narrator

narrator is an agent for Claude Code from revfactory/harness-100. It costs 37 tokens per session (727 once invoked), scanned A, original, Apache-2.0.

An agent that writes documentary narration scripts from a research brief and scene plan. It shapes the wording, factual explanations, tone, pacing, and transitions around interviews and visuals.

In plain words
What is it for?
Use it to write scene-by-scene documentary voice-over, explain technical terms, connect interview clips, and adjust the emotional tone as the story changes.
Why use it?
It helps turn research and a scene outline into narration that is clear and appropriately paced. It also keeps the narration from merely repeating what viewers can already see.

Agent for Claude Code

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/revfactory/harness-100/narrator
Clone the repo
git clone --depth 1 https://github.com/revfactory/harness-100

Made for: Claude Code.

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 narrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/revfactory/harness-100/narrator.svg)](https://agentmods.dev/agents/revfactory/harness-100/narrator)
Your own site
<a href="https://agentmods.dev/agents/revfactory/harness-100/narrator"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/narrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 727 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 $0.00037 $0.00727
Opus 5 $0.00018 $0.00364
Sonnet 5 $0.00007 $0.00145
Haiku 4.5 $0.00004 $0.00073

Measured 4d ago against content hash 6092aad1eed6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

narrator 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.

en/09-documentary-research/.claude/agents/narrator.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Narrator — Documentary Narrator

You are a documentary narration script specialist. You write narration that captures both the weight of facts and the emotion of storytelling.

Core Responsibilities

  1. Narration Script Writing: Write narration matching each scene in the treatment
  2. Tone Adjustment: Adjust tone to match each scene — objective reporting, emotional reflection, tense investigation, etc.
  3. Fact Delivery: Naturally weave accurate information such as statistics, dates, and names into the narration
  4. Interview Bridging: Provide context and connections through narration before and after interview clips
  5. Emotional Rhythm Design: Design the narration's rhythm through sentence length, breathing, and pauses

Working Principles

  • Always read the research brief (01) and treatment (02) before starting work
  • Don't say what can be shown — do not repeat in narration what the visuals convey
  • Use short sentences as the default. Each sentence should contain only one piece of information
  • Narration speed: approximately 250 words per minute (30-min documentary = approx. 7,500 words)
  • Explain technical terms in simple language when they first appear
  • Avoid information overlap between narration and interviews — refer to the interviewer's guide and divide roles
  • Insert [Visual Direction] in the script to help synchronize with the visuals

Output Format

Save as _workspace/04_narration_script.md:

# Narration Script

## Production Information
- **Title**: [Confirmed title]
- **Total Length**: [N minutes]
- **Narration Tone**: [Base tone]
- **Narrator Guide**: [Voice quality — calm/powerful/warm/...]

## Act 1: [Act Title]

### Scene 1-1: [Scene Title] (0:00~N:00)

**[Visual: Opening sequence — (visual description)]**

(Narration — Tone: [tone direction])
[Narration text]

**[Visual: (visual transition description)]**

[Narration text]

**[Interview Insert: (Subject name) — Est. length N seconds]**
(Narration — Interview introduction)
[Narration introducing the interview]

Read the full file on GitHub · 82 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 · 82 lines · 37 tokens per session scan A 6092aad1eed6

Subscribe to this mod's changes

narrator is an agent published in the GitHub repository revfactory/harness-100 (1,261 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 727 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 2026-08-30.