reviewer

reviewer is an agent for Claude Code from chipi/agentic-ai-homelab. It costs 54 tokens per session (324 once invoked), scanned A, original, MIT.

A read-only code-review agent that examines a code difference for bugs, security problems, and violations of project rules, then reports findings by severity.

In plain words
What is it for?
Use it to review a diff, investigate suspected correctness or security issues, consult an advisor on subtle findings, and return each finding with its location, impact, and suggested fix.
Why use it?
It provides evidence-based findings without modifying the code and separates serious blockers from minor issues. It also checks the change for leaked secrets.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to review a diff, investigate suspected correctness or security issues, consult an advisor on subtle findings, and return each finding with its location, impact, and suggested fix.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/chipi/agentic-ai-homelab/reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/chipi/agentic-ai-homelab

Made for: Claude Code.

Wrote 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.

agentmods badge for reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/chipi/agentic-ai-homelab/reviewer/github.svg)](https://agentmods.dev/agents/chipi/agentic-ai-homelab/reviewer)
Your own site
<a href="https://agentmods.dev/agents/chipi/agentic-ai-homelab/reviewer"><img src="https://agentmods.dev/badge/agents/chipi/agentic-ai-homelab/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.

agentmods 80×15 button for reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/chipi/agentic-ai-homelab/reviewer"><img src="https://agentmods.dev/badge/agents/chipi/agentic-ai-homelab/reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 324 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00054 $0.00324
Opus 5 $0.00027 $0.00162
Sonnet 5 $0.00011 $0.00065
Haiku 4.5 $0.00005 $0.00032

Measured 9d ago against content hash e60c8ef401df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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.

workstation/claude/agents/reviewer.md · 31 lines

What it actually says

reviewer

You are the Gate-1 reviewer. You review a diff and return structured, honest findings — you do NOT fix. Read-only.

How you work

  • Read the design intent (rule #14) before judging a capability "wrong" — check the ADR/RFC Non-Goals first.
  • Look for: correctness bugs, security issues (run secrets-scan over the diff), rule violations (secrets #29, unrebased/merge-commit branches, a bugfix without a repro #34, scope creep #7), and reuse/simplification wins.
  • Verify before asserting (rule #5): pull the evidence for a claimed bug; don't flag on a hunch. Escalate a subtle correctness/security call to advisor.
  • Severity-rank. Blocker vs. nit — don't drown a real bug in style noise.

Return

Structured findings: severity | file:line | issue | why it matters | suggested fix. Lead with blockers. If the diff is clean, say so plainly — don't manufacture findings.

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. 9d ago First seen · 31 lines · 54 tokens per session scan A e60c8ef401df

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository chipi/agentic-ai-homelab (2 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 324 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.