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 agentmods add commands/seite-sh/seite/research-performancegit clone --depth 1 https://github.com/seite-sh/seiteWrote 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/commands/seite-sh/seite/research-performance)<a href="https://agentmods.dev/commands/seite-sh/seite/research-performance"><img src="https://agentmods.dev/badge/commands/seite-sh/seite/research-performance.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00469 |
| Opus 5 | $0.00000 | $0.00234 |
| Sonnet 5 | $0.00000 | $0.00094 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
research-performance 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 4d 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.
This is a copy
100% identical to research-performance — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Performance Command
Categorize all content by traffic and rankings to prioritize optimization.
Usage
/research-performance
What This Command Does
Analyzes ALL your blog content and categorizes into 4 performance quadrants:
- ⭐ Stars - High traffic + Good rankings → Maintain & expand
- 🚀 Overperformers - High traffic + Poor rankings → Learn why, improve SEO
- ⚠️ Underperformers - Low traffic + Good rankings → Fix CTR (title/meta)
- 📉 Declining - Low traffic + Poor rankings → Refresh or redirect
For each piece:
- Traffic trends (rising/stable/declining)
- Expected vs actual traffic
- Specific action recommendations
- Priority level
Process
Execute the performance matrix analysis:
python3 research_performance_matrix.py
This will:
- Fetch all pages from GA4 (last 90 days)
- Filter to content pages only
- Enrich with GSC ranking data
- Calculate traffic trends (180-day comparison)
- Categorize into performance quadrants
- Generate report:
research/performance-matrix-YYYY-MM-DD.md
Output
The report includes:
- Distribution across 4 quadrants
- Top performers in each category
- Specific action steps per article
- Expected traffic calculations
- Priority recommendations
Key Insights
Stars: Your best content - keep fresh, expand with clusters Underperformers: QUICK WINS - rewrite titles/meta for better CTR Declining: Content losing traction - needs refresh or redirect Overperformers: Getting traffic despite poor rankings - improve SEO
Integration
After running /research-performance:
- Use
/analyze-existing [URL]for detailed content analysis - Fix underperformer titles/meta first (low effort, high impact)
- Refresh declining stars to prevent traffic loss
Time & Requirements
Time: 2-4 minutes Requirements: GA4 required, GSC recommended Cost: Free
When to Run
- Monthly: Monitor content health
- After major updates: Track impact
- When traffic drops: Identify declining content
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.
- 4d ago First seen · 72 lines · 0 tokens per session scan A 49cdb9cc8faf
research-performance is a command published in the GitHub repository seite-sh/seite (20 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 469 tokens. A static security scan graded it A with 0 findings. It is 100% identical to research-performance, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
init
Scaffold a new MindBase project (v2 layout). Usage: /mb:init [template] [-- mission ...].
commit
智能生成 Git 提交信息并提交.
pr
Handle the full workflow from current branch state to an open, CI-monitored pull request.
doctor.es
Diagnostica problemas de inferencia LLM en Mac: asiai doctor verifica el estado de los motores, conflictos de puertos, carga de modelos y estado de la GPU.
claude-request
Send a prompt to Claude Code via the LLM gateway with session tracking.