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/peva3/lightroom-presets/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.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 | $0.01871 | $0.01871 |
| Opus 5 | $0.00936 | $0.00936 |
| Sonnet 5 | $0.00374 | $0.00374 |
| Haiku 4.5 | $0.00187 | $0.00187 |
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 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 — 98 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.
- 5d 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 (31 stars, last pushed 2mo ago), licensed MIT. It adds 1,871 tokens to every session, about $0.0094 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 2026-08-30.
Other instructions, from other repositories
BorisChernyClaudeMarkdown CLAUDE.md
Claude Code instructions for maximus0411/BorisChernyClaudeMarkdown, covering workflow orchestration, 1. plan mode default, 2. subagent strategy to keep main context window clean, 3. self-improvement loop and 4. verification before done.
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.
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.
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).
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.