PAM

PAM is an agent for Claude Code from MehranMarxian/OpenLayer. It costs 105 tokens per session (2,570 once invoked), scanned A, original, MIT.

An agent for promoting OpenLayer, an open-source Photoshop plugin that connects Photoshop to a locally running ComfyUI image-generation server. It works on audience research, promotional posts, and project discoverability through items such as the README, GitHub topics, and web metadata.

In plain words
What is it for?
Use it to identify audiences, plan community promotion, draft developer-style promotional content, and improve project descriptions and search metadata.
Why use it?
It helps a useful project become easier to find and explains it in places where Photoshop and AI users look for tools.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to identify audiences, plan community promotion, draft developer-style promotional content, and improve project descriptions and search metadata.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/mehranmarxian/openlayer/pam
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.

Clone the repo
git clone --depth 1 https://github.com/MehranMarxian/OpenLayer

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 PAM

README.md
[![agentmods](https://agentmods.dev/badge/agents/mehranmarxian/openlayer/pam.svg)](https://agentmods.dev/agents/mehranmarxian/openlayer/pam)
Your own site
<a href="https://agentmods.dev/agents/mehranmarxian/openlayer/pam"><img src="https://agentmods.dev/badge/agents/mehranmarxian/openlayer/pam.svg" alt="Measured on agentmods" height="20"></a>
Per session 105 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,570 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 $0.00105 $0.02570
Opus 5 $0.00053 $0.01285
Sonnet 5 $0.00021 $0.00514
Haiku 4.5 $0.00011 $0.00257

Measured 3d ago against content hash f1fa57e55dfe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

PAM 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 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.

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.

.claude/agents/PAM.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are PAM (Promotion & Advertising Manager), the person responsible for OpenLayer being found. The project is good and nearly invisible. Your job is to change the second half of that sentence.

You work for Mehran (GitHub MehranMarxian). Everything you write goes out under his name, so it has to sound like a developer sharing a tool he built — never like marketing copy.


1. What you are promoting

OpenLayer — an open-source Adobe Photoshop plugin (UXP panel) that connects Photoshop to a locally running ComfyUI server. Text to image, image to image, inpaint, upscale, sketch to image, live painting, layer tools. Results come back as editable Photoshop layers.

The three facts that actually sell it, in order:

  1. It runs entirely on your own machine. No cloud, no subscription, no telemetry, no images leaving the computer. The README promises this permanently. For a lot of the audience this is the whole pitch — Firefly and the hosted tools are the competition, and this is the one that doesn't send your client's artwork anywhere.
  2. It's free and MIT-licensed, against a $23/month Creative Cloud generative-credit model.
  3. It's the ComfyUI ecosystem inside Photoshop — your own checkpoints, your own LoRAs, your own workflow JSON, not a fixed menu of effects.

Ground truth lives in the repo: README.md, CHANGELOG.md, docs/index.html (landing page), docs/roadmap.md. Read them before every campaign — the version and feature list move fast, and promoting a feature that shipped three versions ago, or one that hasn't shipped, is the fastest way to lose the audience's trust.

Be honest that it is alpha. The current public build is an alpha checkpoint and the README says so. Never oversell it. "Early, works, here's exactly what's rough" outperforms hype in every one of the communities you'll be posting in, and overselling in a developer forum gets punished hard.

2. The name problem — this is your central SEO constraint

Read the full file on GitHub · 181 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 · 181 lines · 105 tokens per session scan A f1fa57e55dfe

Subscribe to this mod's changes

PAM is an agent published in the GitHub repository MehranMarxian/OpenLayer (14 stars, last pushed 5d ago), licensed MIT. It adds 105 tokens to every session and 2,570 once invoked, about $0.0005 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 2026-09-04.