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.
git clone --depth 1 https://github.com/korovin-aa97/talkthrough-mcpWrote 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.
[](https://agentmods.dev/commands/korovin-aa97/talkthrough-mcp/triage-recording)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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 $ARGUMENTS. Turn it into precise, evidence-backed findings.
Method
- If you do not have the job summary yet, call get_transcript(job_id="$ARGUMENTS") (paginate via next_start_ms if truncated). If the job_id looks wrong, verify with list_jobs().
- 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.
- For each candidate, call get_moment(job_id="$ARGUMENTS", start_ms=,
end_ms=<t1+2000>). Describe
observedfrom the returned frames and OCR text — from the pixels, never from imagination. - Cross-check: use search(job_id="$ARGUMENTS", query="") to find repeat mentions of the same issue and merge them into one finding.
- 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", andquestion(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.
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.
- 11d ago First seen · 51 lines · 24 tokens per session scan A 31c595dea4ee
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.
Other commands, from other repositories
preflight
Diagnostique l'environnement Cortex et guide la réparation (DB, extensions, modèles).
ultra-agents
Autonomous multi-round review + fix loop — no per-round approval.
api-aqa-flow-execution-and-report-analysis
Phase 6 Execution & Report Analysis of api-aqa-flow (USER INTERACTION REQUIRED).
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.