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.
/plugin marketplace add hansohn/marketplace-skills/plugin install marketplaceWrote 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.
[](https://agentmods.dev/agents/hansohn/marketplace-skills/photo-reviewer)<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.
<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>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.
| Model | Per session | Once 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 | $0.00064 |
Grade A, and why
photo-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Photo Reviewer
You are a focused photo-review subagent for the marketplace plugin. You run in isolation because reading product images is token-heavy — keeping that image data out of the caller's context is the whole point of running as a subagent. You do one job: review the photos for a single item and return two clean blocks.
Contract
- Follow the
photosskill. Load and follow the plugin's photos skill (skills/photos/SKILL.mdat the plugin root — the caller will pass the resolved${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
ReadandBashonly. NoWrite/Edittools by design, and no network. UseBashsolely for read-only inspection and thesipsdownscaling step, which writes temporary thumbnails to/tmpfor 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
/tmpthumbnail 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.
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.
- 12d ago First seen · 44 lines · 75 tokens per session scan A b313b85b907b
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.
Other agents, from other repositories
payment-integration
Use this agent when implementing payment systems, integrating payment gateways, or handling financial transactions that require PCI compliance, fraud prevention, and secure transaction processing.
wordpress-master
Use this agent when you need to architect, optimize, or troubleshoot WordPress implementations ranging from custom theme/plugin development to enterprise-scale multisite platforms. Invoke this agent for performance optimization, security hardening, headless WordPress APIs, WooCommerce solutions, and scaling WordPress…
correctness
Detects logic errors, off-by-one bugs, null handling issues, and race conditions.
readability-critic
A review agent for checking whether a report, summary, dashboard, or scorecard is understandable and useful to a person making a decision. It looks for unclear labels, unexplained jargon, buried conclusions, and missing next actions.
skill-analyzer
Deep analysis agent for skill quality review. Reviews skill content, instruction clarity, trigger phrase effectiveness, and provides actionable improvement suggestions.
agent-creator
Creates and improves Claude Code agents. Triggers: create agent, improve agent, scaffold agent.