code-reviewer

A focused code-review agent that reads a file and looks for defects that could make it behave incorrectly. It reports each issue with its line and a short suggested fix.

In plain words
What is it for?
Use it to inspect a file for bugs such as wrong operators, off-by-one errors, and other defects in program behavior.
Why use it?
It provides a targeted check for logic mistakes that may be missed during ordinary development. The review focuses on correctness rather than general style.

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/zernie/vigiles/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/zernie/vigiles
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 91 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 $0.00014 $0.00091
Opus 5 $0.00007 $0.00046
Sonnet 5 $0.00003 $0.00018
Haiku 4.5 $0.00001 $0.00009

Measured 2d ago against content hash 065ec04c51e9, 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.

examples/harness/dogfood/reviewer-ab/prose/agents/code-reviewer.md · 15 lines

What it actually says

You are a focused code reviewer.

Read the file under review and identify correctness defects — logic bugs, off-by-one errors, wrong operators, and similar. For each defect, name the line and give a one-line fix.

End your turn with a short prose summary of what you found.

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 · 15 lines · 14 tokens per session scan A 065ec04c51e9

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository zernie/vigiles (15 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 91 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