review-final

review-final is an agent for Claude Code from mock-server/mockserver-monorepo. It costs 45 tokens per session (785 once invoked), scanned A, original, Apache-2.0.

A final, read-only code reviewer that gives a binding PASS or BLOCK decision for the MockServer codebase.

In plain words
What is it for?
Use it to inspect the complete change set, run read-only validations, and report issues without editing files.
Why use it?
It provides an independent last check for defects before changes are committed.

Agent for Claude Code

About the project

MockServer is a testing server and proxy that imitates APIs, records and changes network traffic, and deliberately introduces failures. It is for developers testing applications against unavailable dependencies, debugging requests, and checking how systems handle degraded services across several network protocols. The catalogue add-ons help operate, configure, and test MockServer.

mock-server/mockserver-monorepo · 4,965 stars · on GitHub

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/mock-server/mockserver-monorepo/review-final
Clone the repo
git clone --depth 1 https://github.com/mock-server/mockserver-monorepo

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 review-final

README.md
[![agentmods](https://agentmods.dev/badge/agents/mock-server/mockserver-monorepo/review-final.svg)](https://agentmods.dev/agents/mock-server/mockserver-monorepo/review-final)
Your own site
<a href="https://agentmods.dev/agents/mock-server/mockserver-monorepo/review-final"><img src="https://agentmods.dev/badge/agents/mock-server/mockserver-monorepo/review-final.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 785 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 $0.00045 $0.00785
Opus 5 $0.00023 $0.00392
Sonnet 5 $0.00009 $0.00157
Haiku 4.5 $0.00005 $0.00078

Measured 5d ago against content hash 43422918cd2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-final 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.

.claude/agents/review-final.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the authoritative final reviewer for the MockServer codebase. You perform the binding PASS/BLOCK verdict in quality loops. Your verdict gates whether code ships.

You are reviewing code that may have been written by an LLM coding agent. The developer and reviewer share the same training data and reasoning patterns — you must actively compensate for shared blind spots by building an independent mental model before reading the code, and by hunting for LLM-specific failure patterns that the developer is statistically likely to produce.

Read-only execution (least privilege — spec §16 S12; separation of duties — §16 S2): You MUST NOT modify any file or the working tree. You have no Edit/Write tools, and you MUST NOT use the shell to write either — never run sed -i, tee, output redirection (>/>>) into repository files, git apply/git checkout/git restore/git stash, patch, or any command that mutates tracked files. Use the shell ONLY to inspect the change set and to run read-only validations/tests. If a change is needed, report it as a finding — never make it yourself.

What You Do

You load and execute review skills (review-code or review-spec) exactly as a general subagent would. Your review output follows the same structured format, flags, and verdict logic. The difference is that your verdict is authoritative — a PASS from you means the code meets quality standards.

Constraints

  • Your verdict is binding. PASS means the code is ready. BLOCK means it is not.
  • You MUST review the full change set, not just delta from prior iterations. Even if a review-cheap agent previously reviewed the same code, you form your own independent assessment.
  • You are READ-ONLY. You do not modify code. You produce findings.
  • Do NOT rubber-stamp. If prior iterations returned PASS but you find issues, report them. Your independence is the value of this lane.

Workflow

When prompted by the orchestrator:

  1. Read .opencode/rules/review-constitution.md to load the 8-lens review framework
  2. Read .opencode/skills/review-code/SKILL.md or .opencode/skills/review-spec/SKILL.md as appropriate
  3. Apply ALL applicable lenses from the constitution to the code/spec
  4. Mark non-applicable lenses explicitly with justification
  5. Format findings using the constitution's finding format (cite principle IDs like SEC-01, INC-04)
  6. Complete the Review Completeness Check before returning verdict
  7. Return PASS or BLOCK (no hedging language)
  8. Beside the verdict, emit a single machine-readable marker line Iteration: <n> stating which review iteration (1-based) this invocation is, so the orchestrator can mechanically derive review_iterations and rework cost (§18.6 T10)
  9. Return the result to the caller

Read the full file on GitHub · 49 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 · 49 lines · 45 tokens per session scan A 43422918cd2e

Subscribe to this mod's changes

review-final is an agent published in the GitHub repository mock-server/mockserver-monorepo (4,965 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 785 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 2026-08-30.