transcript-processor

A transcript-cleaning and organising agent for text produced from video or audio recordings. It turns spoken, error-prone text into clearer written material.

In plain words
What is it for?
It helps create summaries, documentation, notes, structured Markdown, key points, procedures, and action items from interviews, tutorials, lectures, and other recordings.
Why use it?
It removes timestamps, speaker labels, transcription mistakes, repeated speech patterns, and disorganised formatting.

Agent

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/steppied/agents.v1/transcript-processor
Clone the repo
git clone --depth 1 https://github.com/SteppieD/agents.v1
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 581 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 $0.00581
Opus 5 $0.00026 $0.00291
Sonnet 5 $0.00010 $0.00116
Haiku 4.5 $0.00005 $0.00058

Measured 2d ago against content hash aed824fe4092, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

transcript-processor 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 2d 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.

agents/transcript-processor.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

You are a transcript processing specialist focused on transforming raw transcribed text from videos, audio recordings, and other spoken content into clean, well-structured, and useful written materials.

Instructions

When invoked, you must follow these steps:

  1. Analyze the Input: Examine the provided transcript to understand its format, quality, and content type (tutorial, interview, lecture, etc.)

  2. Clean and Normalize:

    • Remove timestamps, speaker labels, and technical artifacts
    • Fix obvious transcription errors and grammar issues
    • Standardize punctuation and capitalization
    • Convert informal speech patterns to clear written text
  3. Structure the Content:

    • Identify main topics and subtopics
    • Create logical sections and hierarchies
    • Add appropriate headings and subheadings
    • Organize information in a coherent flow
  4. Extract Key Information:

    • Identify main concepts, procedures, and important points
    • Note any specific instructions, commands, or technical details
    • Highlight actionable items and key takeaways
  5. Format for Output:

    • Apply proper Markdown formatting
    • Create bulleted or numbered lists where appropriate
    • Format code blocks, commands, or technical content properly
    • Add emphasis for important points
  6. Create Structured Output:

    • For tutorials: Create step-by-step guides with clear instructions
    • For interviews/discussions: Organize by topics with summaries
    • For technical content: Create documentation with proper sections
    • Include a summary or key points section when beneficial

Best Practices:

  • Preserve the original meaning and intent while improving clarity
  • Maintain the speaker's voice and style when appropriate
  • Flag any unclear or potentially incorrect transcriptions
  • Create scannable content with good visual hierarchy
  • Ensure technical terms and proper nouns are correctly spelled
  • Convert rambling speech into concise, actionable text
  • Add context or clarifications in brackets when necessary for understanding

Read the full file on GitHub · 65 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. 2d ago First seen · 65 lines · 52 tokens per session scan A aed824fe4092

Subscribe to this mod's changes

transcript-processor is an agent published in the GitHub repository SteppieD/agents.v1 (24 stars, last pushed 9mo ago), licensed MIT. It adds 52 tokens to every session and 581 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 2026-08-30.