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/backlog-from-demo)<a href="https://agentmods.dev/commands/korovin-aa97/talkthrough-mcp/backlog-from-demo"><img src="https://agentmods.dev/badge/commands/korovin-aa97/talkthrough-mcp/backlog-from-demo/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/backlog-from-demo"><img src="https://agentmods.dev/badge/commands/korovin-aa97/talkthrough-mcp/backlog-from-demo.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 | $0.00014 | $0.00342 |
| Opus 5 | $0.00007 | $0.00171 |
| Sonnet 5 | $0.00003 | $0.00068 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade A, and why
backlog-from-demo 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 10d 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.
What it actually says
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 product owner turning a recorded product demo into a prioritized
backlog. The demo was processed by talkthrough as job $ARGUMENTS.
Method
- get_transcript(job_id="$ARGUMENTS") — first pass; note every feature shown, every rough edge, every "we should…" remark.
- For each candidate backlog item, call get_moment(job_id="$ARGUMENTS", start_ms=..., end_ms=...) around the remark to capture what the screen actually showed (frames + OCR).
- search(job_id="$ARGUMENTS", query="") to gather all mentions of the same capability before writing its item.
- Use the wall-clock (t_wall) values in evidence so stakeholders can find the demo moment in their calendars/notes.
Output
A markdown backlog table, ordered by priority, one row per item:
| # | Title | User story | Evidence (quote + t_ms + frame ref) | Effort (S/M/L) | Priority (P1-P3) |
Below the table: a "Cut lines" section — items explicitly deferred in the demo, each with the deferring quote and timestamp. Every row MUST carry real evidence from the recording; no invented items. Write items in the demo's language; evidence quotes stay verbatim.
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.
- 10d ago First seen · 32 lines · 14 tokens per session scan A 8548ab6a1f7d
backlog-from-demo is a command published in the GitHub repository korovin-aa97/talkthrough-mcp (28 stars, last pushed 4d ago), licensed MIT. It adds 14 tokens to every session and 342 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
onplana-connect
Connect Claude Code to the Onplana MCP server, then verify it works.
staff-event
Build a complete event staffing plan (configured-market match, W-2 rates, tier-based lead time, compliance) and prepare a buyer-submitted quote form.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.