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/initgit 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 | $0.02130 |
| Opus 5 | $0.00000 | $0.01065 |
| Sonnet 5 | $0.00000 | $0.00426 |
| Haiku 4.5 | $0.00000 | $0.00213 |
Grade A, and why
init 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
init
First-time setup. Auto-detects installed AI CLIs and configures targets.
skillshare init # Interactive setup
skillshare init --dry-run # Preview without changes
When to Use
- First time setting up skillshare on a machine
- Migrating to a new computer (with
--remoteto connect to existing repo) - Adding skillshare to a project (with
--project) - Discovering newly installed AI CLIs (with
--discover)
What Happens
flowchart TD
TITLE["skillshare init"]
S0["0. Source path prompt"]
S1["1. Create source + agents directories"]
S2["2. Auto-detect AI CLIs"]
S3["3. Initialize git"]
S4["4. Set up remote"]
S4b["5. Subdirectory prompt"]
S5["6. Create config.yaml"]
S6["7. Built-in skill"]
TITLE --> S0 --> S1 --> S2 --> S3 --> S4 --> S4b --> S5 --> S6
init creates the skills source directory and an agents/ sibling directory in one step, so both resource kinds are ready to use immediately. The agents directory is silent — no extra prompts or flags. See Agents for the agent file format.
:::info Universal target
When any AI CLI is detected, init automatically recommends the universal target (~/.agents/skills). This is the shared directory used by vercel-labs/skills (npx skills list) to provide skills to all compatible agents at once.
:::
:::tip Agents source path
The agents source defaults to <source parent>/agents (so ~/.config/skillshare/agents/ for the default install). Set agents_source: in config.yaml to override the location. Project mode always uses .skillshare/agents/ and does not honor agents_source. Agent-capable targets (Claude, Cursor, Augment, OpenCode) pick agents up automatically once you run skillshare sync.
:::
Project Mode
Initialize project-level skills with -p:
skillshare init -p # Interactive
skillshare init -p --targets claude,cursor # Non-interactive
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 · 229 lines · 0 tokens per session scan A 95e6139217ea
init 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 2,130 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.
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.
pm-charter
Create, import, discover, approve, or skip project charter. No-arg form is an interactive wizard.