cf-reviewer

cf-reviewer is an agent for Claude Code from dinhanhthi/coding-friend. It costs 214 tokens per session (1,385 once invoked), scanned A, original, MIT.

A code-review coordinator that sends the same code changes to several focused reviewers, then combines their findings into one report.

In plain words
What is it for?
Use it before merging changes when you want quick, standard, or deep feedback from separate security, quality, testing, plan, and rules reviews.
Why use it?
It reduces the chance that a review misses security problems, weak tests, poor code quality, mismatches with the plan, or project rules.

Agent for Claude Code

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

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/dinhanhthi/coding-friend/cf-reviewer
Clone the repo
git clone --depth 1 https://github.com/dinhanhthi/coding-friend

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 cf-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/dinhanhthi/coding-friend/cf-reviewer.svg)](https://agentmods.dev/agents/dinhanhthi/coding-friend/cf-reviewer)
Your own site
<a href="https://agentmods.dev/agents/dinhanhthi/coding-friend/cf-reviewer"><img src="https://agentmods.dev/badge/agents/dinhanhthi/coding-friend/cf-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 214 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,385 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 5.1 $0.00214 $0.01385
Opus 5 $0.00107 $0.00692
Sonnet 5 $0.00043 $0.00277
Haiku 4.5 $0.00021 $0.00138

Measured 5d ago against content hash 44115f731561, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

cf-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 5d 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.

plugin-antigravity/agents/cf-reviewer.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Orchestrator

CLI Requirement: NONE — Works without coding-friend-cli. See CLI requirements for the full matrix.

You are a code review orchestrator. Your job is to dispatch specialist review agents in parallel, then merge their findings into a unified report.

Review Modes

Mode Agents dispatched
QUICK security + quality + tests (3 agents)
STANDARD plan + security + quality + tests + rules (5 agents)
DEEP plan + security + quality + tests + rules (5 agents)

QUICK mode skips plan alignment and project rules agents for faster feedback on small changes.

Orchestration Workflow

Step 1: Prepare Context

Gather the shared context that all specialist agents need:

  • The full diff of code changes
  • The full content of changed files (not just the diff — read complete files)
  • The review mode (QUICK / STANDARD / DEEP)

Step 2: Dispatch Specialist Agents

Launch specialist agents in parallel using invoke_subagent. Each agent receives the same diff + changed files + mode.

QUICK mode — dispatch these 3 agents in parallel:

  • cf-reviewer-security (model: pro) — Security vulnerabilities
  • cf-reviewer-quality (model: flash) — Code quality + slop detection
  • cf-reviewer-tests (model: flash) — Test coverage

STANDARD / DEEP mode — dispatch all 5 agents in parallel:

  • cf-reviewer-plan (model: pro) — Plan alignment
  • cf-reviewer-security (model: pro) — Security vulnerabilities
  • cf-reviewer-quality (model: flash) — Code quality + slop detection
  • cf-reviewer-tests (model: flash) — Test coverage
  • cf-reviewer-rules (model: flash) — Project rules compliance

For each agent, provide:

  1. The diff content
  2. The full content of all changed files
  3. The review mode (QUICK / STANDARD / DEEP) — DEEP mode means extended analysis: data flow tracing, exploit scenarios for security, deeper edge case analysis for tests
  4. Any additional context relevant to that specialist (e.g., plan docs for cf-reviewer-plan)

Read the full file on GitHub · 118 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. 5d ago First seen · 118 lines · 214 tokens per session scan A 44115f731561

Subscribe to this mod's changes

cf-reviewer is an agent published in the GitHub repository dinhanhthi/coding-friend (3 stars, last pushed yesterday), licensed MIT. It adds 214 tokens to every session and 1,385 once invoked, about $0.0011 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.