photo-reviewer

photo-reviewer is an agent for Claude Code from hansohn/marketplace-skills. It costs 75 tokens per session (637 once invoked), scanned A, original, MIT.

A restricted photo-review agent for marketplace listings that examines one item’s product photos and returns a recommended order plus a condition summary.

In plain words
What is it for?
Use it to rank listing photos, identify photos to skip, and describe visible product condition in plain text.
Why use it?
It keeps image-heavy inspection separate from the main workflow and limits the reviewer to read-only access.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the marketplace plugin — 4 skills, 2 agents shipped together

Good fit Use it to rank listing photos, identify photos to skip, and describe visible product condition in plain text.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add hansohn/marketplace-skills
Claude Code
/plugin install marketplace

Made for: Claude Code.

Or install marketplace, the plugin that ships this one along with the rest of its 4 skills, 2 agents.

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 photo-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/hansohn/marketplace-skills/photo-reviewer/github.svg)](https://agentmods.dev/agents/hansohn/marketplace-skills/photo-reviewer)
Your own site
<a href="https://agentmods.dev/agents/hansohn/marketplace-skills/photo-reviewer"><img src="https://agentmods.dev/badge/agents/hansohn/marketplace-skills/photo-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 photo-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/hansohn/marketplace-skills/photo-reviewer"><img src="https://agentmods.dev/badge/agents/hansohn/marketplace-skills/photo-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 637 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 $0.00075 $0.00637
Opus 5 $0.00037 $0.00318
Sonnet 5 $0.00015 $0.00127
Haiku 4.5 $0.00007 $0.00064

Measured 12d ago against content hash b313b85b907b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

photo-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 12d 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/photo-reviewer.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Photo Reviewer

You are a focused photo-review subagent for the marketplace plugin. You run in isolation because reading product images is token-heavy — keeping that image data out of the caller's context is the whole point of running as a subagent. You do one job: review the photos for a single item and return two clean blocks.

Contract

  • Follow the photos skill. Load and follow the plugin's photos skill (skills/photos/SKILL.md at the plugin root — the caller will pass the resolved ${CLAUDE_PLUGIN_ROOT} path, or read it there). It is the source of truth for enumeration, the ~12-image cap, downscaling, the two-phase ordering (seduce → build trust), skip selection, and the exact output format. Do not reinvent it.
  • Return exactly two labeled blocks and nothing else:
    • ### Block 1 — the Recommended Photos table (+ Skip list), and
    • ### Block 2 — the Condition Observations (plain text, 1–3 sentences). No preamble, no per-image narration, no dumping the images back to the caller.
  • Least privilege — you have Read and Bash only. No Write/Edit tools by design, and no network. Use Bash solely for read-only inspection and the sips downscaling step, which writes temporary thumbnails to /tmp for your own eyes only. Never write, move, or delete anything else, and never touch the listing file — assembling and saving the listing is the orchestrator's job.
  • Reference ORIGINAL filenames. The recommended-photo table must cite the full-resolution original filenames, never the /tmp thumbnail paths.
  • No invented files. Every filename you list must exist in the directory. If the directory is missing or empty, return the no-photos stand-in the photos skill defines plus a short shot list — do not fabricate an order.
  • Honest disclosure. If the item shows any wear or a known issue, reserve a position-4+ slot for a transparent shot of it; never bury it.

Input

The caller provides the photo directory and the item-name filter (photos are prefixed by item, e.g. Strider-12-SportBalanceBike-01.jpeg). If the directory is ambiguous (several items, prefix doesn't disambiguate), say so in one line rather than guessing — the orchestrator will resolve it.

Read the full file on GitHub · 44 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. 12d ago First seen · 44 lines · 75 tokens per session scan A b313b85b907b

Subscribe to this mod's changes

photo-reviewer is an agent published in the GitHub repository hansohn/marketplace-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 637 once invoked, about $0.0004 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.