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 commands/runkids/skillshare/hubgit clone --depth 1 https://github.com/runkids/skillshareWhat 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 | $0.00000 | $0.01889 |
| Opus 5 | $0.00000 | $0.00945 |
| Sonnet 5 | $0.00000 | $0.00378 |
| Haiku 4.5 | $0.00000 | $0.00189 |
Grade A, and why
hub 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 2d 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hub
Manage skill hubs — saved hub sources for organization-wide skill discovery.
When to Use
- Set up your organization's skill catalog for
searchto query - Switch between multiple hubs (e.g., company-wide vs team-specific)
- List or remove saved hub sources
hub add
Save a hub source to config for reuse in search --hub.
skillshare hub add <url> [options]
| Flag | Description |
|---|---|
--label, -l |
Custom label (default: derived from URL hostname) |
--project, -p |
Save to project config |
--global, -g |
Save to global config |
The first hub added is automatically set as the default. Labels are case-insensitive.
A hub URL can be an HTTP(S) URL, a local file path, or an SSH URL — scp-style (git@host:org/repo.git) or scheme-style (ssh://git@host/org/repo.git). For SSH sources the index file is read from the repo via the //path suffix, defaulting to skillshare-hub.json at the repo root. SSH sources are cloned using your SSH agent/keys, which works for private and GitHub Enterprise hosts.
When an SSH hub contains same-host GitHub or GitHub Enterprise domain-prefixed entries, Skillshare installs them through the hub's SSH identity. For example, a hub added as [email protected]:Org/skills.git//hubs/team.json can contain acme.ghe.com/Org/skills/skills/reviewer, and search results install it as [email protected]:Org/skills.git//skills/reviewer. Outside an SSH hub, domain-prefixed sources still mean HTTPS.
skillshare hub add https://internal.corp/hub.json --label team
skillshare hub add ./local-hub.json # label derived: "local-hub"
skillshare hub add [email protected]:team/skills.git --label ghe
skillshare hub add [email protected]:team/skills.git//hubs/team.json --label ghe-team
hub list
List saved hubs. * marks the default hub.
skillshare hub list [options]
| Flag | Description |
|---|---|
--project, -p |
Show project hubs |
--global, -g |
Show global hubs |
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.
- 2d ago First seen · 236 lines · 0 tokens per session scan A f76423106a86
hub is a command published in the GitHub repository runkids/skillshare (2,597 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,889 tokens. 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 commands, from other repositories
constraints
Define and enforce this project's quality bar — interview, sane defaults, CONSTRAINTS.md.
webperf
Run a web performance audit via the web-performance-auditor persona.
spec
Start spec-driven development — write a structured specification before writing code.
plan
Break work into small verifiable tasks with acceptance criteria and dependency ordering.
pm-arch
Scan project structure and generate Mermaid architecture diagrams + flowcharts under .pm/architecture/.
pm-done
Close a todo (TODO-xxx), sync completed.md, refresh overview.