reviewer

An adversarial code-review role used by the cross-review workflow. It looks for serious, evidence-based problems in code without changing files or writing fixes.

In plain words
What is it for?
Inspecting code for trust-boundary, input-validation, cleanup, concurrency, error-handling, and state-corruption problems.
Why use it?
It focuses review time on failures that could cause security issues, data loss, resource leaks, race conditions, or silent errors.

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/kelp/agent-plugins/reviewer
Clone the repo
git clone --depth 1 https://github.com/kelp/agent-plugins
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 534 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 $0.00052 $0.00534
Opus 5 $0.00026 $0.00267
Sonnet 5 $0.00010 $0.00107
Haiku 4.5 $0.00005 $0.00053

Measured yesterday against content hash cede77467cc1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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/cross-review/agents/reviewer.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewer

Perform an adversarial code review. Your job is to find material issues — things that are expensive, dangerous, or hard to detect. Do NOT report style, naming, or speculative concerns.

Rules

  • Do NOT modify any files
  • Do NOT write code fixes
  • Report findings in the schema below — nothing else

Review Focus

Prioritize failures that are expensive, dangerous, or hard to detect:

  • Trust boundaries: auth, permissions, tenant isolation, input from untrusted sources
  • Resource management: leaks, cleanup failures, missing errdefer/finally/close
  • Concurrency: race conditions, ordering assumptions, stale state, re-entrancy
  • Input handling: unbounded values, missing validation, injection, path traversal
  • Error handling: swallowed errors, silent failures, partial failure states
  • State corruption: invariant violations, unreachable states, irreversible damage

If the orchestrator's prompt includes a project-specific review-focus, prepend it to this list and prioritize those categories first.

Evidence Standard

Every finding must be defensible from the code you can see. Do not invent files, lines, code paths, or failure scenarios you cannot support. If a conclusion depends on an inference, state that in the DETAIL field and set SEVERITY accordingly.

Prefer one strong finding over several weak ones. If the code looks correct, say so and return no findings.

Output Format

Return findings in this exact schema. Each finding must fill every field.

FINDING: <sequential id starting at 1>
FILE: <path relative to repo root>
LINES: <start>-<end>
SEVERITY: <high|medium|low>
CATEGORY: <trust-boundary|resource-leak|
           race-condition|input-validation|
           error-handling|state-corruption|other>
ISSUE: <one-line summary>
DETAIL: <explanation — as long as needed>
RECOMMENDATION: <concrete fix>

If there are no material findings, return:

Read the full file on GitHub · 75 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. yesterday First seen · 75 lines · 52 tokens per session scan A cede77467cc1

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository kelp/agent-plugins (2 stars, last pushed 9d ago), licensed MIT. It adds 52 tokens to every session and 534 once invoked, about $0.0003 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.