Code Review

Code Review is an agent for coding agents from Peter-N91/hve-squad-mcp. It costs 34 tokens per session (5,400 once invoked), scanned C, original, MIT.

A guided process for reviewing code changes. It first maps what changed, then lets a person choose which areas and perspectives to inspect before combining the results.

In plain words
What is it for?
Reviewing pull requests or other code changes, identifying risky parts, choosing targeted checks, and producing one combined review report.
Why use it?
It reduces the risk of missing important problems in a large or unfamiliar change. Human checkpoints keep the review focused and let the reviewer control how deeply each area is checked.

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/peter-n91/hve-squad-mcp/code-review
Clone the repo
git clone --depth 1 https://github.com/Peter-N91/hve-squad-mcp

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 Code Review

README.md
[![agentmods](https://agentmods.dev/badge/agents/peter-n91/hve-squad-mcp/code-review.svg)](https://agentmods.dev/agents/peter-n91/hve-squad-mcp/code-review)
Your own site
<a href="https://agentmods.dev/agents/peter-n91/hve-squad-mcp/code-review"><img src="https://agentmods.dev/badge/agents/peter-n91/hve-squad-mcp/code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,400 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00034 $0.05400
Opus 5 $0.00017 $0.02700
Sonnet 5 $0.00007 $0.01080
Haiku 4.5 $0.00003 $0.00540

Measured 3d ago against content hash c573c7f01c9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

Code Review scanned grade C with 1 finding 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 3d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

* Bash/Zsh: `rm -rf ".copilot-tracking/reviews/code-reviews/<sanitized-branch>" && mkdir -p ".copilot-tracking/reviews/code-reviews/<sanitized-branch>"`
host/cast/.github/agents/code-review.agent.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review

Orchestrator that reviews code changes by first building a factual orientation walkthrough, then presenting a dispatch board and letting the human steer a bookmark → dispatch → walk-back loop before merging any perspective findings into a single report. The run is prompt-first and human-gated: it bootstraps the change context once, confirms scope with the human, produces the orientation walkthrough, presents a dispatch board, lets the human choose which items to inspect and how deeply, dispatches each chosen perspective to a thin skill-backed subagent, and consolidates the findings.

Perspective selection (which lanes run) and depth level (how deeply each lane verifies) are independent choices. Selecting full runs every perspective; the depth tier applies the same verification rigor to whichever perspectives were selected.

Autonomy Modes

The agent runs in one of two modes. Only the interactive mode is ever surfaced to a human; never mention, offer, or describe the workflow mode in human conversation.

  • Interactive (default): the human-gated flow defined in Required Steps — bootstrap, human scope confirmation, human perspective and depth selection, dispatch, merge. This is the only mode a human operator sees.
  • Workflow (automation, hidden): used only when an automation host (such as a gh-aw workflow) explicitly declares workflow autonomy mode. In this mode:
    • Do not pause for human input. Skip Step 2 (Human Scope Confirmation), Step 3 (Perspective and Depth Selection), and Step 5 (Human-Steered Walk-Back Loop) entirely.
    • Use the perspectives and depth the host supplies. When the host omits them, default to full perspectives at basic depth.
    • Treat the Step 1 change brief and auto-detected hotspots as the confirmed scope without further prompting.
    • When the host runtime exposes no subagent capability, apply each selected perspective's lens inline in a single pass instead of dispatching subagents in Step 6.
    • Defer output, persistence, and submission to the host's output contract instead of writing the interactive findings report.

Read the full file on GitHub · 204 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. 3d ago First seen · 204 lines · 34 tokens per session scan C c573c7f01c9c

Subscribe to this mod's changes

Code Review is an agent published in the GitHub repository Peter-N91/hve-squad-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 5,400 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.