Commands for copying locally created or edited skills and agents from a target directory back to Skillshare's source collection. Skillshare is a tool for sharing these coding-assistant resources across tools.

Use it to collect skills or agents from a selected target, collect from all targets, preview the operation, or copy resources while excluding Git metadata.

It prevents useful changes made in a target folder from remaining disconnected from the source used for sharing, syncing, or version control.

collect — Command by runkids

Install

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.

agentmods

npx agentmods add commands/runkids/skillshare/collect

Clone the repo

git clone --depth 1 https://github.com/runkids/skillshare

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 883 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What 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	$0.00883
Opus 5	$0.00000	$0.00441
Sonnet 5	$0.00000	$0.00177
Haiku 4.5	$0.00000	$0.00088

Measured yesterday against content hash 1d1902418209, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

collect 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 yesterday.

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.

website/docs/reference/commands/collect.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

collect

Collect local skills or agents from targets back to source.

skillshare collect claude           # From specific target
skillshare collect --all            # From all targets
skillshare collect claude --dry-run # Preview
skillshare collect agents claude    # Collect agents instead of skills

When to Use

Use collect when you've created or edited resources directly in a target directory and want to pull them back into the source of truth:

Add them to your source for sharing
Sync them to other AI CLIs
Back them up with git

Examples:

Skills: ~/.claude/skills/my-skill/
Agents: ~/.claude/agents/tutor.md

What Happens

flowchart TD
    CMD["skillshare collect claude"]
    FIND["1. Find local items in target"]
    CONFIRM["2. Confirm collection"]
    COPY["3. Copy to source"]
    CMD --> FIND --> CONFIRM --> COPY

:::tip .git/ directories are automatically excluded during collection. If you've git-cloned a skill repo directly into a target directory, only the skill content is copied — repository metadata stays behind. :::

:::note The web dashboard's Collect page is currently skills-only. Use the CLI for collect agents. :::

Options

Flag	Description
`--all, -a`	Collect from all targets
`--force, -f`	Overwrite existing items in source and skip confirmation
`--dry-run, -n`	Preview without making changes
`--json`	Output JSON and skip confirmation; existing items in source still require `--force` to overwrite

JSON Output

skillshare collect claude --json

{
  "pulled": ["new-skill", "another-skill"],
  "skipped": [],
  "failed": {},
  "dry_run": false,
  "duration": "0.123s"
}

Combine with --dry-run to preview without changes:

skillshare collect claude --json --dry-run
skillshare collect -p --json
skillshare collect -p agents --json

Example Output

$ skillshare collect claude

Local skills found
  ℹ new-skill       [claude] ~/.claude/skills/new-skill
  ℹ another-skill   [claude] ~/.claude/skills/another-skill

Collect these skills to source? [y/N]: y

Collecting skills
  ✓ new-skill: copied to source
  ✓ another-skill: copied to source

Run 'skillshare sync' to distribute to all targets

Read the full file on GitHub · 148 lines

Changes

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.

yesterday First seen · 148 lines · 0 tokens per session scan A 1d1902418209

Subscribe to this mod's changes

collect 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 883 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.

Git and workflow Writing and docs ai cli codex cursor skills team-management

collect

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

collect

When to Use

What Happens

Options

JSON Output

Example Output

What this file has done since we first saw it

Other commands, from other repositories

constraints

webperf

spec

plan

pm-arch

pm-done