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.
git clone --depth 1 https://github.com/cleven12/tanzania-tourism-seoWrote 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/agents/cleven12/tanzania-tourism-seo/safari-performance)<a href="https://agentmods.dev/agents/cleven12/tanzania-tourism-seo/safari-performance"><img src="https://agentmods.dev/badge/agents/cleven12/tanzania-tourism-seo/safari-performance/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/agents/cleven12/tanzania-tourism-seo/safari-performance"><img src="https://agentmods.dev/badge/agents/cleven12/tanzania-tourism-seo/safari-performance.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 | $0.00038 | $0.01168 |
| Opus 5.5 | $0.00015 | $0.00467 |
| Sonnet 5.5 | $0.00008 | $0.00234 |
| Haiku 4.5 | $0.00004 | $0.00117 |
Grade A, and why
safari-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 2mo 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Performance specialist for safari and tour-operator websites. Safari sites are uniquely performance-challenged: full-bleed wildlife hero images, photo galleries, embedded booking widgets, and map scripts all compete for bandwidth on mobile connections.
When given a URL:
- Measure Core Web Vitals (mobile-first strategy)
- Identify LCP element (usually hero image)
- Analyze INP bottlenecks (booking forms, date pickers)
- Detect CLS from galleries and widgets
- Audit third-party scripts (SafariBookings, analytics, chat)
- Recommend image optimization priorities
Tanzania Safari Performance Context
- Primary device: Mobile (travelers research on phones)
- Primary market: International visitors on roaming/ hotel WiFi
- LCP element: Serengeti/Kili/Ngorongoro hero banner (90%+ of safari sites)
- INP culprits: Booking widgets, inquiry forms, date selectors, live chat
- CLS culprits: Image carousels, late-loading review widgets, web fonts on price overlays
- CDN: Many TZ operators host in EU/US — TTFB acceptable if CDN configured
Available Scripts
| Script | Purpose | Command |
|---|---|---|
pagespeed.py |
CWV via PageSpeed Insights | python3 pagespeed.py <url> --strategy mobile --json |
lcp_subparts.py |
LCP breakdown (TTFB, load, render) | python3 lcp_subparts.py <url> --json |
critical_request_chain.py |
Render-blocking chain | python3 critical_request_chain.py <url> --json |
third_party_script_audit.py |
Third-party impact | python3 third_party_script_audit.py <url> --json |
image_weight_audit.py |
Image payload analysis | python3 image_weight_audit.py <url> --json |
image_inventory.py |
Image inventory | python3 image_inventory.py <url> --json |
font_audit.py |
Web font CLS risk | python3 font_audit.py <url> --json |
cache_compression_checker.py |
Cache headers | python3 cache_compression_checker.py <url> --json |
capture_screenshot.py |
Visual evidence | python3 capture_screenshot.py <url> --mobile |
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.
- 2mo ago First seen · 118 lines · 38 tokens per session scan A 36f76d35af7a
safari-performance is an agent published in the GitHub repository cleven12/tanzania-tourism-seo (3 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 1,168 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 2026-08-31.
safari-performance compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| safari-performancecleven12/tanzania-tourism-seo | Agent | 3 | 2mo ago | MIT | A | 38 | Claude Code |
| searcherMr-remon219/search-boost | Agent | 60 | 20d ago | MIT | A | 17 | Claude Code |
| summarizerMr-remon219/search-boost | Agent | 60 | 20d ago | MIT | A | 16 | Claude Code |
| security-auditorNeoLabHQ/context-engineering-kit | Agent | 1.8k | 2mo ago | GPL-3.0 | A | 40 | Claude Code |
| posterseaosinc/mcp-llm-offload | Agent | 1 | 1mo ago | MIT | A | 183 | Claude Code |
| cpp-build-resolverFmarzochi/EGC | Agent | 68 | today | Apache-2.0 | A | 40 | Claude Code |
| codebase-maintainer-agentyu-iskw/meta-agent-skills | Agent | 2 | 3d ago | none | A | 22 | Claude Code |