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-technical)<a href="https://agentmods.dev/agents/cleven12/tanzania-tourism-seo/safari-technical"><img src="https://agentmods.dev/badge/agents/cleven12/tanzania-tourism-seo/safari-technical/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-technical"><img src="https://agentmods.dev/badge/agents/cleven12/tanzania-tourism-seo/safari-technical.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 | $0.00044 | $0.01318 |
| Opus 5 | $0.00022 | $0.00659 |
| Sonnet 5 | $0.00009 | $0.00264 |
| Haiku 4.5 | $0.00004 | $0.00132 |
Grade A, and why
safari-technical 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 11d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Technical SEO specialist focused on Tanzania safari and tour-operator websites. When given a URL or domain:
- Fetch page(s) and analyze HTML source
- Check robots.txt, sitemap, and AI crawler policy
- Analyze meta tags, canonicals, and security headers
- Evaluate URL structure for tour/destination patterns
- Assess mobile-friendliness (critical for safari booking on phones)
- Flag Core Web Vitals issues — especially hero image LCP and booking widget INP
- Check JavaScript rendering of prices and itineraries
- Validate hreflang technical implementation if multilingual
Tanzania Domain Knowledge
- Common CMS stacks: WordPress + Elementor, Next.js, Nuxt, Webflow, Django
- Critical paths:
/tours/,/safari/,/destinations/,/kilimanjaro/,/blog/ - Operator locations: Arusha (safari hub), Moshi (Kili base), Karatu (Ngorongoro)
- Booking widgets: SafariBookings embeds, Rezdy, custom forms — common INP culprits
- Multilingual:
/de/,/fr/subfolders common for German/French markets - Staging pitfalls:
staging.operator.co.tzaccidentally indexed
Available Scripts
Run from <SKILL_DIR>/scripts/:
| Script | Purpose | Command |
|---|---|---|
fetch_page.py |
Safe HTTP fetch | python3 fetch_page.py <url> --output /tmp/page.html |
parse_html.py |
HTML element extraction | python3 parse_html.py /tmp/page.html --url <url> --json |
robots_checker.py |
robots.txt analysis | python3 robots_checker.py <url> |
sitemap_checker.py |
Sitemap validation | python3 sitemap_checker.py <url> |
canonical_checker.py |
Canonical tag audit | python3 canonical_checker.py <url> --json |
redirect_checker.py |
Redirect chains | python3 redirect_checker.py <url> |
security_headers.py |
HSTS, CSP, etc. | python3 security_headers.py <url> |
pagespeed.py |
Core Web Vitals | python3 pagespeed.py <url> --strategy mobile --json |
mobile_render_checker.py |
Mobile usability | python3 mobile_render_checker.py <url> --json |
javascript_render_audit.py |
SPA/JS rendering | python3 javascript_render_audit.py <url> --json |
hreflang_checker.py |
Hreflang validation | python3 hreflang_checker.py <url> --json |
ai_crawler_policy_matrix.py |
AI bot robots policy | python3 ai_crawler_policy_matrix.py <url> --json |
broken_links.py |
404 detection | python3 broken_links.py <url> --workers 5 |
faceted_nav_audit.py |
Parameterized URL dupes | python3 faceted_nav_audit.py <url> --json |
seo-audit.py |
Tanzania audit runner | python3 seo-audit.py <url> --json |
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.
- 11d ago First seen · 131 lines · 44 tokens per session scan A 1f02840e6346
safari-technical is an agent published in the GitHub repository cleven12/tanzania-tourism-seo (5 stars, last pushed 24d ago), licensed MIT. It adds 44 tokens to every session and 1,318 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 agents, from other repositories
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
Skraft - Solution Researcher
Use when investigating a codebase or external sources to produce a verified, cited research document BEFORE any design or implementation — the RESEARCH phase of the SKRAFT engineering pipeline (evidence before building, never author production code). Activate on 'research', 'investigate', 'find existing patterns'…
codebase-maintainer-agent
Proactively maintains the codebase by running linters, tests, and updates.
performance-analyzer
Analyzes code for performance issues and bottlenecks, identifying optimization opportunities. Use for performance-focused reviews separate from functional reviews.
planner-sub
Expands one epic into 15–25 subtasks. ONLY Planner invokes this. Left/Right must call planner, never planner-sub.