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 jpaarhuis/claude-foundry-image --skill setupgit clone --depth 1 https://github.com/jpaarhuis/claude-foundry-imageWrote 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/jpaarhuis/claude-foundry-image/setup)<a href="https://agentmods.dev/skills/jpaarhuis/claude-foundry-image/setup"><img src="https://agentmods.dev/badge/skills/jpaarhuis/claude-foundry-image/setup.svg" alt="Measured on agentmods" 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 | $0.00089 | $0.01673 |
| Opus 5 | $0.00044 | $0.00837 |
| Sonnet 5 | $0.00018 | $0.00335 |
| Haiku 4.5 | $0.00009 | $0.00167 |
Grade B, and why
setup scanned grade B with 1 finding 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 yesterday.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Alternative: `~/.claude/settings.json` → `env`.** One file, works on every OS, only How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
foundry-image setup
The MCP server reads four environment variables. They must be visible to the Claude Code process that spawns the plugin's server. Set them once; every project and every conversation then has image generation.
| Variable | Required | Value |
|---|---|---|
MAI_IMAGE_ENDPOINT |
yes | Full generation URL: https://<resource>.services.ai.azure.com/mai/v1/images/generations |
MAI_IMAGE_DEPLOYMENT |
yes | Deployment name as shown in Foundry (e.g. MAI-Image-2.5-Pro) |
MAI_IMAGE_API_KEY |
yes | Key 1 or Key 2 of the Foundry resource |
MAI_IMAGE_OUTPUT_DIR |
no | Folder for images when no output_path is given. Default: OS temp dir |
GPT_IMAGE_ENDPOINT |
for gpt-image | Resource base URL: https://<resource>.services.ai.azure.com (Foundry) or https://<resource>.openai.azure.com |
GPT_IMAGE_DEPLOYMENT |
for gpt-image | Deployment name of the gpt-image model, e.g. gpt-image-2 |
GPT_IMAGE_API_KEY |
no | Only when gpt-image is on another resource; defaults to MAI_IMAGE_API_KEY |
GPT_IMAGE_API_VERSION |
no | Default 2025-04-01-preview |
IMAGE_DEFAULT_MODEL |
no | mai (default) or gpt-image |
At least one backend must be complete. The MAI block is the original setup; the
GPT_IMAGE_* block adds gpt-image-2 (OpenAI-compatible Azure API) and is selected per
call with model: "gpt-image".
Where to put them (pick one)
Recommended: the env file ~/.claude/foundry-image.env. Plain KEY=VALUE lines,
# comments, quotes optional. Read once at server start; anything already set in the
process environment (OS env, settings.json env) wins over the file. Another path can be
given in FOUNDRY_IMAGE_ENV_FILE. Survives plugin updates, is outside every repo, and
check_config prints whether it was found.
MAI_IMAGE_ENDPOINT=https://<resource>.services.ai.azure.com/mai/v1/images/generations
MAI_IMAGE_DEPLOYMENT=MAI-Image-2.5-Pro
MAI_IMAGE_API_KEY=<paste-key-here>
MAI_IMAGE_OUTPUT_DIR=C:/Users/<you>/Pictures/ai
GPT_IMAGE_ENDPOINT=https://<resource>.services.ai.azure.com
GPT_IMAGE_DEPLOYMENT=gpt-image-2
GPT_IMAGE_API_KEY=<paste-key-here>
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.
- yesterday Changed · +21 lines 9bb921435810
- 3d ago Changed · +17 lines 5444965571a3
- 7d ago First seen · 72 lines · 89 tokens per session scan B 682c0d2a2f2c
setup is a skill published in the GitHub repository jpaarhuis/claude-foundry-image (0 stars, last pushed 3d ago), licensed MIT. It adds 89 tokens to every session and 1,673 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…