grade-m

grade-m is an agent for coding agents from jenkinsm13/resolve-mcp. It costs 43 tokens per session (3,395 once invoked), scanned A, a copy of grade-k, MIT.

A DaVinci Resolve color-grading agent that builds Juan M.’s five-stage node layout, an ordered set of correction steps.

In plain words
What is it for?
Use it to prepare a clip, create the five-stage node structure, and apply corrections in the intended order, with the look and LUT applied later.
Why use it?
A consistent order helps color adjustments preserve useful image information and keeps later changes easier to control.

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-m
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-m

README.md
[![agentmods](https://agentmods.dev/badge/agents/jenkinsm13/resolve-mcp/grade-m.svg)](https://agentmods.dev/agents/jenkinsm13/resolve-mcp/grade-m)
Your own site
<a href="https://agentmods.dev/agents/jenkinsm13/resolve-mcp/grade-m"><img src="https://agentmods.dev/badge/agents/jenkinsm13/resolve-mcp/grade-m.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,395 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 88% copy Near-identical to another mod 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 $0.00043 $0.03395
Opus 5 $0.00022 $0.01698
Sonnet 5 $0.00009 $0.00679
Haiku 4.5 $0.00004 $0.00340

Measured 4d ago against content hash ede0d5dc388c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

grade-m 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 4d 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

This is a copy

88% identical to grade-k — 218 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

agents/grade-m.md · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Juan M. Node Structure Agent

You implement Juan M.'s 5-stage node methodology — a logical, data-preserving approach to color grading that prioritises correct order of operations for maximum downstream flexibility.

Philosophy

The core insight: corrections in a logical order, each preserving the image data needed for the next stage. A balanced, information-rich image makes downstream keying easier. A properly exposed image makes look application more predictable.

Key principles:

  • Order of operations matters — balance before look, look before final
  • Each stage preserves data for the next — a balanced image keys better
  • LUTs go last — applying them on the final node produces better results
  • The final node is an "adjustable LUT" — a consistent finishing layer

Build Procedure

Step 1: Prepare the clip

resolve_switch_page("color")
resolve_item_add_version("M. 5-Stage")
resolve_reset_grades()

Step 2: Build the 5-stage structure

Start from default 1 node. Add 4 more serial nodes, plus a parallel branch for Stage 3:

# Build serial backbone (5 nodes)
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

Step 3: Label the 5 stages

resolve_node_set_label(1, "BALANCE")
resolve_node_set_label(2, "LOCAL EXPOSURE")
resolve_node_set_label(3, "LOCAL COLOR")
resolve_node_set_label(4, "LOOK")
resolve_node_set_label(5, "FINAL")

Step 4: Expand Stage 3 with parallel nodes

Stage 3 (LOCAL COLOR) often needs multiple qualifiers that overlap. Add parallel nodes for separate corrections:

resolve_node_add_parallel(3)
resolve_node_set_label(NEW_INDEX, "SKIN")

resolve_node_add_parallel(3)
resolve_node_set_label(NEW_INDEX, "SKY/ENV")

Step 5: (Optional) Add CST wrapper for color-managed workflows

For color-managed projects, add CST nodes at the beginning and end:

# Insert a new serial node at position 0 (before BALANCE)
# Note: After insertion, all indices shift. Re-check with node_overview.
resolve_node_add_serial(0)
resolve_node_set_label(1, "CST IN")

# Append a serial node at the end (after FINAL)
resolve_node_add_serial(LAST_INDEX)
resolve_node_set_label(NEW_INDEX, "CST OUT")

Read the full file on GitHub · 276 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. 4d ago First seen · 276 lines · 43 tokens per session scan A ede0d5dc388c

Subscribe to this mod's changes

grade-m is an agent published in the GitHub repository jenkinsm13/resolve-mcp (6 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 3,395 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to grade-k, differing in 218 lines, and is treated as a copy.

Related

Other agents, from other repositories

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

AGENTS.motiscope

Agent "AGENTS.motiscope" from KumarSashank/motiscope, covering motiscope — recreate animations from screen recordings, the division of labor, commands and workflows.

KumarSashank/motiscope · 0 tokens

proposal-writer

Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.

Zeekeey-jpeg/LeRoy-HQ · 34 tokens

sagi-haviv

ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.

felipenalves/InvOS · 0 tokens

image-generator

Use this agent when the conversation context involves generating or editing images. This agent should be used proactively when image creation would help the user's task. It also covers named product and brand assets, which users rarely call "images": app icons, bot avatars, logos, favicons, hero images, banners…

hex/claude-image-generation · 378 tokens

builder

Turn shot-plan.json into one renderable HyperFrames composition (compositions/index.html). Everything stays in the HF ecosystem — HTML is the source of truth; a single paused GSAP timeline carries all motion; the engine seeks it. Category-specific build rules live in categories/ /module.md; this file is the shared…

chmonitor/chmonitor · 0 tokens