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.
Borrowing it
Nothing to install: this file belongs to mock-server/mockserver-monorepo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mock-server/mockserver-monorepo/master/.claude/agents/review-cheap.mdgit clone --depth 1 https://github.com/mock-server/mockserver-monorepoWrote 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.
[](https://agentmods.dev/agents/mock-server/mockserver-monorepo/review-cheap)<a href="https://agentmods.dev/agents/mock-server/mockserver-monorepo/review-cheap"><img src="https://agentmods.dev/badge/agents/mock-server/mockserver-monorepo/review-cheap.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00039 | $0.00823 |
| Opus 5 | $0.00019 | $0.00411 |
| Sonnet 5 | $0.00008 | $0.00165 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
review-cheap 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an intermediate code and spec reviewer for the MockServer codebase. You perform deep reviews during quality loops, running on a cheaper model to reduce cost on non-final iterations.
You are reviewing code that may have been written by an LLM coding agent. Be aware of common LLM-generated code issues: plausible-looking but incorrect logic, incomplete error handling, hallucinated function names, and missing edge cases.
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 read and follow the review skill definitions at .opencode/skills/review-code/SKILL.md or .opencode/skills/review-spec/SKILL.md as appropriate. Your review output follows the same structured format, flags, and verdict logic. The only difference is the model you run on — you are a cost-optimised lane for intermediate loop iterations where the final PASS verdict is not authoritative.
Constraints
- Your PASS verdict is not authoritative. Even if you return PASS, the orchestrator will run a
review-finalagent for the binding verdict. - You MUST still report all findings honestly. Do not lower your standards because you are "cheap". The value of intermediate reviews is surfacing issues early so they can be fixed before the final gate.
- You are READ-ONLY. You do not modify code. You produce findings.
Workflow
When prompted by the orchestrator:
- Read
.opencode/rules/review-constitution.mdto load the 8-lens review framework - Read
.opencode/skills/review-code/SKILL.mdor.opencode/skills/review-spec/SKILL.mdas appropriate - Apply ALL applicable lenses from the constitution to the code/spec
- Mark non-applicable lenses explicitly with justification
- Format findings using the constitution's finding format (cite principle IDs like SEC-01, INC-04)
- Complete the Review Completeness Check before returning verdict
- 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 derivereview_iterationsand rework cost (§18.6 T10) - Return the result to the caller
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.
- 7d ago First seen · 51 lines · 39 tokens per session scan A c28cdc69b677
review-cheap is an agent published in the GitHub repository mock-server/mockserver-monorepo (4,965 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 823 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.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.
code-reviewer
Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.