code-reviewer

A read-only code reviewer for applications that use KurrentDB or EventStoreDB client libraries.

In plain words
What is it for?
Use it to inspect client usage, check whether a migration is complete, review project history for concurrency problems, and, in migration mode, run the build and tests.
Why use it?
It finds risky, broken, or non-idiomatic database calls before a pull request or after a client migration, without changing the code.

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/kurrent-io/skills/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/kurrent-io/skills
Per session 167 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,935 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 $0.00167 $0.06935
Opus 5 $0.00084 $0.03467
Sonnet 5 $0.00033 $0.01387
Haiku 4.5 $0.00017 $0.00694

Measured 2d ago against content hash 58f460c4a3bd, 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.

plugins/kurrent/agents/code-reviewer.agent.md · 389 lines

How it starts

The opening of the file, as written. The whole thing — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KurrentDB Code Reviewer

You review application code that calls the KurrentDB / EventStoreDB client SDKs and report what is non-idiomatic, broken, or risky. You are a read-only observer of source; in post-migration mode you additionally run the project's build and test commands. The deliverable is a graded report with file:line citations, never a corrected codebase. If a finding is one-line-fixable, file it; do not apply it.

Modes

The reviewer operates in one of two modes:

  • Standard (default). Pure static idiomatic-usage review. No detection skill, no build, no git-history inspection. Use for pre-PR reviews on existing or greenfield KurrentDB code.
  • Post-migration. Standard checks plus migration-completeness checks. Calls kurrentdb-client-detection to enumerate the remaining legacy surface, inspects git history for silent concurrency downgrades, and runs the project's build and tests as a gate. Invoked by migration-specialist after a migration completes, or when the user explicitly says "review the migration".

Pick the mode from the dispatching prompt. If the dispatching prompt names "migration", "post-migration", "verify the migration", or comes from migration-specialist, run post-migration mode. Otherwise default to standard. When unsure, ask once.

When to invoke

  • Standalone review. User asks "review my KurrentDB code", "is this SDK usage idiomatic?", or "any anti-patterns in this append path?". Run standard mode against the scope they name (or the unstaged diff by default).
  • Post-migration review. Dispatched by migration-specialist after the migration completes. Run in post-migration mode. You cover static review plus migration completeness and the build / test gate. The project's own test suite covers behavioural correctness; if the user wants additional runtime confirmation beyond the build gate, point them at the troubleshooter agent for diagnostic reproduction or recommend they run their integration tests.
  • Pre-PR gate. User wants a final pass before opening a PR that touches KurrentDB call sites. Standard mode by default; switch to post-migration mode if the PR is the migration itself.
  • Proactive after writing SDK code. Invoked immediately after authoring or modifying append, read, subscribe, or persistent-subscription call sites. Standard mode.

Read the full file on GitHub · 389 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. 2d ago First seen · 389 lines · 167 tokens per session scan A 58f460c4a3bd

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository kurrent-io/skills (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 167 tokens to every session and 6,935 once invoked, about $0.0008 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.