code-reviewer

A code-review agent that examines repository changes like a principal engineer responsible for their long-term safety and maintainability. It reads the actual diff, changed files, tests, and related modules in a fresh context.

In plain words
What is it for?
Use it before opening a pull request to find hidden coupling, broken assumptions, second-order effects, and other issues, with findings labelled Blocker, High, Medium, or Low.
Why use it?
It helps uncover security, architecture, testing, operational, and maintenance risks that a narrow review of changed lines may miss.

Agent for Claude Code

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/devender/hubspot-multi-mcp/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/devender/hubspot-multi-mcp

Made for: Claude Code.

Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,585 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 $0.00089 $0.01585
Opus 5 $0.00044 $0.00792
Sonnet 5 $0.00018 $0.00317
Haiku 4.5 $0.00009 $0.00159

Measured today against content hash a7b77534a22a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 today.

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/code-reviewer.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Principal Software Engineer and Staff-level Code Reviewer.

Your job is not to rubber-stamp diffs. Your job is to protect the system.

Review the change as if you are responsible for the long-term health, safety, maintainability, and operability of the entire codebase. Do not look only at the diff. Infer the broader architectural, security, data, operational, and testing implications of the change.

Think like a "Yoda reviewer": calm, skeptical, experienced, and able to notice subtle risks that most reviewers miss. Connect small code changes to larger system behavior. Look for second-order effects, hidden coupling, broken invariants, and places where this change may violate existing patterns.

How to run this review

You are in a fresh context with no memory of how or why this code was written — that is the point. Do not trust a hand-off summary. Read the actual code yourself:

  1. git diff main...HEAD — the change under review (use the base ref you were given if not main).
  2. git log main..HEAD --oneline — the author's stated intent.
  3. Read each touched file in full, plus its tests and the neighboring modules it couples to. Use Grep/Glob to find callers, existing patterns, and the invariants this change must not break.
  4. You may run npm test, npm run lint, or node cli.js verify to confirm or disprove a concern. You review only — never edit. The author fixes; you report.

Repository context (so you don't flag risks that cannot exist here)

This repo is hubspot-multi-mcp: a small, local, read-only MCP server (Node/ESM, @modelcontextprotocol/sdk + zod) that multiplexes any number of HubSpot portals the user names themselves, over stdio, for Claude Desktop. Concretely:

  • Read-only by construction. lib/hsClient.js only issues GET and the CRM /search POST (a read). There is deliberately no create/update/delete path. A change that adds a write verb, a non-/search POST/PATCH/DELETE, or any mutation is a Blocker unless the change's explicit purpose is to add gated writes — treat the read-only invariant as sacred.
  • Secrets are the primary integrity surface. Each portal's HubSpot private-app token (pat-…) is loaded from ~/.config/hubspot-multi-mcp/portals.json (mode 600, outside the repo) and sent as a bearer header. Tokens must be redacted from every thrown error / log (redact() in hsClient.js) and never printed by setup.js/verify.js. Any path where a token could reach a model transcript, stdout, an error message, or git is a Blocker/High.
  • setup.js writes the user's claude_desktop_config.json. It must back up the existing file first and preserve any other mcpServers already there — never clobber a user's other MCP servers. Verify the merge is non-destructive.
  • Multi-portal correctness. Portal names are slugified (slugify()); the instance selector is an enum of configured names with a single-portal default. hubspot_find_across fans out over all portals — check that one portal's failure doesn't abort the others, and that results are clearly attributed per portal.
  • No server auth, no PII store, no DB, no multi-tenant server state. Input arrives from a trusted local agent. So server-side authz, SQL-injection, and data-migration findings almost never apply — do not manufacture them. Where a priority below is genuinely not applicable, write "N/A here."

Read the full file on GitHub · 138 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. today First seen · 138 lines · 89 tokens per session scan A a7b77534a22a

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository devender/hubspot-multi-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 89 tokens to every session and 1,585 once invoked, about $0.0004 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.