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 yaojingang/GEOHub --skill geo-diagnosegit clone --depth 1 https://github.com/yaojingang/GEOHubWrote 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/yaojingang/geohub/geo-diagnose)<a href="https://agentmods.dev/skills/yaojingang/geohub/geo-diagnose"><img src="https://agentmods.dev/badge/skills/yaojingang/geohub/geo-diagnose/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/yaojingang/geohub/geo-diagnose"><img src="https://agentmods.dev/badge/skills/yaojingang/geohub/geo-diagnose.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 | $0.00075 | $0.00363 |
| Opus 5.5 | $0.00030 | $0.00145 |
| Sonnet 5.5 | $0.00015 | $0.00073 |
| Haiku 4.5 | $0.00007 | $0.00036 |
Grade A, and why
geo-diagnose 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/interface.yaml 1.7 KB
- evals/output/cases.jsonl 2.1 KB
- evals/semantic_config.json 361 B
- evals/trigger_cases.json 413 B
- manifest.json 1.3 KB
- references/audit-catalog.md 1.1 KB
- references/diagnosis-method.md 4.7 KB
- references/input-example.json 577 B
- reports/output_quality_scorecard.md 414 B
- reports/skill-ir.json 2.6 KB
- reports/trust-report.md 372 B
- scripts/run_diagnose.py 424 B runs code
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 · 23 lines · 75 tokens per session scan A 3f1e575131a3
geo-diagnose is a skill published in the GitHub repository yaojingang/GEOHub (170 stars, last pushed 2mo ago), licensed AGPL-3.0. It adds 75 tokens to every session and 363 once invoked, about $0.0003 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 2026-08-30.
geo-diagnose compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| geo-diagnoseyaojingang/GEOHub | Skill | 170 | 2mo ago | AGPL-3.0 | A | 75 | Claude Code, Codex |
| seo-content-blogThibaultbm/claude-seo-geo | Skill | 18 | yesterday | MIT | A | 235 | Claude Code |
| seo-content-collection-pageThibaultbm/claude-seo-geo | Skill | 18 | yesterday | MIT | A | 214 | Claude Code |
| seo-content-product-pageThibaultbm/claude-seo-geo | Skill | 18 | yesterday | MIT | A | 220 | Claude Code |
| seo-content-service-pageThibaultbm/claude-seo-geo | Skill | 18 | yesterday | MIT | A | 228 | Claude Code |
| seo-localThibaultbm/claude-seo-geo | Skill | 18 | yesterday | MIT | A | 211 | Claude Code |
| seo-content-comparison-pageThibaultbm/claude-seo-geo | Skill | 18 | yesterday | MIT | A | 214 | Claude Code |