triage-recording

triage-recording is a command for Claude Code from korovin-aa97/talkthrough-mcp. It costs 24 tokens per session (705 once invoked), scanned A, original, MIT.

A workflow for turning a narrated screen recording into structured findings with supporting video frames. It routes each finding as a bug, feature request, or question and checks the recording for repeated mentions.

In plain words
What is it for?
Processing a recording, inspecting relevant moments, reading on-screen text, confirming ambiguous details, and producing evidence-backed findings.
Why use it?
It connects spoken feedback to visible evidence, making reported problems easier to verify and file accurately.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the talkthrough plugin — 6 commands, 1 agent shipped together

Good fit Processing a recording, inspecting relevant moments, reading on-screen text, confirming ambiguous details, and producing evidence-backed findings.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/korovin-aa97/talkthrough-mcp/triage-recording
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.

Clone the repo
git clone --depth 1 https://github.com/korovin-aa97/talkthrough-mcp

Made for: Claude Code.

Or install talkthrough, the plugin that ships this one along with the rest of its 6 commands, 1 agent.

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 triage-recording

README.md
[![agentmods](https://agentmods.dev/badge/commands/korovin-aa97/talkthrough-mcp/triage-recording/github.svg)](https://agentmods.dev/commands/korovin-aa97/talkthrough-mcp/triage-recording)
Your own site
<a href="https://agentmods.dev/commands/korovin-aa97/talkthrough-mcp/triage-recording"><img src="https://agentmods.dev/badge/commands/korovin-aa97/talkthrough-mcp/triage-recording/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for triage-recording

Your own site · 80×15
<a href="https://agentmods.dev/commands/korovin-aa97/talkthrough-mcp/triage-recording"><img src="https://agentmods.dev/badge/commands/korovin-aa97/talkthrough-mcp/triage-recording.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 705 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00024 $0.00705
Opus 5 $0.00012 $0.00352
Sonnet 5 $0.00005 $0.00141
Haiku 4.5 $0.00002 $0.00071

Measured 11d ago against content hash 31c595dea4ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

triage-recording 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 11d 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.

integrations/claude-code/commands/triage-recording.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

If no job_id was passed as an argument: call list_jobs() to find the right recording, or process_media(path) if the user gave a file path — then follow the workflow below with that job_id.

You are a meticulous triage agent. A narrated screen recording was processed by talkthrough as job $ARGUMENTS. Turn it into precise, evidence-backed findings.

Method

  1. If you do not have the job summary yet, call get_transcript(job_id="$ARGUMENTS") (paginate via next_start_ms if truncated). If the job_id looks wrong, verify with list_jobs().
  2. Walk the transcript in order. Every remark that points at a problem, deviation, or wish becomes a candidate finding. The narrator's words are directives, not suggestions.
  3. For each candidate, call get_moment(job_id="$ARGUMENTS", start_ms=, end_ms=<t1+2000>). Describe observed from the returned frames and OCR text — from the pixels, never from imagination.
  4. Cross-check: use search(job_id="$ARGUMENTS", query="") to find repeat mentions of the same issue and merge them into one finding.
  5. If a frame is ambiguous, call extract_frame(job_id="$ARGUMENTS", at_ms=, crop=) for a full-resolution look before judging.

Output contract

Return ONE fenced JSON object, no other prose:

  • findings: array of objects with: title, quote (narrator's exact words), t_ms, t_wall (null when unknown), frame_refs (frame files you actually looked at), observed, expected, acceptance_criteria (verifiable list), verify_via (the exact flow to reproduce), route = "bug" | "feature" | "question", severity = "P1" (flow broken) | "P2" (default) | "P3" (polish), confidence = "high" | "medium" | "low", and question (only when route="question").
  • digest: a numbered one-line-per-finding summary the recording author can answer with "1,3-4".
  • key_frames: 2-3 frame refs that best show the problems.

Key names above are the contract — use them EXACTLY as written (quote, frame_refs, t_ms, …): no renames, no wrappers, no quotes[] or evidence[] arrays. Downstream tooling reads these keys mechanically.

Read the full file on GitHub · 51 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. 11d ago First seen · 51 lines · 24 tokens per session scan A 31c595dea4ee

Subscribe to this mod's changes

triage-recording is a command published in the GitHub repository korovin-aa97/talkthrough-mcp (28 stars, last pushed 4d ago), licensed MIT. It adds 24 tokens to every session and 705 once invoked, about $0.0001 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.