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 aakashg/pm-github-workflow-repo --skill feedback-synthesizergit clone --depth 1 https://github.com/aakashg/pm-github-workflow-repoWrote 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/aakashg/pm-github-workflow-repo/feedback-synthesizer)<a href="https://agentmods.dev/skills/aakashg/pm-github-workflow-repo/feedback-synthesizer"><img src="https://agentmods.dev/badge/skills/aakashg/pm-github-workflow-repo/feedback-synthesizer/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/aakashg/pm-github-workflow-repo/feedback-synthesizer"><img src="https://agentmods.dev/badge/skills/aakashg/pm-github-workflow-repo/feedback-synthesizer.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 | $0.00048 | $0.00653 |
| Opus 5 | $0.00024 | $0.00327 |
| Sonnet 5 | $0.00010 | $0.00131 |
| Haiku 4.5 | $0.00005 | $0.00065 |
Grade A, and why
feedback-synthesizer 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 9d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feedback Synthesizer
Analyze provided user feedback and produce a structured synthesis. Works with interviews, surveys, support tickets, NPS responses, app reviews, or any combination.
Process
- Read all provided sources.
- Extract observations: direct quotes, pain points, feature requests, workarounds, positive signals.
- Group into themes by frequency and severity.
- Rank by signal strength (sources x severity x consistency).
Output Format
## Feedback Synthesis
**Date:** [today]
**Sources:** [list type and count]
**Observations extracted:** [count]
### Top Themes (ranked by signal strength)
#### Theme 1: [3-5 word name]
- **Signal:** [X] / [total] mentioned - severity: [low/medium/high/critical]
- **Summary:** [2-3 sentences]
- **Quotes:**
- "[exact quote]" - [source identifier]
- "[exact quote]" - [source identifier]
- **Implication:** [one sentence]
### What to Build
[Features supported by 2+ high-signal themes. Confidence level for each.]
### What NOT to Build
[Low-signal requests. Why each is a non-goal right now.]
### Open Questions
[What needs validation. Specific next steps.]
### Quote Bank
[Up to 15-20 strongest quotes by theme, copy-paste ready for PRDs. Fewer is fine for small inputs - never pad or invent to hit a count.]
Good vs Bad Output
GOOD: "Onboarding friction - 6/8 sources, high severity. 'I gave up at the API-key step.' - Ticket #4412." BAD: "Several users found onboarding confusing." (no count, no severity, no verbatim quote, no source)
Edge Cases
Fewer than 5 sources: Flag low confidence. Recommend 5+ more before decisions. Contradictory feedback: Report the split. "Power users (4/8) want more automation, new users (3/8) find existing automation confusing." Pre-PMF (before product-market fit): Focus on problem validation, not feature requests. "7/8 described the problem. Signal is real."
Rules
- Never invent quotes. Every quote must come verbatim from sources.
- Count honestly. 1/8 is "1/8," not "several."
- Save with this exact dated filename:
feedback-synthesis-[YYYY-MM-DD].md(anywhere in the repo - the ignore rule keys off the date in the name, not the folder). - Saved that way, the file is git-ignored by default; drop the date and it is NOT protected. It holds verbatim customer quotes / PII (personally identifiable information). To version a sanitized copy, use
git add -f <file>.
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.
- 9d ago First seen · 64 lines · 48 tokens per session scan A a2b79d2b2368
feedback-synthesizer is a skill published in the GitHub repository aakashg/pm-github-workflow-repo (3 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 653 once invoked, about $0.0002 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
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…