Borrowing it
Nothing to install: this file belongs to peva3/Lightroom-Presets. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/peva3/Lightroom-Presets/main/AGENTS.mdgit clone --depth 1 https://github.com/peva3/Lightroom-PresetsWrote 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/peva3/lightroom-presets/agents-md)<a href="https://agentmods.dev/instructions/peva3/lightroom-presets/agents-md"><img src="https://agentmods.dev/badge/instructions/peva3/lightroom-presets/agents-md/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/instructions/peva3/lightroom-presets/agents-md"><img src="https://agentmods.dev/badge/instructions/peva3/lightroom-presets/agents-md.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 | $0.02299 | $0.02299 |
| Opus 5.5 | $0.00920 | $0.00920 |
| Sonnet 5.5 | $0.00460 | $0.00460 |
| Haiku 4.5 | $0.00230 | $0.00230 |
Grade A, and why
Lightroom-Presets AGENTS.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 17d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project: Lightroom Presets (peva3/Lightroom-Presets)
Overview
48 XMP Lightroom presets across 4 categories:
- Color Negative (16): Film stock emulations — Portra, Gold, Ektar, Fuji, etc.
- Black White (6): Tri-X, HP5, Delta 3200, Acros, T-Max 3200, Ricoh HC
- Slide (4): Kodachrome 64, Velvia 50, Astia 100F, Ektachrome E100
- Creative (22): Cinestill, bleach bypass, cyberpunk, VHS, WKW, etc.
Critical Findings: XMP Color Issues
The "B&W with one color" bug
Multiple presets were creating a selective-color effect (near-monochrome with one boosted hue). Root causes identified:
-
Vibrance >> Saturation gap: When
Vibrance - Saturation > 10, Lightroom desaturates globally (via Saturation) then selectively boosts midtones (via Vibrance), creating a selective-color effect. Fix: Keep Vibrance within 5 points of Saturation, or remove Vibrance entirely. -
Calibration panel (
CalibrationRedHue/Sat,CalibrationGreenHue/Sat,CalibrationBlueHue/Sat): The original working XMPs had ZERO calibration values. Adding calibration shifts global primary interpretation, which compounds unpredictably with HSL + split toning. Fix: Remove calibration entirely unless absolutely needed. -
Temperature/Tint: Original XMPs had no WB adjustments. Adding WB shifts before HSL/split toning creates color conflicts. Fix: Use only for presets where WB is a defining characteristic (e.g., Ultramax's warm cast). Remove from generic film emulations.
-
Extreme HSL saturation (> |60|): Nukes entire color channels. Fix: Cap at ±60.
The retuning disaster
The intermediate "retune all 48" commit (339fe11) made presets far too aggressive. The fuzzy-merge agents compounded this by adding Calibration, Temperature/Tint, and extreme Vibrance values from aggregated community recipes. The result was presets with 55-68 attributes that looked broken on real photos.
Original working XMPs (old/ folder)
The old/ directory contains the reference versions. They are SIMPLE — 8-15 attributes each, no calibration, no WB adjustments, no extreme values. They prioritize subtlety over "pop."
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.
- 17d ago Changed · +4 lines · +428 tokens per session 6bdfcd771d44
- 2mo ago First seen · 98 lines · 1,871 tokens per session scan A 459f5da82324
Lightroom-Presets AGENTS.md is an instructions file published in the GitHub repository peva3/Lightroom-Presets (104 stars, last pushed 17d ago), licensed MIT. It adds 2,299 tokens to every session, about $0.0092 per session on Opus 5.5. 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 2026-08-30.
Lightroom-Presets AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Lightroom-Presets AGENTS.mdpeva3/Lightroom-Presets | Instructions file | 104 | 17d ago | MIT | A | 2,299 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |