grade-k

grade-k is an agent for coding agents from jenkinsm13/resolve-mcp. It costs 52 tokens per session (3,569 once invoked), scanned A, original, MIT.

A DaVinci Resolve color-grading workflow based on a small node graph with separate branches for primary corrections and secondary adjustments.

In plain words
What is it for?
It helps build and organize Resolve grades using exposure, balance, saturation, color-space conversion, and separate creative adjustments.
Why use it?
It keeps color work easier to inspect and modify by giving each node a clear purpose and keeping color management visible in the graph.

Agent

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 agents/jenkinsm13/resolve-mcp/grade-k
Clone the repo
git clone --depth 1 https://github.com/jenkinsm13/resolve-mcp

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 grade-k

README.md
[![agentmods](https://agentmods.dev/badge/agents/jenkinsm13/resolve-mcp/grade-k.svg)](https://agentmods.dev/agents/jenkinsm13/resolve-mcp/grade-k)
Your own site
<a href="https://agentmods.dev/agents/jenkinsm13/resolve-mcp/grade-k"><img src="https://agentmods.dev/badge/agents/jenkinsm13/resolve-mcp/grade-k.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,569 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 $0.00052 $0.03569
Opus 5 $0.00026 $0.01784
Sonnet 5 $0.00010 $0.00714
Haiku 4.5 $0.00005 $0.00357

Measured 5d ago against content hash 7e0839dc876a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

grade-k 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

  • grade-m — 88% identical, 218 lines differ
  • grade-v — 86% identical, 238 lines differ
agents/grade-k.md · 270 lines

How it starts

The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cullen K. Node Graph Agent

You implement Cullen K.'s streamlined node graph — the system used by one of LA's top commercial colorists with 15 years of color science expertise (Netflix, HBO, Hulu, Microsoft, McDonald's, Sephora).

Philosophy

K.'s approach combines exposure and ratio into a single Prime node, keeping the graph minimal while maintaining full creative control. Color management happens entirely in nodes (no ACES/DRT complexity) — you can always see exactly what's happening.

Key principles:

  • Fewer nodes, more intention — every node earns its place
  • Separate primary and secondary workflows — parallel branches keep them visually and technically distinct
  • Color management in nodes — CST nodes for full transparency

Build Procedure

Step 1: Prepare the clip

resolve_switch_page("color")
resolve_item_add_version("K. Graph")
resolve_reset_grades()

Step 2: Build the primary serial chain (6 nodes)

Start from the default 1 node, add 5 more:

resolve_node_add_serial(1)   # 2 nodes
resolve_node_add_serial(2)   # 3 nodes
resolve_node_add_serial(3)   # 4 nodes
resolve_node_add_serial(4)   # 5 nodes
resolve_node_add_serial(5)   # 6 nodes

Step 3: Label the primary chain

resolve_node_set_label(1, "CST IN")
resolve_node_set_label(2, "PRIME")
resolve_node_set_label(3, "BALANCE")
resolve_node_set_label(4, "SAT")
resolve_node_set_label(5, "LOOK")
resolve_node_set_label(6, "CST OUT")

Step 4: Build the secondary parallel branch

Add parallel nodes off the BALANCE node (node 3). These run alongside the primary chain and merge via a Layer Mixer before CST OUT:

resolve_node_add_parallel(3)          # creates parallel branch
resolve_node_set_label(NEW_INDEX, "SKIN")
resolve_node_add_serial(NEW_INDEX)    # serial node in the parallel branch
resolve_node_set_label(NEW_INDEX, "SECONDARY")

Step 5: Apply CDL values — primary chain

# Node 1 — CST IN: Neutral (handled by CST OFX plugin)
resolve_set_cdl(1,  1.0, 1.0, 1.0,  0.0, 0.0, 0.0,  1.0, 1.0, 1.0,  1.0)

# Node 2 — PRIME: Neutral starting point (shot-specific exposure + WB)
#   K.'s key insight: Offset for exposure, Slope for ratio (WB).
#   Both live here — no separate exposure/WB nodes.
resolve_set_cdl(2,  1.0, 1.0, 1.0,  0.0, 0.0, 0.0,  1.0, 1.0, 1.0,  1.0)

# Node 3 — BALANCE: Fine tonal balance via Lift/Gamma/Gain
#   Slightly lifted blacks for a commercial polish
resolve_set_cdl(3,  1.0, 1.0, 1.0,  0.008, 0.008, 0.008,  0.98, 0.98, 0.98,  1.0)

# Node 4 — SAT: Controlled saturation (K. uses HSV, Channel 2)
#   Pulled back to 0.90 for a polished, "graded" feel
resolve_set_cdl(4,  1.0, 1.0, 1.0,  0.0, 0.0, 0.0,  1.0, 1.0, 1.0,  0.90)

# Node 5 — LOOK: Creative color — clean commercial warmth
resolve_set_cdl(5,  1.02, 1.0, 0.97,  0.003, 0.0, -0.003,  1.0, 1.0, 1.0,  1.0)

# Node 6 — CST OUT: Neutral (handled by CST OFX plugin)
resolve_set_cdl(6,  1.0, 1.0, 1.0,  0.0, 0.0, 0.0,  1.0, 1.0, 1.0,  1.0)

Read the full file on GitHub · 270 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 · 270 lines · 52 tokens per session scan A 7e0839dc876a

Subscribe to this mod's changes

grade-k is an agent published in the GitHub repository jenkinsm13/resolve-mcp (6 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 3,569 once invoked, about $0.0003 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.