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 Rifteo/skills --skill cvss-scorergit clone --depth 1 https://github.com/Rifteo/skillsWrote 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/rifteo/skills/cvss-scorer)<a href="https://agentmods.dev/skills/rifteo/skills/cvss-scorer"><img src="https://agentmods.dev/badge/skills/rifteo/skills/cvss-scorer/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/rifteo/skills/cvss-scorer"><img src="https://agentmods.dev/badge/skills/rifteo/skills/cvss-scorer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00096 | $0.02304 |
| Opus 5.5 | $0.00038 | $0.00922 |
| Sonnet 5.5 | $0.00019 | $0.00461 |
| Haiku 4.5 | $0.00010 | $0.00230 |
Grade A, and why
cvss-scorer 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CVSS Scorer
Produce an exact CVSS v3.1 vector and score from a vulnerability description. Be decisive. Be accurate. Be short.
When NOT to use
Do NOT produce a CVSS vector — respond normally — when:
- The user is asking what CVSS is or how it works (answer the theory question directly)
- The user wants a full risk assessment beyond CVSS — likelihood, business impact, SLAs (use
risk-assessorinstead) - The user is asking how to fix a vulnerability (use
remediation-plannerinstead) - No specific vulnerability has been described — a score requires a concrete finding, not a hypothetical
Core Behavior
- Infer aggressively from context. Most metrics can be determined from a good description. Do it.
- Pick the best score when you have enough. Do not flood with scenarios for every metric. Only surface ambiguity when it would change the severity bucket (e.g. Medium vs High) or meaningfully changes the score (≥1.0 difference).
- Ask once, ask sharp. If you need clarification, ask one short question, show 2–3 short conditional scores, then stop.
- No metric-by-metric explanations. Only explain a metric if it's non-obvious or the auditor asks. Never explain what AV, AC, PR, etc. mean unless asked.
- No formula display. The auditor does not need to see the math.
- Do not assume AV:N by default. Infer it. If the description says nothing about how the vuln is reached, ask — or state the assumption explicitly in one word.
Metric Inference
Attack Vector (AV)
- Web app, API, internet/intranet-reachable → N
- Same LAN / WiFi / Bluetooth required → A
- Local OS session required → L
- Physical device access required → P
- If not mentioned and not obvious → state "assumed AV:N (web app)" and flag it
Attack Complexity (AC)
- IDOR with numeric/sequential ID → L
- IDOR with UUID/GUID → H
- Race condition → H
- MitM required → H
- Everything else standard → L
Privileges Required (PR)
- Pre-auth / unauthenticated → N
- Any valid account → L
- Admin / elevated → H
- If unclear → ask (this is the most common ambiguity and always matters)
What ships with it
1 file 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.
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 · 167 lines · 96 tokens per session scan A f34b3c503fcd
cvss-scorer is a skill published in the GitHub repository Rifteo/skills (38 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 2,304 once invoked, about $0.0004 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.
cvss-scorer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cvss-scorerRifteo/skills | Skill | 38 | 1mo ago | MIT | A | 96 | Claude Code, Codex |
| pcbwayaklofas/kicad-happy | Skill | 1.6k | 3d ago | MIT | A | 119 | Claude Code |
| remotion-best-practicesguanyang/open-agent-hub | Skill | 994 | yesterday | MIT | A | 116 | Claude Code |
| asc-subscription-localizationrorkai/app-store-connect-cli-skills | Skill | 1.1k | 5d ago | MIT | A | 60 | Claude Code |
| happiness-skillkangarooking/cangjie-skill | Skill | 13k | 1mo ago | MIT | A | 136 | Claude Code, Codex |
| influence-psychologywondelai/skills | Skill | 2.7k | 9d ago | MIT | A | 156 | Claude Code |
| jobs-to-be-donewondelai/skills | Skill | 2.7k | 9d ago | MIT | A | 137 | Claude Code |