An adversarial review skill for changed code that checks for security and other failure risks. It focuses on the most serious findings, including issues covered by the OWASP security guidelines, rather than confirming that tests pass.

Use it after a code change, when preparing a pull request, or when asking whether a change is safe or secure.

It looks for ways code could break, leak data, or be abused, including cases ordinary tests may miss. Limiting the review to changed lines keeps the results focused.

reviewer — Skill for Claude Code by umangbuilds

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.

Any agent

npx skills add umangbuilds/dhurandhar-os --skill reviewer

Clone the repo

git clone --depth 1 https://github.com/umangbuilds/dhurandhar-os

Made for: Claude Code.

Or install dhurandhar-os, the plugin that ships this one along with the rest of its 10 skills, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/umangbuilds/dhurandhar-os/reviewer/github.svg)](https://agentmods.dev/skills/umangbuilds/dhurandhar-os/reviewer)

Your own site

<a href="https://agentmods.dev/skills/umangbuilds/dhurandhar-os/reviewer"><img src="https://agentmods.dev/badge/skills/umangbuilds/dhurandhar-os/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/umangbuilds/dhurandhar-os/reviewer"><img src="https://agentmods.dev/badge/skills/umangbuilds/dhurandhar-os/reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 160 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,957 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.

Model	Per session	Once invoked
Fable 5.1	$0.00160	$0.02957
Opus 5	$0.00080	$0.01478
Sonnet 5	$0.00032	$0.00591
Haiku 4.5	$0.00016	$0.00296

Measured 12d ago against content hash e1e186018558, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

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 12d 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/reviewer/SKILL.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewer

Reviewer is the adversarial layer. Its job is not to validate that the code works — that's the test suite's job. Its job is to find what breaks under attack, what leaks under load, what fails when the regulator inspects, what surprises the on-call engineer at 2am.

Five real findings beat thirty noisy ones.

When this skill activates

Auto-trigger conditions:

git diff output appearing in the conversation.
PR created or referenced.
"Review this," "check this," "is this safe," "is this secure," "look at the diff," "what could go wrong here."
After the Builder skill completes a task batch (handoff).

Explicit invocation: "use reviewer on this diff."

Does not activate on: spec writing, brainstorming, hiring, full-codebase audit (use a Tier 2 audit kit for full audit).

Review scope — what gets scanned

Reviewer is diff-aware. It scans only the changed lines, not the full codebase. This keeps signal-to-noise high.

Coverage:

OWASP Top 10:2025 — Injection (A03), Broken Access Control (A01), Cryptographic Failures (A02), Insecure Design (A04), Security Misconfiguration (A05), Vulnerable Components (A06), Identification & Authentication Failures (A07), Software & Data Integrity Failures (A08), Security Logging & Monitoring Failures (A09), Server-Side Request Forgery (A10).
ASVS 5.0 — V2 (Authentication), V3 (Session), V5 (Validation), V7 (Cryptography), V8 (Data Protection), V9 (Communication), V10 (Malicious Code), V13 (API), V14 (Configuration).
Agentic AI ASI01–ASI10 — prompt injection, tool poisoning, excessive agency, sensitive information disclosure via tool use, etc.
Language-specific quirks — Python (eval, pickle, subprocess), JavaScript (eval, dangerouslySetInnerHTML, prototype pollution), Java (deserialisation), SQL (injection patterns), shell (command injection), Go (race conditions in goroutines), Rust (unsafe blocks).

Out of scope at v0.1:

Full DPDPA / GDPR / CCPA / HIPAA compliance audit. Reviewer routes to Tier 2 add-ons.
Full RBI Digital Lending compliance audit. Reviewer routes to v0.2 deferral note.
Performance / load testing. Different skill class.
Architecture review. PRD Writer territory.

Read the full file on GitHub · 208 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.

12d ago First seen · 208 lines · 160 tokens per session scan A e1e186018558

Subscribe to this mod's changes

reviewer is a skill published in the GitHub repository umangbuilds/dhurandhar-os (1 stars, last pushed 4mo ago), licensed MIT. It adds 160 tokens to every session and 2,957 once invoked, about $0.0008 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.

Code review Security

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

openclaw/clawhub · 20 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

code-reviewer

Code review specialist focused on patterns, bugs, security, and performance.

RightNow-AI/openfang · 17 tokens

full-repo-review

Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.

notque/vexjoy-agent · 22 tokens

agent-teams-simplify-and-harden

Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…

LeoYeAI/openclaw-master-skills · 115 tokens