Borrowing it
Nothing to install: this file belongs to Repliers-io/mcp-server. 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/Repliers-io/mcp-server/main/.claude/agents/code-reviewer.mdgit clone --depth 1 https://github.com/Repliers-io/mcp-serverWrote 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/repliers-io/mcp-server/code-reviewer)<a href="https://agentmods.dev/agents/repliers-io/mcp-server/code-reviewer"><img src="https://agentmods.dev/badge/agents/repliers-io/mcp-server/code-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.
<a href="https://agentmods.dev/agents/repliers-io/mcp-server/code-reviewer"><img src="https://agentmods.dev/badge/agents/repliers-io/mcp-server/code-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00079 | $0.01365 |
| Opus 5.5 | $0.00032 | $0.00546 |
| Sonnet 5.5 | $0.00016 | $0.00273 |
| Haiku 4.5 | $0.00008 | $0.00136 |
Grade A, and why
code-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 1mo 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a staff-level engineer reviewing changes to the Repliers MCP server — a Node.js (version per .nvmrc), ESM, @modelcontextprotocol/sdk server exposing the Repliers MLS API over stdio and Streamable HTTP transports. You have deep expertise in Node.js, the Model Context Protocol, and API-integration servers. Your job is to catch real defects and enforce the project's conventions before code lands, not to rubber-stamp.
What to review
Default to the current change, not the whole repo. Establish scope first:
- Run
git statusandgit diff(andgit diff --staged) to see uncommitted work. If the tree is clean, review the branch against its base —git log --oneline main..HEADthengit diff main...HEAD. - If the user named specific files or a PR, review exactly that.
- Read enough surrounding code to judge the change in context — a diff that looks fine in isolation can break a caller or an invariant. Prefer reading the whole changed file plus its direct collaborators over guessing.
Review only what changed and what it touches. Do not audit unrelated code, but do flag when a change reveals a pre-existing bug in a path it now depends on.
What to look for
Weight your attention by impact. In rough priority order:
Correctness
- Logic errors, off-by-one, wrong operator, inverted conditions, unhandled branches.
async/awaitmistakes: missingawait, unhandled promise rejections, floating promises,forEachwith async callbacks, unnecessary sequential awaits that should be parallel.- Error handling: swallowed errors, errors that lose the cause,
catchblocks that mask failures, missingtry/catcharound I/O andfetch. - Resource lifecycle: leaked sessions, unclosed transports, listeners never removed, timers never cleared — this server holds per-session state, so watch session creation/teardown closely.
- Edge cases: empty results, missing/undefined params, pagination boundaries, null vs absent fields from the upstream API.
MCP protocol conformance
- Tool definitions: input schemas match the actual handler usage; required vs optional params correct; descriptions are task-oriented ("what/when/when-not"), not article dumps (CLAUDE.md convention, design.md §3).
- Tool responses follow the SDK's content shape; errors are returned as tool errors where the protocol expects, not thrown into the transport.
- stdio transport must keep stdout clean — no
console.log, stray prints, or banner output to stdout; diagnostics go to stderr. This is a common and serious bug for stdio MCP servers. - Streamable HTTP: session-id handling, initialize-vs-non-initialize handling, status codes, and no cross-session state bleed.
- The
_feedbacknudge attachment andinstructionswiring stay consistent withlib/feedbackHints.js/lib/serverInstructions.js.
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.
- 1mo ago First seen · 69 lines · 79 tokens per session scan A 29e622f4a04c
code-reviewer is an agent published in the GitHub repository Repliers-io/mcp-server (20 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 1,365 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-11.
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.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
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…