agentic-review

agentic-review is a skill for Claude Code, Codex from SZoloth/skill-pack. It costs 71 tokens per session (2,079 once invoked), scanned A, original, MIT.

A code-review workflow that uses several specialized reviewers and combines their findings. It examines local changes, commits, or differences between branches in a Git repository, where Git tracks code history.

In plain words
What is it for?
Use it after significant coding work, before a commit, to review staged or unstaged changes, specific commits, or a branch compared with the main branch.
Why use it?
It helps catch security, speed, design, and architecture problems before code is committed or pushed. The combined report organizes findings into actions to take.

Skill for Claude CodeCodex

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 skills/szoloth/skill-pack/agentic-review
Any agent
npx skills add SZoloth/skill-pack --skill agentic-review
Clone the repo
git clone --depth 1 https://github.com/SZoloth/skill-pack

Made for: Claude Code, Codex.

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 agentic-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/szoloth/skill-pack/agentic-review.svg)](https://agentmods.dev/skills/szoloth/skill-pack/agentic-review)
Your own site
<a href="https://agentmods.dev/skills/szoloth/skill-pack/agentic-review"><img src="https://agentmods.dev/badge/skills/szoloth/skill-pack/agentic-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,079 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 $0.00071 $0.02079
Opus 5 $0.00036 $0.01040
Sonnet 5 $0.00014 $0.00416
Haiku 4.5 $0.00007 $0.00208

Measured 5d ago against content hash 9b0b4e16c9a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentic-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 5d 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.

skills/agentic-review/SKILL.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Code Review

Deep, multi-agent code review for personal repos. Analyzes changes, prioritizes files, spawns specialized review agents in parallel, and synthesizes actionable findings.

When to Use

  • After writing significant code, before committing
  • Before pushing a branch
  • Reviewing specific commits
  • Comparing branches (e.g., feature vs main)

Usage

# Review all local changes (staged + unstaged)
skill agentic-review

# Review only staged changes
skill agentic-review --staged

# Review specific commit(s)
skill agentic-review abc123
skill agentic-review abc123..def456

# Review branch diff against main
skill agentic-review --branch feature-branch
skill agentic-review --branch HEAD  # current branch vs main

How It Works

Phase 1: Detect & Gather Changes

First, determine what to review based on arguments:

# Check if we're in a git repo
git rev-parse --is-inside-work-tree 2>/dev/null || echo "NOT_GIT_REPO"

# Get current branch
git branch --show-current

# Check for changes
git status --porcelain        # Any local changes?
git diff --stat               # Unstaged changes stats
git diff --cached --stat      # Staged changes stats

Determine review scope from $ARGUMENTS:

Argument What to Review
(empty) All local changes (staged + unstaged)
--staged Only staged changes
abc123 Specific commit
abc123..def456 Commit range
--branch NAME Branch diff vs main/master
--branch HEAD Current branch vs main/master

Phase 2: Pre-Scan & Prioritize Files

Analyze changed files to recommend review order:

# Get changed files with stats
git diff --numstat HEAD~1 2>/dev/null || git diff --numstat

# For each file, assess:
# - Lines changed (more = higher priority)
# - File type (src > test > config > docs)
# - Risk areas (auth, security, data, API)

Prioritization Heuristics:

  1. HIGH: Security-related files (auth, crypto, permissions, secrets)
  2. HIGH: Core business logic (models, services, controllers)
  3. MEDIUM: API endpoints, data access
  4. MEDIUM: Configuration files that affect runtime
  5. LOW: Tests, documentation, styling

Read the full file on GitHub · 293 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. 5d ago First seen · 293 lines · 71 tokens per session scan A 9b0b4e16c9a1

Subscribe to this mod's changes

agentic-review is a skill published in the GitHub repository SZoloth/skill-pack (14 stars, last pushed 5mo ago), licensed MIT. It adds 71 tokens to every session and 2,079 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

reply-email

Draft an email reply in your voice. Use when you want to reply to an email, draft a response, or answer a message.

marian-kamenistak/claude-email-assistant · 30 tokens

claudeshrink

Automatically compress large natural text or log files before processing. Trigger when the user pastes massive text blobs, or asks to analyze a large file (logs, docs, transcripts), or provides a prompt that is too large for the context window. DO NOT trigger on source code files or structural data (JSON, XML).

g-akshay/ClaudeShrink · 68 tokens

bug-report-writer

Converts rough notes, casual descriptions, console errors, or quick observations into professional, complete bug reports — exported as a formatted Excel (.xlsx) file ready for Excel, Google Sheets, Jira, or Azure DevOps. Use this skill whenever the user mentions: "write a bug report", "log a bug", "report this issue"…

ShreyasBh02/AI-Skills-Collection · 186 tokens

daily-planner-prioritizer

Creates a smart, time-blocked daily plan from a user's task dump, meetings, errands, habits, and goals — then outputs BOTH a clean text summary in chat AND a formatted Excel (.xlsx) schedule file. Covers work tasks, meetings, personal errands, health/exercise reminders, and QA-specific tasks (test runs, bug triage…

ShreyasBh02/AI-Skills-Collection · 187 tokens

recipe-grocery-list

Converts one or more recipes, a weekly meal plan, or even just dish names into a clean, categorized, deduplicated grocery shopping list — with quantities scaled to the number of servings needed. Also exports a formatted Excel (.xlsx) shopping list file. Use this skill whenever the user mentions: "make a grocery list"…

ShreyasBh02/AI-Skills-Collection · 167 tokens

test-case-generator

Generates comprehensive, structured test cases from feature descriptions, user stories, requirements, or acceptance criteria — and exports them as a formatted Excel (.xlsx) file ready for use in Excel or Google Sheets. Use this skill whenever the user mentions: "write test cases", "generate test cases", "create test…

ShreyasBh02/AI-Skills-Collection · 169 tokens