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 skills/nvidia/skillspector/safe_skillnpx skills add NVIDIA/SkillSpector --skill safe_skillgit clone --depth 1 https://github.com/NVIDIA/SkillSpectorWhat 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 | $0.00013 | $0.00121 |
| Opus 5 | $0.00006 | $0.00060 |
| Sonnet 5 | $0.00003 | $0.00024 |
| Haiku 4.5 | $0.00001 | $0.00012 |
Grade A, and why
safe-greeting 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 3d 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.
What it actually says
Greeting Skill
Purpose
This skill provides friendly greetings to users.
Usage
Simply ask the agent to greet you and it will respond with a friendly message.
Examples
- "Say hello"
- "Greet me"
- "Good morning"
Responses
The agent will respond with contextually appropriate greetings based on:
- Time of day
- User's name (if known)
- Previous interactions
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.
- 3d ago First seen · 31 lines · 13 tokens per session scan A e2e39dab2c40
safe-greeting is a skill published in the GitHub repository NVIDIA/SkillSpector (15,545 stars, last pushed yesterday), licensed Apache-2.0. It adds 13 tokens to every session and 121 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
add-ave-record
The main workflow for this repo. Adds one new AVE record end to end.
research-new-attack-classes
Keep AVE current with the real threat landscape. This skill researches agentic AI / MCP attack classes from primary sources, benchmarks each against the existing AVE record set, and for every class decides one of three outcomes: ALREADY COVERED, VARIANT OF EXISTING, or NEW CLASS.
tdd
For this repo, TDD means: fixtures first, then rule, then record validation.
setup-ave-skills
Skill "setup-ave-skills" from aveproject/ave, covering setup-ave-skills, install matt pocock's skills and key context.
grill-with-docs
Grill before defining a vulnerability class. No record until complete.
diagnose
Repro: run the rule against the negative fixture in isolation. Minimize: trim the negative fixture to the smallest triggering line. Hypothesize: which pattern/condition is too broad? Fix: tighten the rule. Re-run both fixtures.