Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add idan-yaron/claude-cowork-skills-toolkit/plugin install skills-toolkitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/idan-yaron/claude-cowork-skills-toolkit/skills-load)<a href="https://agentmods.dev/skills/idan-yaron/claude-cowork-skills-toolkit/skills-load"><img src="https://agentmods.dev/badge/skills/idan-yaron/claude-cowork-skills-toolkit/skills-load/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/idan-yaron/claude-cowork-skills-toolkit/skills-load"><img src="https://agentmods.dev/badge/skills/idan-yaron/claude-cowork-skills-toolkit/skills-load.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00092 | $0.03278 |
| Opus 5 | $0.00046 | $0.01639 |
| Sonnet 5 | $0.00018 | $0.00656 |
| Haiku 4.5 | $0.00009 | $0.00328 |
Grade A, and why
skills-load 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 12d 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 — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Load Skills from GitHub
Fetch a GitHub repo, show its skill catalog, resolve dependencies, and package
selected skills as a single .plugin file that installs into Cowork with one click.
How it works
Cowork's plugin system accepts .plugin files (ZIP archives with a standard
directory layout). When presented via mcp__cowork__present_files, Cowork
renders a rich preview with an "Save plugin" button. Clicking it installs the
entire plugin — all skills appear in the / menu immediately, mid-session.
This is better than installing skills individually because:
- One click installs everything (not N clicks for N skills)
- Dependencies stay bundled together as a coherent package
- The plugin can be shared as a single file
Skills are also injected into the conversation for immediate use, even before the user clicks Save plugin.
VM constraints
- Bash runs in an isolated Linux VM — use for cloning repos and building ZIPs.
- Write tool bridges to the HOST filesystem.
- Host paths like
~/AppData/...don't exist inside the VM.
Step 1: Parse the URL
Extract the GitHub URL from $ARGUMENTS. Handle these formats:
https://github.com/owner/repohttps://github.com/owner/repo/tree/branchhttps://github.com/owner/repo/tree/branch/path/to/subdirgithub.com/owner/repo(no protocol)[email protected]:owner/repo.git(SSH)
Extract owner and repo from the URL — you'll use repo as the default
plugin name (kebab-case, lowercase). If no valid URL, ask the user.
Sanitize the repo name: only a-z, 0-9, and hyphens. Strip anything else.
Step 2: Fetch the repository
FETCH_JSON=$(bash "${CLAUDE_PLUGIN_ROOT}/skills/skills-load/scripts/fetch-repo.sh" "<github-url>" "<branch-if-any>")
fetch-repo.sh outputs JSON with four fields: path, branch, subpath, sha.
Parse them all — path is needed for skill discovery, the other three are carried
through to the plugin manifest as source provenance so /skills-update can later
refresh against the SAME branch and do fast-path SHA comparisons.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 344 lines · 92 tokens per session scan A a4743da06596
skills-load is a skill published in the GitHub repository idan-yaron/claude-cowork-skills-toolkit (5 stars, last pushed 5mo ago), licensed MIT. It adds 92 tokens to every session and 3,278 once invoked, about $0.0005 per session on Opus 5. 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 2026-08-31.
Other skills, from other repositories
session-status
Analyzes current session state without any cleanup. Full mode (default): resolves the active plan file, reads plan checklist + TaskList, gathers unfinished work/issues from conversation history, and emits a /handoff-built next-session prompt. Mid-session mode (/session-status mid): a fast plain-language 'done vs…
wrap-up
End-of-session handler that first checks whether the current session's plan is actually complete. If complete: run a quick retrospective, emit a forward-looking follow-up prompt, and — in a git repository — refresh the repo and clean gone branches. If incomplete: skip cleanup and emit ready-to-paste resume prompts so…
finalize-pr
Automatically finalize pull requests for merge by resolving CodeQL violations, review threads, merge conflicts, and CI failures. Handles single PR (current branch or by number), all open PRs in the repo, or all open PRs across the org. Includes bot-authored PRs in all modes.
gh-cli-patterns
Canonical reference for all gh CLI command shapes used by skills in this plugin. Defines the placeholder convention, default-branch (trunk vs git-flow) detection, allowed --json fields, GraphQL fallback rules, -f/-F/--raw-field flag semantics, the PR-readiness gate, code-scanning alert query, review-thread…
ship
Commit, push, create PR(s), and auto-finalize — full automation pipeline. Handles uncommitted changes and recently created PRs.
dell-idrac-bmc-ops
Bring a Dell PowerEdge BMC (iDRAC) onto the network headlessly, standardize its baseline settings, stage its firmware, and drive an unattended Proxmox/Linux install through it — including generation-specific Redfish/racadm gotchas, the identity-before-power-action rule, and the phantom-drive failure mode caused by…