code-reviewer

A code-review agent for generated code and language bindings, which connect one programming language to another. It checks generated web handlers, API schemas, validation, error handling, memory ownership, and middleware behavior.

In plain words
What is it for?
Use it to review code generators, API clients or servers, foreign-function interfaces, and HTTP middleware across Python, Node.js, Ruby, PHP, Elixir, and Rust.
Why use it?
Generated code and cross-language bindings can fail in ways that ordinary reviews overlook, including crashes, unsafe memory use, broken errors, and inconsistent behavior between languages.

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/goldziher/spikard/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/Goldziher/spikard
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 450 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 $0.00026 $0.00450
Opus 5 $0.00013 $0.00225
Sonnet 5 $0.00005 $0.00090
Haiku 4.5 $0.00003 $0.00045

Measured 2d ago against content hash 75c7fbabba96, 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 2d 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.

.ai-rulez/agents/code-reviewer.md · 45 lines

What it actually says

code-reviewer

Review Focus Areas

Codegen Output Quality

  • Generated handlers implement Handler trait correctly
  • OpenAPI/GraphQL/AsyncAPI specs round-trip without data loss
  • Schema validators enforce constraints (types, formats, min/max, patterns)
  • Generated code is tested against testing_data/ fixtures

FFI Safety

  • No .unwrap() or panics in binding crates (spikard-py, spikard-node, spikard-rb, spikard-php, spikard-elixir)
  • PyO3: returns PyResult, converts errors via PyErr::new_err
  • napi-rs: returns napi::Result, errors via napi::Error::from_reason
  • magnus: returns Result<T, magnus::Error>
  • ext-php-rs: returns ext-php-rs Result, throws PHP exceptions
  • rustler: returns NIF-safe types, no panics (crashes BEAM VM)
  • Arc-based ownership for cross-FFI data (RequestData fields)
  • GIL released for CPU-intensive Rust code in PyO3 (py.allow_threads)
  • ThreadsafeFunction used for async Node.js callbacks
  • No blocking the scheduler in NIF functions (use DirtyCpu)

HTTP Middleware

  • Tower middleware ordering matches docs/adr/0002-runtime-and-middleware.md
  • Lifecycle hooks execute in order: onRequest, preValidation, preHandler, onResponse, onError
  • Auth middleware returns 401 with ProblemDetails, not raw errors
  • ServerConfig structs exposed to all bindings with type safety
  • Zero-cost when middleware/hooks not registered

Cross-Binding Consistency

  • Same behavior across Python, Node, Ruby, PHP, Elixir for identical fixtures
  • HandlerError variants map to correct HTTP status codes (400, 401, 404, 500)
  • Response body types (Json, Text, Binary, Empty) handled in all bindings
  • No duplicate business logic in binding crates
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. 2d ago First seen · 45 lines · 26 tokens per session scan A 75c7fbabba96

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository Goldziher/spikard (118 stars, last pushed 20d ago), licensed MIT. It adds 26 tokens to every session and 450 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

merge-conflict-resolver

Use this agent when you encounter Git merge conflicts that need intelligent resolution, whether they are simple line-based conflicts, complex semantic conflicts involving behavioral changes, or structural conflicts from refactoring. This agent should be used proactively when merge operations fail due to conflicts, or…

module-federation/core · 264 tokens

git-conflict-resolver

Use this agent when you need to resolve git merge conflicts, merge branches, or handle complex git operations involving branch integration. This includes resolving conflicts in files, choosing between conflicting changes, merging feature branches into main/master, rebasing branches, or cleaning up merge-related…

module-federation/core · 343 tokens

config-auditor

Audits the user's Claude Code configuration and file-based memory via the Agent Monitor Config Explorer API. Detects surface sprawl (skills, agents, commands across user vs project scope), duplicate or overlapping skills/subagents, hooks that run shell commands or POST to the network, and stale or oversized memory…

hoangsonww/Claude-Code-Agent-Monitor · 85 tokens

budget-sentinel

Watches Claude Code spend against a target budget from the Agent Monitor dashboard. Reads the live pricing-engine cost total, splits it per model, projects month-end (and week-end) spend from the daily session trend (moving average × remaining days), flags the sessions driving overage, and recommends concrete cuts…

hoangsonww/Claude-Code-Agent-Monitor · 116 tokens

token-economist

Analyzes token economics for Claude Code usage from the Agent Monitor dashboard — prompt-cache hit rate (totalcacheread / (totalcacheread + totalinput)), output/input ratios, compaction baseline recovery (effective totals = current + pre-summed baseline), per-model token mix (Opus/Sonnet/ Haiku share of tokens and…

hoangsonww/Claude-Code-Agent-Monitor · 110 tokens

dashboard-operator

Operates the Claude Code Agent Monitor dashboard. Verifies the API is up on port 4820, summarizes live state from /api/stats (sessions, agents, events, websocket connections), probes endpoints, reports config from /api/settings/info and self-update status from /api/updates/status, and guides the user through…

hoangsonww/Claude-Code-Agent-Monitor · 92 tokens