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/backupgit 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 | $0.01696 |
| Opus 5 | $0.00000 | $0.00848 |
| Sonnet 5 | $0.00000 | $0.00339 |
| Haiku 4.5 | $0.00000 | $0.00170 |
Grade A, and why
backup 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
backup
Create, list, and manage backups of target directories.
skillshare backup # Backup all skill targets
skillshare backup claude # Backup specific target
skillshare backup agents # Backup all agent targets
skillshare backup --all # Backup skills + agents
skillshare backup --list # List all backups
skillshare backup --cleanup # Remove old backups
When to Use
- Create a manual backup before risky changes
- List existing backups to check recovery options
- Clean up old backups to free disk space
Automatic Backups
Backups are created automatically before:
skillshare sync(skill targets and agent targets)skillshare sync agents(agent targets only)skillshare target remove
Location: ~/.local/share/skillshare/backups/<timestamp>/ (global), .skillshare/backups/ (project mode, agents only)
Retention is applied automatically after each automatic backup, using the same policy as --cleanup. You do not need to prune snapshots by hand.
Commands
Create Backup
skillshare backup # All targets
skillshare backup claude # Specific target
skillshare backup --dry-run # Preview
List Backups
skillshare backup --list
All backups (15.3 MB total)
2026-01-20_15-30-00 claude, cursor 4.2 MB ~/.local/share/.../2026-01-20_15-30-00
2026-01-19_10-00-00 claude 2.1 MB ~/.local/share/.../2026-01-19_10-00-00
2026-01-18_09-00-00 claude, cursor 4.0 MB ~/.local/share/.../2026-01-18_09-00-00
Cleanup Old Backups
skillshare backup --cleanup # Remove old backups
skillshare backup --cleanup --dry-run # Preview cleanup
Default cleanup policy:
- Keep last 10 backups
- Remove backups older than 30 days
- Cap total size at 500 MB
The newest snapshot is always kept, even when it alone exceeds the size cap — you are never left without a restore point.
This same policy runs automatically after every sync, so --cleanup is only needed to prune on demand.
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 · 177 lines · 0 tokens per session scan A 1ebd871dbab5
backup 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 1,696 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.