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 shawnpang/startup-founder-skills --skill feedback-synthesisgit clone --depth 1 https://github.com/shawnpang/startup-founder-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/shawnpang/startup-founder-skills/feedback-synthesis)<a href="https://agentmods.dev/skills/shawnpang/startup-founder-skills/feedback-synthesis"><img src="https://agentmods.dev/badge/skills/shawnpang/startup-founder-skills/feedback-synthesis/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/shawnpang/startup-founder-skills/feedback-synthesis"><img src="https://agentmods.dev/badge/skills/shawnpang/startup-founder-skills/feedback-synthesis.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 | $0.00028 | $0.01870 |
| Opus 5 | $0.00014 | $0.00935 |
| Sonnet 5 | $0.00006 | $0.00374 |
| Haiku 4.5 | $0.00003 | $0.00187 |
Grade A, and why
feedback-synthesis 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- feedback-synthesis — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feedback Synthesis
When to Use
Activate when a founder or product lead needs to make sense of customer feedback from multiple sources -- support tickets, NPS surveys, user interviews, app store reviews, social media, sales call notes, feature request logs, spreadsheets, or CSVs. This includes prompts like "analyze our customer feedback," "what are users asking for most," "prioritize feature requests," "triage this backlog," or "what themes are showing up in our support tickets."
Context Required
- From startup-context: product type, customer segments, current product roadmap priorities, company stage, strategic goals, and product objectives.
- From the user: the raw feedback data (or access to it), the sources being analyzed, the time period, the product goal or desired outcomes guiding prioritization, and the decision this analysis will inform.
Workflow
- Understand the goal -- Confirm the product objective and desired outcomes that will guide prioritization. Feedback analysis without a strategic lens produces noise, not signal.
- Collect and normalize -- Gather feedback from all sources. If data is in structured formats (CSV, spreadsheet), create summary tables. Each piece of feedback becomes a row with source, date, customer segment, verbatim quote, and sentiment.
- Categorize into themes -- Group related requests and feedback together. Name each theme. Focus on identifying the underlying opportunity (problem) rather than the surface-level feature request.
- Assess strategic alignment -- For each theme, evaluate how well it aligns with the stated product goals and company strategy.
- Score with Opportunity Score -- Use the Opportunity Score framework (Dan Olsen): Opportunity Score = Importance x (1 - Satisfaction), normalized to 0-1. This prioritizes problems that matter most and are least well-served today.
- Prioritize top opportunities -- Select the top 3 themes based on impact (customer value and breadth of users affected), effort (development and design resources required), risk (technical and market uncertainty), and strategic alignment (fit with product vision).
- Deep-dive top items -- For each top opportunity, document: rationale, alternative solutions worth considering, high-risk assumptions, and how to test those assumptions with minimal effort.
- Present findings -- Deliver a structured synthesis with executive summary first, supporting data second, and recommended actions third.
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 · 123 lines · 28 tokens per session scan A cb2adaeb56d0
feedback-synthesis is a skill published in the GitHub repository shawnpang/startup-founder-skills (321 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 1,870 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…