match-reference

match-reference is a skill for Claude Code, Codex from jenkinsm13/resolve-mcp. It costs 42 tokens per session (1,013 once invoked), scanned A, original, MIT.

A DaVinci Resolve workflow that adjusts the current frame’s color grade to resemble a supplied reference image.

In plain words
What is it for?
Use it to compare the current frame with the reference in the same color space and adjust CDL color-correction nodes toward the reference.
Why use it?
It helps match a target visual style when the desired look is represented by a film still, screenshot, LUT preview, or another image.

Skill for Claude CodeCodex

Part of the resolve-mcp plugin — 16 skills, 25 agents, 2 hooks, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add skills/jenkinsm13/resolve-mcp/match-reference
Any agent
npx skills add jenkinsm13/resolve-mcp --skill match-reference
Clone the repo
git clone --depth 1 https://github.com/jenkinsm13/resolve-mcp

Made for: Claude Code, Codex.

Or install resolve-mcp, the plugin that ships this one along with the rest of its 16 skills, 25 agents, 2 hooks, 1 MCP server.

Wrote 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.

agentmods badge for match-reference

README.md
[![agentmods](https://agentmods.dev/badge/skills/jenkinsm13/resolve-mcp/match-reference.svg)](https://agentmods.dev/skills/jenkinsm13/resolve-mcp/match-reference)
Your own site
<a href="https://agentmods.dev/skills/jenkinsm13/resolve-mcp/match-reference"><img src="https://agentmods.dev/badge/skills/jenkinsm13/resolve-mcp/match-reference.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,013 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00042 $0.01013
Opus 5 $0.00021 $0.00507
Sonnet 5 $0.00008 $0.00203
Haiku 4.5 $0.00004 $0.00101

Measured 5d ago against content hash 976d0305eee2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

match-reference 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.

.claude/skills/match-reference/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/match-reference — Match a Reference Image

Look at a reference image and the current timeline frame side by side, then adjust the grade to match the reference.

Arguments

The user provides a path to a reference image. This can be:

  • A still frame from another project
  • A film still or screenshot
  • A LUT preview image
  • Any image that represents the target look

Workflow

1. Switch to Color page

Use resolve_switch_page("color").

2. Export current frame in sRGB

Use resolve_export_frame to export to /tmp/resolve_match_current.png.

Convert to sRGB with ffmpeg:

ffmpeg -y -i /tmp/resolve_match_current.png \
  -vf "colorspace=all=bt709:iall=bt2020:fast=1" \
  -color_primaries bt709 -color_trc iec61966-2-1 -colorspace bt709 \
  /tmp/resolve_match_current_srgb.png 2>/dev/null

Fallback if that fails:

ffmpeg -y -i /tmp/resolve_match_current.png -pix_fmt rgb24 /tmp/resolve_match_current_srgb.png 2>/dev/null

3. Read both images

Use the Read tool on both:

  • /tmp/resolve_match_current_srgb.png (current timeline frame)
  • The user's reference image path

Claude can see both images simultaneously and compare them visually.

4. Get current grade state

Use resolve_node_overview to see all nodes. Use resolve_get_cdl to read current CDL. Use resolve_get_node_count for node count.

5. Analyze the difference

Compare the reference to the current frame across these dimensions:

Overall exposure: Is the reference brighter/darker? Contrast curve: Is the reference higher/lower contrast? Are blacks lifted or crushed? Color temperature: Is the reference warmer or cooler? Shadow color: What hue are the shadows in the reference? (teal, blue, purple, neutral) Highlight color: What hue are the highlights? (warm, cool, neutral) Midtone color: Any color shift in the midtones? Saturation level: More or less saturated than current? Specific color shifts: Any obvious color grading choices (orange/teal, bleach bypass, cross-process, etc.)

Read the full file on GitHub · 119 lines

Changes

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.

  1. 5d ago First seen · 119 lines · 42 tokens per session scan A 976d0305eee2

Subscribe to this mod's changes

match-reference is a skill published in the GitHub repository jenkinsm13/resolve-mcp (6 stars, last pushed 4mo ago), licensed MIT. It adds 42 tokens to every session and 1,013 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

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…

microsoft/vscode · 72 tokens