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/doctorgit 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 | $0.02444 |
| Opus 5 | $0.00000 | $0.01222 |
| Sonnet 5 | $0.00000 | $0.00489 |
| Haiku 4.5 | $0.00000 | $0.00244 |
Grade C, and why
doctor scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
brew upgrade skillshare OR curl -fsSL .../install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
brew upgrade skillshare OR curl -fsSL .../install.sh | sh How it starts
The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
doctor
Check environment and diagnose issues with your skillshare setup.
skillshare doctor
skillshare doctor -p # Project mode (.skillshare/config.yaml)
skillshare doctor -g # Force global mode
skillshare doctor --json # Structured JSON output for CI
When to Use
- Something isn't working and you don't know why
- After upgrading skillshare or your OS
- Verify all targets, git, and symlinks are healthy
- First diagnostic step before filing a bug report
What It Checks
skillshare doctor
Checking environment
✓ Config: ~/.config/skillshare/config.yaml
→ Config directory: ~/.config/skillshare
→ Data directory: ~/.local/share/skillshare
→ State directory: ~/.local/state/skillshare
✓ Source: ~/.config/skillshare/skills (12 skills)
✓ Agents source: ~/.config/skillshare/agents (8 agents)
✓ Skillignore: 2 patterns, 1 skills ignored
✓ Link support: OK
✓ Git: initialized with remote
✓ Skill integrity: 12/12 verified
Checking targets
claude
skills [merge] merged (8 shared, 2 local)
agents [merge] merged (8/8 linked)
cursor
skills [copy] copied (8 managed, 0 local)
agents [merge] merged (8/8 linked)
codex
skills [merge] needs sync
Extras
✓ rules: 4 files, 1/1 targets OK
✓ commands: 3 files, 1/1 targets OK
Version
✓ CLI: 0.17.0
✓ Skill: 0.17.0
Summary
✓ All checks passed!
Checks Performed
Environment
| Check | What It Verifies |
|---|---|
| Config | Config file exists and is valid |
| Source | Source directory exists and is readable |
| Agents source | Agents source directory exists (if configured) |
| Skillignore | .skillignore (and .skillignore.local) active patterns and ignored skill count |
| Link support | System can create symlinks |
| Git | Repository status and remote configuration |
Targets
Each target shows sub-items for skills and agents (when agents are configured):
- Skills: path, sync mode, sync state, shared/local counts
- Agents: linked count, drift detection
- No broken symlinks
- Duplicate-skill checks for unintended local collisions:
mergemode: skipped (local skills are expected)copymode: manifest-managed copies are ignored; only local colliding copies are warned
- Valid include/exclude glob patterns
- Info-level per-target compatibility hint when applicable (example target priority:
cursor→antigravity→copilot→opencode; no hint when these targets are absent)
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 · 302 lines · 0 tokens per session scan C 53c6d0c434d3
doctor is a command published in the GitHub repository runkids/skillshare (2,607 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,444 tokens. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). 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.
plan
Break work into small verifiable tasks with acceptance criteria and dependency ordering.
spec
Start spec-driven development — write a structured specification before writing code.
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.