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 varunk130/ai-customer-discovery-skills --skill feedback-prioritizergit clone --depth 1 https://github.com/varunk130/ai-customer-discovery-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/varunk130/ai-customer-discovery-skills/feedback-prioritizer)<a href="https://agentmods.dev/skills/varunk130/ai-customer-discovery-skills/feedback-prioritizer"><img src="https://agentmods.dev/badge/skills/varunk130/ai-customer-discovery-skills/feedback-prioritizer/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/varunk130/ai-customer-discovery-skills/feedback-prioritizer"><img src="https://agentmods.dev/badge/skills/varunk130/ai-customer-discovery-skills/feedback-prioritizer.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 | $0.00082 | $0.01004 |
| Opus 5 | $0.00041 | $0.00502 |
| Sonnet 5 | $0.00016 | $0.00201 |
| Haiku 4.5 | $0.00008 | $0.00100 |
Grade A, and why
feedback-prioritizer 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 12d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feedback Prioritizer
Convert a stack of customer feedback (tickets, interview notes, NPS comments, sales loss reasons) into a small ranked list of opportunities, with explicit reasoning for what not to act on. The single most important section of the output is "Do Not Act" - vocal-minority signals that look compelling but would distract the roadmap.
Core Principle
Most feedback is noise; the prioritizer's job is to find the signal and name the noise. A ranked list without a "Do Not Act" section silently licenses the team to chase the loudest voices.
Scoring Model: RSCF
Each candidate opportunity is scored 1-5 on four dimensions:
| Letter | Dimension | Question |
|---|---|---|
| R | Reach | What share of paying customers will benefit? |
| S | Severity | When the problem hits, how badly does it hurt? |
| C | Strategic fit | Does this align with the current strategy or pull us off-mission? |
| F | Confidence | How certain are we, given evidence quality and quantity? |
Score = R × S × C × F / 25 (normalized to 0-25). Confidence acts as a multiplier that crushes weakly-evidenced items.
Output
Save to outputs/feedback-priority-[period]-[YYYY-MM-DD].md
| Section | Description |
|---|---|
| Top 5 Opportunities | Ranked by RSCF, with evidence count and source breakdown |
| Watch List | Promising but evidence-light items (Confidence ≤ 2) - gather more data |
| Do Not Act | Vocal-minority signals with explicit reasoning for de-prioritization |
| Patterns Across Sources | Themes that appeared in 3+ independent channels (highest-trust signal) |
| Counterfactual Check | "If we only did the top-1 item, would the next quarter look meaningfully better?" |
Process
Step 1: Intake
I'll ask:
"Share the feedback corpus (paste, file, or sample). Tell me the time window, source mix (tickets / interviews / NPS / sales / churn), and your current strategy in one sentence."
Step 2: Cluster
Group raw items into themes. Items that repeat across different sources weight more than the same item repeated 50× from one source.
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.
- 12d ago First seen · 78 lines · 82 tokens per session scan A b5ae6463e5f6
feedback-prioritizer is a skill published in the GitHub repository varunk130/ai-customer-discovery-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 1,004 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
Subpoena Triage
Use when an incoming subpoena has been received to produce a structured triage summary identifying the compliance deadline, scope, objections, privilege issues, preservation obligations, and internal notification requirements for immediate attorney review.
profile-builder
Produces discovery-context.md — the single source of truth that every other skill in this pack reads. Without it, other skills will warn and offer to bootstrap inline (a 2–3 question mini-interview held in conversation, not written to disk). Running this skill first gives the best, most consistent results.
solution-architecture
Produces a discovery-grade architecture: enough detail to estimate effort, surface technical risks, and explain choices to the client — but not detailed design. Detailed design happens in delivery, not here. Where the BA isn't a tech lead, this skill is best run pair-mode with an architect; otherwise it produces vague…
insight-synthesis
Turns whatever evidence the BA managed to gather into structured insights — weighted by source quality so the team doesn't treat one SME's hunch as equal to five user interviews.
user-interviews
Direct user interviews. Run only when useraccess allows it.
discovery-handoff
When discovery ends and delivery begins — possibly with a different team. This document is the bridge. Reading it cold should be enough to start delivery work.