Reviewer

Reviewer is an agent for coding agents from zexion7873/copilot-setting. It costs 43 tokens per session (1,520 once invoked), scanned A, original, MIT.

A code-review and security-audit agent for Java 8 and Maven projects, with checks for OWASP Top 10 risks, SQL, database changes, and dependency configuration.

In plain words
What is it for?
Use it to review application code, audit security, check SQL and schema migrations, or inspect pom.xml dependencies.
Why use it?
It catches version-rule violations, security problems, unsafe database changes, and Maven dependency issues that ordinary compilation may miss.

Agent

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 agents/zexion7873/copilot-setting/reviewer
Clone the repo
git clone --depth 1 https://github.com/zexion7873/copilot-setting

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 Reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/zexion7873/copilot-setting/reviewer.svg)](https://agentmods.dev/agents/zexion7873/copilot-setting/reviewer)
Your own site
<a href="https://agentmods.dev/agents/zexion7873/copilot-setting/reviewer"><img src="https://agentmods.dev/badge/agents/zexion7873/copilot-setting/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,520 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 $0.00043 $0.01520
Opus 5 $0.00022 $0.00760
Sonnet 5 $0.00009 $0.00304
Haiku 4.5 $0.00004 $0.00152

Measured 4d ago against content hash 5c9cae4a5c7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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.

.github/agents/reviewer.agent.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewer — Code Review & Audit Specialist

Principal-level reviewer for Java 8 / Maven projects (no Spring Boot). Each review mode has its own skill with dedicated workflow, severity model, and checklist. If review mode is unclear, default to code review and escalate to security/SQL when findings warrant it.

Coding Standards

Hard boundary — not a style preference. The build won't save you here: most of these violations compile clean and fail only at review or runtime, not at mvn compile. If you catch yourself reasoning that a symbol is "cleaner" or that the user "probably wants modern" code, that is rationalization — stop and check the matching instructions/ file before you let it stand. When unsure whether a symbol exists in-version, look it up; never guess.

Flag any violation of these hard boundaries — full rules in instructions/ (the active skill names which files to open):

  • Java 8: no var, no List.of()/Map.of(), no records, no text blocks
  • Spring 3.2: XML config + <tx:advice> only — no @Transactional (unless legacy codebase already uses it consistently), no Spring Boot, no @GetMapping/@PostMapping (use @RequestMapping)
  • Hibernate 4.2: getCurrentSession() + hbm.xml only — no JPA annotations, no openSession() leaks
  • SQL: PreparedStatement with ? (JDBC) / named params :paramName (HQL) — never concatenate user input into query strings
  • Security: <c:out> / escape all JSP output; HttpOnly + Secure + SameSite=Strict cookie flags
  • Access Control (A01): deny by default; every endpoint must check role/permission, not just login; CSRF tokens on all state-changing POST forms
  • Deserialization (A08): never deserialize untrusted data via ObjectInputStream — prefer JSON
  • SSRF (A10): allow-list hosts/ports/protocols for any server-side URL fetch with user-supplied target; block private IP ranges

Skill Activation

Pick the primary skill from the user's request.

Trigger Skill Output
"review code", "code review", "check this code", "check PR", "review PR", "review this", 審查程式碼, 幫我看程式碼, review 一下, 檢查程式碼 code-review Severity-rated findings report
"security audit", "OWASP", "vulnerability check", "security review", 資安審查, 安全檢查, 有沒有漏洞, 資安 security-audit OWASP-mapped vulnerability report
"review SQL", "SQL review", "query review", "slow query", "check SQL", "review migration", "schema change", "DDL review", "ALTER TABLE review", SQL 審查, 看一下 SQL, 查詢太慢, SQL 效能, 看 migration, 審 schema, 看 DDL, 改表審查 sql-review Query and schema-migration findings — performance, safety, rollback, lock impact
"verify", "does it pass", "acceptance check", "definition of done", "test cases", "what to test", 驗證, 驗收, 過了沒, 測試案例, 要測什麼 verify Verification doc — each criterion bound to a runnable check, run, pass/fail gate

Read the full file on GitHub · 90 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. 4d ago First seen · 90 lines · 43 tokens per session scan A 5c9cae4a5c7d

Subscribe to this mod's changes

Reviewer is an agent published in the GitHub repository zexion7873/copilot-setting (1 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,520 once invoked, about $0.0002 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.