty → Self-review mode (base=main)
- "pr <number>" → PR review mode (use gh pr diff)
- Otherwise → Self-review mode (base=specified branch)

Review Process

IMPORTANT: Use Serena MCP extensively to analyze code efficiently while minimizing token consumption.

CRITICAL: Before starting any code review, you MUST read and understand the implementation guidelines:

  • Read @~/.claude/templates/frontend-implementation-guidelines.md for frontend code reviews
  • Read @~/.claude/templates/backend-implementation-guidelines.md for backend code reviews
  • Apply the specific principles from these guidelines during your review

Step 1: Get Changes

For Self-Review (no args or branch name):

# Get current branch name
git branch --show-current

# Determine base branch (use main if $ARGUMENTS is empty, otherwise use $ARGUMENTS)
BASE_BRANCH=${ARGUMENTS:-main}

# Get list of changed files
git diff $BASE_BRANCH...HEAD --name-status

# Get commit history
git log $BASE_BRANCH..HEAD --oneline

# Get detailed diff
git diff $BASE_BRANCH...HEAD

For PR Review (pr <number>):

# Get PR information
gh pr view <number>

# Get PR diff
gh pr diff <number>

Step 2: Quality Check (All Files)

Perform quality checks on all changed files before detailed review:

Code Quality:

  1. Detect unused code (variables, parameters, functions, classes)
  2. Detect commented-out code blocks
  3. Detect unreachable code branches

Comment Quality:

  1. Detect progress/completion declarations ("implemented", "done", etc.)
  2. Detect date or version references in comments

Read the full file on GitHub · 366 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. 2mo ago First seen · 366 lines · 28 tokens per session scan A 465d942588a3

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository nianyi778/jira-dev-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 28 tokens to every session and 3,018 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories

code-review

Review code for quality, maintainability, and correctness.

PrefectHQ/fastmcp · 13 tokens

release-pr-review

Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…

cyanheads/obsidian-mcp-server · 136 tokens

github-commenting

How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.

juspay/neurolink · 41 tokens

vibecheck

Use immediately before declaring a task or session done—run the discipline checks that catch scope creep, leftover artifacts, unsolicited refactoring, and inflated prose, and block the completion claim on any failure unless the operator supplies a recorded override reason.

mtarcure/claude-vibe-squad · 51 tokens

differential-review

Use when a proposed change claims to preserve or intentionally alter behavior and the delta must be proven between baseline and candidate—run both states, predict each observable shift, then compare return values, persistence, emitted events, logs, exit codes, wire formats, timing, errors, empty cases, and boundaries.…

mtarcure/claude-vibe-squad · 80 tokens

semgrep-rule-author

Use after a defect pattern is confirmed and you need a reusable Semgrep detector for sibling instances: derive syntactic or taint rules from vulnerable and safe fixtures, encode project sanitizers, and measure repository-wide false positives. Not for choosing generic rulesets or scanning only a change.

mtarcure/claude-vibe-squad · 61 tokens