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.
npx skills add tryproduck/produck-skills --skill produck-feedbackgit clone --depth 1 https://github.com/tryproduck/produck-skillsWrote 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/skills/tryproduck/produck-skills/produck-feedback)<a href="https://agentmods.dev/skills/tryproduck/produck-skills/produck-feedback"><img src="https://agentmods.dev/badge/skills/tryproduck/produck-skills/produck-feedback/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/skills/tryproduck/produck-skills/produck-feedback"><img src="https://agentmods.dev/badge/skills/tryproduck/produck-skills/produck-feedback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00090 | $0.00968 |
| Opus 5 | $0.00045 | $0.00484 |
| Sonnet 5 | $0.00018 | $0.00194 |
| Haiku 4.5 | $0.00009 | $0.00097 |
Grade A, and why
produck-feedback 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 13d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building from Produck feedback
Purpose: Turn real, in-context user feedback into shipped fixes. This skill drives the Produck MCP — it tells the agent how to find the right feedback, load the full context behind it, and convert that context into an aligned change instead of a guess.
Requires the Produck MCP server connected. If
search_feedback/get_feedbackare not available, seereferences/connect-mcp.mdto connect it and mint a token first.
1. What this connects to
Produck captures feedback in the user's own session, so a ticket is far richer than a text complaint. Each ticket can carry:
- Written and spoken feedback — the user's typed note plus any voice transcription.
- Reconstructed page HTML — a static snapshot of the exact page the user was looking at.
- Annotation markers — the specific elements/regions the user pointed at.
- Session activity — a timeline of what the user did leading up to the feedback.
- A generated design doc — Produck's own first-pass analysis of the issue, when present.
The job of this skill is to pull that context and use all of it, not just the title.
2. The two MCP tools
The server is named produck (tools may appear prefixed, e.g. mcp__produck__search_feedback).
search_feedback — find relevant tickets
Returns lightweight summaries; use it to locate tickets, then load full context with get_feedback.
| Input | Type | Notes |
|---|---|---|
domain |
string, optional | Filter to one website domain. |
limit |
int 1–50, optional | Defaults to 20. |
cursor |
string, optional | Pagination cursor from a previous call. |
Returns { items, nextCursor, count } — each item a summary (id, domain, page URL, created-at,
annotation count, source). Page with cursor until nextCursor is null when you need the full set.
get_feedback — load one ticket in full
| Input | Type | Notes |
|---|---|---|
feedbackId |
string, required | The ticket id (from a search_feedback item, a URL, or the user). |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 81 lines · 90 tokens per session scan A 80706515999a
produck-feedback is a skill published in the GitHub repository tryproduck/produck-skills (511 stars, last pushed 29d ago), licensed Apache-2.0. It adds 90 tokens to every session and 968 once invoked, about $0.0005 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 skills, from other repositories
implement-improvements
Validate improvements from .turbo/improvements.md, recommend a working set tailored to what's in the backlog, and run one lane: direct fixes, investigation, or planned work. One lane per session. Use when the user asks to "implement improvements", "work on improvements", "address improvements", "process improvement…
note-improvement
Capture an out-of-scope improvement opportunity so it doesn't get lost. Use when the user asks to "note improvement", "save improvement", "track this for later", "remember this improvement", "note this idea", "log improvement", "backlog this", or "park this idea". Also invoke proactively when noticing something…
create-issue
Create a GitHub issue with a drafted title and body. Use when the user asks to "create an issue", "file an issue", "open an issue", "submit an issue", "report a bug", "file a bug report", "file a feature request", or "file a design proposal".
pick-next-issue
Fetch and rank open GitHub issues by community engagement, present the top 3 candidates, and plan implementation for the selected issue. Use when the user asks to "pick next issue", "next issue", "which issue should I work on", "top issues", "most popular issues", "prioritize issues", or "what should I work on next".
split-and-ship
Execute an approved split plan, shipping each change group separately as its own branch and PR or as sequential commits on the current branch. Use when the user asks to "split and ship", "ship the split plan", "create separate PRs", or "split changes into branches".
zero-to-prod-orchestrator
Master orchestrator to build an application from scratch to a production-ready release, enforcing strict step-by-step progression and continuous documentation / Orkestrator utama untuk membangun aplikasi dari nol hingga rilis siap produksi dengan dokumentasi bertahap.