Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add davistroy/claude-marketplace/plugin install personal-pluginWrote 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/davistroy/claude-marketplace/summarize-feedback)<a href="https://agentmods.dev/skills/davistroy/claude-marketplace/summarize-feedback"><img src="https://agentmods.dev/badge/skills/davistroy/claude-marketplace/summarize-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/davistroy/claude-marketplace/summarize-feedback"><img src="https://agentmods.dev/badge/skills/davistroy/claude-marketplace/summarize-feedback.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 | $0.00046 | $0.02799 |
| Opus 5.5 | $0.00018 | $0.01120 |
| Sonnet 5.5 | $0.00009 | $0.00560 |
| Haiku 4.5 | $0.00005 | $0.00280 |
Grade A, and why
summarize-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 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 — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are generating a professional employee feedback assessment document. You will query Notion for feedback entries, synthesize them with Claude, and produce a formatted .docx file. The user may provide arguments: $ARGUMENTS
Input Validation
Required Arguments:
employee_name="..."- Employee name to match against the "Related To" property in Notion (partial matches supported)
Optional Arguments:
days=N- Lookback period in days (default: 365, max: 1095)start_date=YYYY-MM-DD- Override start date (ISO 8601)end_date=YYYY-MM-DD- Override end date (ISO 8601)output_path="..."- Custom output file path (default:./output/Feedback_Summary_{Name}_{datetime}.docx)
If no employee_name is provided, ask the user for it before proceeding.
Prerequisites Check
Before starting, verify all prerequisites:
1. Notion MCP Server
Verify the Notion MCP tools are available (mcp__plugin_Notion_notion__notion-search, mcp__plugin_Notion_notion__notion-fetch). If not connected:
Notion MCP is not connected. Please verify:
1. Notion MCP is configured in your Claude settings
2. The MCP server is running and connected
3. Your Notion API key has access to the Voice Captures database
2. python-docx Package
python -c "import docx; print('python-docx: OK')" 2>/dev/null || echo "python-docx: MISSING"
If missing, ask the user to install: pip install python-docx>=1.0
Step 1: Compute Date Range
Calculate the assessment period:
- If
start_dateandend_dateare provided, use those - Otherwise:
end_date= today,start_date= today minusdaysparameter (default 365)
Display: Assessment period: {start_date} to {end_date}
Step 2: Query Notion for Feedback Entries
Use the Notion MCP tools to search for feedback entries:
- Use
mcp__plugin_Notion_notion__notion-searchto find pages in the Voice Captures database - Filter results where:
- Type property equals "Feedback"
- Related To property contains the
employee_name(case-insensitive partial match) - Date property falls within the computed date range
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 First seen · 329 lines · 46 tokens per session scan A 667ceafdd85d
summarize-feedback is a skill published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 18d ago), licensed MIT. It adds 46 tokens to every session and 2,799 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 2026-09-04.
Other skills, from other repositories
apify-youtube-transcript-scraper
Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
meta-web-to-pdf-briefing
Render a topic into a distributable PDF briefing in three steps: web search → bullet summary → styled PDF. Trigger when the user asks for a PDF briefing on a single topic.
paper-reader
A reading assistant for computer-vision and deep-learning research papers. It can work with PDF files, arXiv papers, and papers stored in Zotero, a reference-management app.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…