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/searchgit 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 | $0.02322 |
| Opus 5 | $0.00000 | $0.01161 |
| Sonnet 5 | $0.00000 | $0.00464 |
| Haiku 4.5 | $0.00000 | $0.00232 |
Grade A, and why
search 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 — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
search
Discover and install skills from GitHub repositories.
When to Use
- Discover community skills from hub indexes
- Find skills by name, tag, or description
- Browse available skills before installing
Quick Start
skillshare search vercel # Search by keyword
skillshare search # Browse popular skills
This searches GitHub for repositories containing SKILL.md files that match your query.
Browse Mode
When no query is provided, search browses popular skills on GitHub:
skillshare search # Browse popular skills
skillshare search --list # List popular skills
This uses filename:SKILL.md as the GitHub query and sorts results by star count, showing the most popular skill repositories first.
How It Works
skillshare search [query]
│
▼
GitHub Code Search API (filename:SKILL.md + query)
│
▼
Fetch star counts for each repository
│
▼
Sort by stars (most popular first)
│
▼
Interactive selector → Install selected skill
Preview
Controls:
↑↓— Navigate resultsEnter— Install selected skillCtrl+C— Cancel and exit- Type to filter results
After installing, you can search again or press Enter to quit.
Options
| Flag | Description |
|---|---|
--project, -p |
Install to project-level config (.skillshare/) |
--global, -g |
Install to global config (~/.config/skillshare) |
--hub [URL] |
Search from a hub index (default: skillshare-hub; or custom URL/path) |
--list, -l |
List results only, no install prompt |
--json |
Output as JSON (for scripting) |
--limit N, -n N |
Maximum results (default: 20, max: 100) |
--help, -h |
Show help |
:::tip Auto-detection
If neither --project nor --global is specified, skillshare auto-detects: if .skillshare/config.yaml exists in the current directory, it defaults to project mode; otherwise global mode.
:::
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 · 314 lines · 0 tokens per session scan A 29ebcae14e9c
search 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 2,322 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.