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 agentmods add instructions/teexiii/ai-psd-thumbnails/claude-mdgit clone --depth 1 https://github.com/teexiii/ai-psd-thumbnailsWrote 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/instructions/teexiii/ai-psd-thumbnails/claude-md)<a href="https://agentmods.dev/instructions/teexiii/ai-psd-thumbnails/claude-md"><img src="https://agentmods.dev/badge/instructions/teexiii/ai-psd-thumbnails/claude-md.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 | $0.02442 | $0.02442 |
| Opus 5 | $0.01221 | $0.01221 |
| Sonnet 5 | $0.00488 | $0.00488 |
| Haiku 4.5 | $0.00244 | $0.00244 |
Grade A, and why
ai-psd-thumbnails CLAUDE.md 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 5d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ai-psd-thumbnails
Windows Explorer thumbnail + preview-pane shell extension for .ai .psd .psb .eps .svg
(plus thumbnail-only .pdf), written in Rust (windows-rs), shipped as a per-machine x64 MSI. Design rationale lives in
plans/260610-1131-thumb-viewer-shell-extension/; this file is the operational reference.
Architecture
crates/core ai-psd-thumbnails-core — pure decode/render, NO Win32 (unit-testable)
crates/shell ai-psd-thumbnails-shell — cdylib `thumb_viewer.dll`, COM in-proc server
crates/installer-ca installer-ca — MSI custom-action exe (2 verbs, see Installer)
installer/ WiX v4 authoring + build script
scripts/ dev register/unregister/cache-clear (elevated PowerShell)
third_party/bin/ pdfium.dll (bundled binary, see Pin below)
COM objects (both ThreadingModel=Apartment):
| Object | CLSID | Interfaces |
|---|---|---|
| Thumbnail provider | {90E3822E-5F70-40BF-884E-77544797AD41} |
IThumbnailProvider, IInitializeWithStream |
| Preview handler | {2CFC1F9E-0B23-48C3-AE46-29025209D0D4} |
IPreviewHandler, IInitializeWithStream, IObjectWithSite, IOleWindow |
Format → render path:
| Format | Fast path | Fallback |
|---|---|---|
.psd |
resource 1036 embedded JPEG thumb (RGB; 1033 = old BGR) | flattened composite |
.psb |
same (Image Resources section layout identical to PSD) | composite (RLE counts widen to 4 bytes) |
.ai (PDF-style) |
pdfium page-1 render | — |
.ai (EPS-style) |
DOS-EPS TIFF → %AI_Thumbnail → XMP xmpGImg JPEG |
Ghostscript subprocess |
.eps |
DOS-EPS embedded TIFF preview → XMP xmpGImg JPEG |
Ghostscript subprocess |
.svg |
resvg/usvg (external hrefs disabled, dims capped) | — |
.pdf |
pdfium page-1 render (same route as PDF-style .ai; magic %PDF → Ext::Ai) |
— |
Build
cargo build -p ai-psd-thumbnails-core # decode lib only
cargo build -p ai-psd-thumbnails-shell --release # → target/release/thumb_viewer.dll
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.
- 5d ago First seen · 159 lines · 2,442 tokens per session scan A c438fb5591bb
ai-psd-thumbnails CLAUDE.md is an instructions file published in the GitHub repository teexiii/ai-psd-thumbnails (10 stars, last pushed 25d ago), licensed MIT. It adds 2,442 tokens to every session, about $0.0122 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).