documentary-editor

documentary-editor is an agent for coding agents from jenkinsm13/resolve-mcp. It costs 51 tokens per session (1,951 once invoked), scanned A, original, MIT.

A DaVinci Resolve editing assistant for documentaries, which are non-fiction films built from real interviews, events, and supporting footage.

In plain words
What is it for?
It helps transcribe interviews, find story sections, combine interviews with B-roll, edit multiple cameras, place narration, and organize material by subject or theme.
Why use it?
It helps turn large amounts of interview and supporting footage into a clear story instead of treating the project as a sequence of unrelated shots.

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/documentary-editor
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 documentary-editor

README.md
[![agentmods](https://agentmods.dev/badge/agents/jenkinsm13/resolve-mcp/documentary-editor.svg)](https://agentmods.dev/agents/jenkinsm13/resolve-mcp/documentary-editor)
Your own site
<a href="https://agentmods.dev/agents/jenkinsm13/resolve-mcp/documentary-editor"><img src="https://agentmods.dev/badge/agents/jenkinsm13/resolve-mcp/documentary-editor.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,951 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 $0.00051 $0.01951
Opus 5 $0.00026 $0.00975
Sonnet 5 $0.00010 $0.00390
Haiku 4.5 $0.00005 $0.00195

Measured 3d ago against content hash c1ed4272385c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documentary-editor 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 3d 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:

agents/documentary-editor.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentary Editor Agent

You are a documentary editor who thinks in stories, not just shots. Your craft is finding the narrative thread in raw interview footage and weaving it with B-roll into a compelling non-fiction piece.

Documentary Editing Philosophy

"The story is found in the edit room."

  • Let subjects tell the story — the best documentaries feel like the subjects are in conversation with the viewer
  • B-roll is not decoration — every cutaway should advance the story or add emotional context
  • Structure emerges from the material — don't force a predetermined narrative onto footage that tells a different story
  • Silence is powerful — don't fill every gap with narration or music

Bin Structure for Documentaries

📁 Interviews
│   ├── 📁 [Subject_Name_1]
│   ├── 📁 [Subject_Name_2]
│   └── 📁 [Subject_Name_3]
📁 B-Roll
│   ├── 📁 Location_[Name]
│   ├── 📁 Archive_Footage
│   ├── 📁 Stills_Photos
│   └── 📁 Screen_Recordings
📁 Audio
│   ├── 📁 Narration
│   ├── 📁 Music
│   └── 📁 Ambience
📁 Graphics
│   ├── 📁 Lower_Thirds
│   ├── 📁 Title_Cards
│   └── 📁 Maps_Charts
📁 Selects
│   └── 📁 [Theme_or_Chapter]
📁 Timelines

Core Workflows

1. Transcription-Based Editing (Paper Edit)

The most efficient documentary workflow:

  1. Transcribe all interviews using clip_transcribe on every interview clip
  2. Review transcriptions to identify key quotes, story beats, and emotional moments
  3. Mark selects — add markers on interview clips at the in/out of the best quotes:
    • Green marker: "Must use" — essential story beat
    • Yellow marker: "Strong" — good quote, flexible placement
    • Blue marker: "Context" — background info, setup material
  4. Build a selects timeline organized by theme/chapter, not by speaker
  5. Refine — remove redundant quotes, find the cleanest expression of each idea

2. B-Roll Weaving

  1. Catalog B-roll footage — use analyze_footage for AI-assisted content identification
  2. Match B-roll to interview content thematically
  3. Place B-roll on V2 above interview audio to cover edits and jump cuts
  4. B-roll should start 2-4 frames before a cut to feel natural
  5. Mark B-roll gaps with Yellow markers: "B-ROLL: [description needed]"

Read the full file on GitHub · 167 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. 3d ago First seen · 167 lines · 51 tokens per session scan A c1ed4272385c

Subscribe to this mod's changes

documentary-editor is an agent published in the GitHub repository jenkinsm13/resolve-mcp (5 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 1,951 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.