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/spec-from-workshop)<a href="https://agentmods.dev/commands/korovin-aa97/talkthrough-mcp/spec-from-workshop"><img src="https://agentmods.dev/badge/commands/korovin-aa97/talkthrough-mcp/spec-from-workshop.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.00451 |
| Opus 5 | $0.00009 | $0.00226 |
| Sonnet 5 | $0.00004 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
spec-from-workshop 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 8d 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 engineer writing a spec from a recorded workshop / design
walkthrough, processed by talkthrough as job $ARGUMENTS.
Method
- Read the whole discussion: get_transcript(job_id="$ARGUMENTS", format="text"); for long sessions page with start_ms/end_ms via the segments format instead.
- Identify decision points and requirement statements. For each, keep the speaker's exact wording and t_ms; re-read the precise slice with get_transcript(job_id="$ARGUMENTS", start_ms=..., end_ms=...) when in doubt.
- Whenever the discussion references something visual (whiteboard, mockup, screen), pull it: get_frames(job_id="$ARGUMENTS", at_ms=) — or get_moment(job_id="$ARGUMENTS", start_ms=..., end_ms=...) for slice + frames + OCR in one call.
- Use search(job_id="$ARGUMENTS", query="") to collect every mention of a contested term before writing its section.
Output
A markdown spec with these sections:
- Goal — one paragraph, in the participants' own framing.
- Decisions — bullet list; each bullet: the decision, a supporting quote,
t_ms/t_wall. - Requirements — numbered, testable statements; mark each MUST/SHOULD/COULD.
- Visual references — frame refs for every screen/mockup discussed.
- Open questions — everything ambiguous or contested, with the quote that raised it. Do not resolve ambiguity yourself — surface it.
Copy t_wall values VERBATIM from the payload — never compute them from t_ms
yourself. Write the spec in the workshop's language; 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.
- 8d ago First seen · 38 lines · 18 tokens per session scan A 8eca779de701
spec-from-workshop is a command published in the GitHub repository korovin-aa97/talkthrough-mcp (26 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 451 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
compile
Compile a FIBER decision context (world + query) and report the oracle verdict, omission accounting, and certificate digest faithfully.
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.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.