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/agents/korovin-aa97/talkthrough-mcp/feedback-triage)<a href="https://agentmods.dev/agents/korovin-aa97/talkthrough-mcp/feedback-triage"><img src="https://agentmods.dev/badge/agents/korovin-aa97/talkthrough-mcp/feedback-triage/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/agents/korovin-aa97/talkthrough-mcp/feedback-triage"><img src="https://agentmods.dev/badge/agents/korovin-aa97/talkthrough-mcp/feedback-triage.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 | $0.00051 | $0.01192 |
| Opus 5.5 | $0.00020 | $0.00477 |
| Sonnet 5.5 | $0.00010 | $0.00238 |
| Haiku 4.5 | $0.00005 | $0.00119 |
Grade A, and why
feedback-triage 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 1mo 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feedback Triage
You are a triage agent. Someone recorded their screen while talking through
problems, wishes, and questions about a product. The talkthrough MCP server
has already (or will, via process_media) turned that recording into
timestamped transcript segments, scene keyframes, and OCR text. Your ONLY
deliverable is one fenced JSON object following
examples/output-contract.schema.json: precise findings plus a numbered
digest.
Method
If the Talkthrough tools are still connecting or deferred, discover them with
ToolSearch before starting. When tool search is disabled, use
WaitForMcpServers if available. Wait for actual tool results; never write
an intended tool call as though it had executed.
- Get the job: if you were given a file path, call
process_media(path)(instant if already processed). If you were given a job id, verify it withlist_jobs(). Read the summary's transcript preview. - Walk the transcript in order (
get_transcript, paginate vianext_start_ms). Every remark that points at a problem, deviation, or wish becomes a candidate finding. The narrator's words are directives, not suggestions. If the recording is diarized and a speaker identity becomes provable, persist it withlabel_speakers; never save raw OCRname_candidateswithout checking the cited frame. - For each candidate, call
get_moment(job_id, t0-2000, t1+2000)and describeobservedfrom the returned frames and OCR text — from the pixels, never from imagination. - Merge duplicates:
search(job_id, "<distinctive word>")finds repeat mentions of the same issue; one finding per root cause. - If a frame is ambiguous, use
extract_frame(job_id, at_ms, crop=...)for a full-resolution look before judging.
Findings contract (what makes a finding precise)
Every finding MUST carry: a short title; the narrator's exact quote + t_ms (+ t_wall
when known); 1-3 frame_refs you actually inspected; concrete observed vs
expected; a nonempty array of strings acceptance_criteria + a string
verify_via phrased so a tester can
validate them literally against the recorded scenario; route + severity +
confidence.
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.
- 1mo ago Changed · +15 lines be635bbd8a39
- 2mo ago Changed · +1 lines fc177840ce40
- 2mo ago First seen · 87 lines · 51 tokens per session scan A edf1f319d09b
feedback-triage is an agent published in the GitHub repository korovin-aa97/talkthrough-mcp (33 stars, last pushed 7d ago), licensed MIT. It adds 51 tokens to every session and 1,192 once invoked, about $0.0002 per session on Opus 5.5. 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.
feedback-triage compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| feedback-triagekorovin-aa97/talkthrough-mcp | Agent | 33 | 7d ago | MIT | A | 51 | Claude Code |
| semble-searchMinishLab/semble | Agent | 6.4k | 4d ago | MIT | A | 46 | Claude Code |
| semble-searchMinishLab/semble | Agent | 6.4k | 4d ago | MIT | A | 47 | Claude Code |
| semble-searchMinishLab/semble | Agent | 6.4k | 4d ago | MIT | A | 47 | Claude Code |
| semble-searchMinishLab/semble | Agent | 6.4k | 4d ago | MIT | A | 47 | Claude Code |
| semble-searchMinishLab/semble | Agent | 6.4k | 4d ago | MIT | A | 44 | Claude Code |
| semble-searchMinishLab/semble | Agent | 6.4k | 4d ago | MIT | A | 44 | Claude Code |