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.
npx skills add Vaxaxas/photoshop-mcp-windows-first --skill image-editing-agentgit clone --depth 1 https://github.com/Vaxaxas/photoshop-mcp-windows-firstWrote 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/skills/vaxaxas/photoshop-mcp-windows-first/image-editing-agent)<a href="https://agentmods.dev/skills/vaxaxas/photoshop-mcp-windows-first/image-editing-agent"><img src="https://agentmods.dev/badge/skills/vaxaxas/photoshop-mcp-windows-first/image-editing-agent/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/skills/vaxaxas/photoshop-mcp-windows-first/image-editing-agent"><img src="https://agentmods.dev/badge/skills/vaxaxas/photoshop-mcp-windows-first/image-editing-agent.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 | $0.00076 | $0.01991 |
| Opus 5 | $0.00038 | $0.00996 |
| Sonnet 5 | $0.00015 | $0.00398 |
| Haiku 4.5 | $0.00008 | $0.00199 |
Grade A, and why
image-editing-agent 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 11d 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Editing Agent
Use this skill when the task should be completed inside the local photoshop-mcp server, not by generic image generation.
Work like a careful Photoshop operator:
- preserve unrelated content
- prefer reversible edits
- use structured MCP tools before raw scripts
- validate after each major step
Tool Priority
Use tools in this order:
- Structured Photoshop MCP tools
photoshop_execute_script_with_statewhen the structured toolset is close but not enoughphotoshop_execute_scriptonly as an escape hatch- Windows UI fallback tools only for dialog recovery or window inspection
photoshop_play_actiononly after checkingphotoshop_list_actions, and only if the workflow can tolerate interactive or unreliable behavior
Do not default to raw ExtendScript if a structured tool already exists.
Start State
Before editing:
- Verify Photoshop is reachable with
photoshop_ping. - Read environment and capabilities with
photoshop_get_version. - Inspect current workspace with
photoshop_get_stateorphotoshop_get_active_context.
If the user gave a file path:
- open it with
photoshop_open_image
If the user wants to work on the current document:
- inspect with
photoshop_get_open_documents - select the intended one with
photoshop_select_document
If there is no active document and no source path:
- ask for the source image path or ask the user to open the target document in Photoshop
Safety First
Before destructive edits:
- Create a checkpoint with
photoshop_snapshot_checkpoint - If the user wants a non-destructive branch, create a duplicate with
photoshop_duplicate_document - Wait for Photoshop to settle with
photoshop_wait_for_idle
For multi-step edits that should roll back cleanly:
- prefer
photoshop_run_transaction
Workflow Classes
Choose the narrowest workflow that matches the request.
Targeted local edit
Use this for:
- object cleanup
- bounded recolor
- replacing one region
- text or label corrections
- local retouching
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 265 lines · 76 tokens per session scan A 043f1a7f7404
image-editing-agent is a skill published in the GitHub repository Vaxaxas/photoshop-mcp-windows-first (3 stars, last pushed 5mo ago), licensed MIT. It adds 76 tokens to every session and 1,991 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 skills, from other repositories
premiere-dialogue-cut
Tighten interviews, podcasts, tutorials, and talking-head edits in Adobe Premiere Pro by detecting silence, preserving natural speech margins, keeping an untouched recovery sequence, and verifying sync. Use for pause removal, dialogue cleanup, jump-cut planning, or rough-cut acceleration through the Premiere Pro MCP…
premiere-social-reframe
Produce vertical, square, and platform-specific versions of an Adobe Premiere Pro sequence while preserving the master edit. Use for 9:16, 1:1, and social cutdowns, Auto Reframe workflows, safe-zone checks, title repositioning, or multi-platform exports through the Premiere Pro MCP server.
premiere-batch-delivery
Validate, export, and inspect multiple Adobe Premiere Pro deliverables with explicit pending and unverified states. Use for YouTube, social, web, mobile, archive, audio-only, versioned export, delivery QA, caption validation, direct export, AME submission, or repeatable batch output through the Premiere Pro MCP server.
premiere-captions
Import, verify, structurally validate, and export timed captions or subtitles in Adobe Premiere Pro. Use for SRT workflows, supplied timed transcripts, caption QA, accessibility checks, or sidecar subtitle delivery through the Premiere Pro MCP server.
premiere-proxy-conform
Speed Adobe Premiere Pro editing with proxy creation, attachment, media matching, and original-media readiness checks. Use for high-resolution or remote-media projects, batch proxy preparation, relinking, proxy status audits, or pre-delivery original-media checks through the Premiere Pro MCP server.
premiere-look-effects
Build consistent, reversible visual effect recipes in Adobe Premiere Pro from effects confirmed as installed. Use for clip effects, parameterized looks, motion treatments, vignettes, controlled tests, or applying one approved recipe across multiple clips through the Premiere Pro MCP server.