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 vinhnx/VTCode --skill skill-installergit clone --depth 1 https://github.com/vinhnx/VTCodeWrote 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/vinhnx/vtcode/skill-installer)<a href="https://agentmods.dev/skills/vinhnx/vtcode/skill-installer"><img src="https://agentmods.dev/badge/skills/vinhnx/vtcode/skill-installer/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/vinhnx/vtcode/skill-installer"><img src="https://agentmods.dev/badge/skills/vinhnx/vtcode/skill-installer.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 | $0.00052 | $0.00664 |
| Opus 5.5 | $0.00021 | $0.00266 |
| Sonnet 5.5 | $0.00010 | $0.00133 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
skill-installer 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 13d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Installer
Helps install skills. By default these are from https://github.com/openai/skills/tree/main/skills/.curated, but users can also provide other locations.
Use the helper scripts based on the task:
- List curated skills when the user asks what is available, or if the user uses this skill without specifying what to do.
- Install from the curated list when the user provides a skill name.
- Install from another repo when the user provides a GitHub repo/path (including private repos).
Install skills with the helper scripts.
Communication
- Start by confirming the task and running the appropriate command.
- If something fails, report the exact error and ask what to do next.
- Say only what is necessary.
Scripts
List Curated Skills
Show available skills from the curated list:
scripts/list-curated-skills.py
Optional: specify a different repo or path:
scripts/list-curated-skills.py --repo owner/repo --path skills/path --ref branch
Output formats:
- Default: numbered list with installation status
- JSON:
--format jsonfor programmatic use
Install from Curated List
Install a skill by name from the curated list:
scripts/install-skill-from-github.py <skill-name>
The skill will be installed to ~/.agents/skills/<skill-name>/.
Install from Any GitHub Repo
Install skills from any GitHub repository:
scripts/install-skill-from-github.py owner/repo path/to/skill
For private repos, ensure gh CLI is authenticated or GITHUB_TOKEN is set.
Install multiple skills from the same repo:
scripts/install-skill-from-github.py owner/repo path/to/skill1 path/to/skill2
Behavior and Options
Installation Location
Skills are installed to ~/.agents/skills/ by default.
Private Repositories
For private repositories:
- Ensure GitHub CLI (
gh) is installed and authenticated:gh auth login - Or set the
GITHUB_TOKENenvironment variable
Overwriting Existing Skills
What ships with it
2 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.
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.
- 13d ago Changed · +2 lines ee7322408541
- 1mo ago First seen · 108 lines · 52 tokens per session scan A 0df7ec102c32
skill-installer is a skill published in the GitHub repository vinhnx/VTCode (880 stars, last pushed today), licensed Apache-2.0. It adds 52 tokens to every session and 664 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 2026-08-30.
Other skills, from other repositories
unifly
Inspect and manage UniFi Network infrastructure with the unifly CLI: devices, clients, VLANs, WiFi, firewall, VPN, switch ports, site settings, and cloud fleets. Use for UniFi network configuration, monitoring, and troubleshooting, not UniFi Protect camera or recording management.
verify
Drive an engine app headlessly in a pty, record a video of the whole verification, and open a summary page (video + timeline + checks) with pixel open.
unifly
Inspect and manage UniFi Network infrastructure with the unifly CLI: devices, clients, VLANs, WiFi, firewall, VPN, switch ports, site settings, and cloud fleets. Use for UniFi network configuration, monitoring, and troubleshooting, not UniFi Protect camera or recording management.
rust-doctor
Use when Rust code just changed and must not regress, when the user asks to scan, audit or health-check a Cargo workspace, says "rust-doctor", or wants one of its findings explained, tuned or switched off.
monitor-fleet
A dashboard that puts claude-monitor pages from multiple machines into one switchable page. claude-monitor shows activity on one machine, while this tool connects to other machines through SSH tunnels.
jdi-handoff
Hand the current interactive Claude/Codex session off to an unattended agent-jdi background run — it quits this session and resumes it autonomously so the human can walk away. Trigger when the user says "hand this off to jdi", "justdoit", "let jdi finish this", "hand off to agent-jdi", "take it from here unattended"…