agentmods.dev

reviewer

reviewer is an agent for coding agents from jrpease/throughline. It costs 67 tokens per session (471 once invoked), scanned A, original, MIT.

A read-only checker for a finished unit of work, such as code changes or a Figma design. It compares the result with its requirements and reports whether it meets them.

In plain words
What is it for?
Use it to review a git diff for correctness and code quality, or to inspect a fresh screenshot of a Figma component for layout, spacing, proportions, and fidelity to the specification.
Why use it?
It helps catch missing requirements, defects, weak tests, and design problems before the work is merged or handed off. It reports issues but does not change the work.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the throughline plugin — 12 skills, 5 commands, 4 agents, 1 MCP server shipped together

not rated 76 3d ago A scan 67 tokens original MIT
View the source file jrpease/throughline
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/jrpease/throughline/reviewer
Clone the repo
git clone --depth 1 https://github.com/jrpease/throughline

Or install throughline, the plugin that ships this one along with the rest of its 12 skills, 5 commands, 4 agents, 1 MCP server.

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/jrpease/throughline/reviewer.svg)](https://agentmods.dev/agents/jrpease/throughline/reviewer)
Your own site
<a href="https://agentmods.dev/agents/jrpease/throughline/reviewer"><img src="https://agentmods.dev/badge/agents/jrpease/throughline/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 471 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 $0.00067 $0.00471
Opus 5 $0.00034 $0.00235
Sonnet 5 $0.00013 $0.00094
Haiku 4.5 $0.00007 $0.00047

Measured 4d ago against content hash 69068af8cf92, 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 4d 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.

agents/reviewer.md · 33 lines

What it actually says

reviewer

Tier: balanced, scaled to risk (see ${CLAUDE_PLUGIN_ROOT}/references/agent-routing.md). Concurrency: parallel-safe.

Review the unit you are given against its spec. Report; do not edit.

Mode: code-diff

Given a spec and a diff:

  1. Spec compliance — does the diff do what the spec requires, and only that?
  2. Quality — correctness, DRY, repo conventions, dead code, tests that assert something real. Return: spec: ✅/❌ <reason>, then quality findings ranked most-severe first, then an overall approved / changes-requested. Flag anything you cannot verify from the diff alone as ⚠️ cannot verify — do not block on it; the dispatcher holds the cross-task context to resolve it.

Mode: Figma-visual

Figma work has no diff. Concurrency: 1 (bridge-locked) — never screenshot while another Figma-touching subagent runs.

  1. Preflight figma_get_status; locate the finalized component by name via figma_search_components.
  2. Take your own fresh figma_capture_screenshot (independence — do not rely on the executor's shot; you may need state it did not capture).
  3. Analyze design quality against the spec — alignment, spacing, proportion, spec fidelity. The executor already checked structural correctness; focus on quality, not re-checking node placement.
  4. Report approved / changes-requested with findings ranked most-severe first. Flag anything you cannot verify from the screenshot as ⚠️ cannot verify.
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. 4d ago First seen · 33 lines · 67 tokens per session scan A 69068af8cf92

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository jrpease/throughline (76 stars, last pushed 3d ago), licensed MIT. It adds 67 tokens to every session and 471 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 2026-08-30.

Code reviewDesign and UXLegal and compliance
Related

Other agents, from other repositories

a11y-auditor

Accessibility auditor specialist. MUST BE USED when analyzing pages for WCAG compliance. Use PROACTIVELY for accessibility audits, screen reader testing, keyboard navigation checks, and color contrast validation.

LeoYeAI/openclaw-master-skills · 44 tokens

patent-illustrator

Expert in creating patent-style technical diagrams - flowcharts, block diagrams, system architectures - using Graphviz with proper reference numbering.

RobThePCGuy/Claude-Patent-Creator · 31 tokens

a11y-review

WCAG 2.1 AA compliance, semantic HTML, ARIA, keyboard navigation, focus management.

bdfinst/agentic-dev-team · 25 tokens

ui-ux-designer

User interface design, UX optimization, and accessibility compliance.

bdfinst/agentic-dev-team · 16 tokens

edtech-reviewer

Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…

avelikiy/great_cto · 112 tokens

ux-ui-designer

UX/UI design, design systems, user flows, and accessibility compliance. Use for creating design specifications, component libraries, and WCAG-compliant interfaces.

davidmatousek/tachi · 35 tokens