skills-save

skills-save is a skill for Claude Code from idan-yaron/claude-cowork-skills-toolkit. It costs 104 tokens per session (3,326 once invoked), scanned A, original, MIT.

A skill for packaging the skills loaded in the current conversation into a new plugin file. It preserves changes made to those skills during the conversation.

In plain words
What is it for?
Use it after loading or refining skills when you want a reusable plugin snapshot that can be installed later.
Why use it?
It prevents useful in-conversation skill edits or loaded skills from being lost.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the skills-toolkit plugin — 5 skills shipped together

Good fit Use it after loading or refining skills when you want a reusable plugin snapshot that can be installed later.

Compare 6 skills from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add idan-yaron/claude-cowork-skills-toolkit
Claude Code
/plugin install skills-toolkit

Made for: Claude Code.

Or install skills-toolkit, the plugin that ships this one along with the rest of its 5 skills.

Wrote 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.

agentmods badge for skills-save

README.md
[![agentmods](https://agentmods.dev/badge/skills/idan-yaron/claude-cowork-skills-toolkit/skills-save/github.svg)](https://agentmods.dev/skills/idan-yaron/claude-cowork-skills-toolkit/skills-save)
Your own site
<a href="https://agentmods.dev/skills/idan-yaron/claude-cowork-skills-toolkit/skills-save"><img src="https://agentmods.dev/badge/skills/idan-yaron/claude-cowork-skills-toolkit/skills-save/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.

agentmods 80×15 button for skills-save

Your own site · 80×15
<a href="https://agentmods.dev/skills/idan-yaron/claude-cowork-skills-toolkit/skills-save"><img src="https://agentmods.dev/badge/skills/idan-yaron/claude-cowork-skills-toolkit/skills-save.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,326 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00104 $0.03326
Opus 5 $0.00052 $0.01663
Sonnet 5 $0.00021 $0.00665
Haiku 4.5 $0.00010 $0.00333

Measured 12d ago against content hash a28f5b4d5959, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

skills-save 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/discover-installed-plugins.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/skills-save/SKILL.md · 337 lines

How it starts

The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Save Loaded Skills as a New Plugin

Package the skills loaded in THIS conversation as a fresh .plugin file — either the iterated versions (if you modified them), or the originals (if you loaded but never clicked Save plugin). The saved plugin reflects the current in-context state.

This saves what /skills-load brought in. To fetch skills from GitHub, use /skills-load. To refresh installed plugins from their GitHub sources, use /skills-update. To package already-installed skills for sharing, use /skills-share.

When to use this

  • You ran /skills-load <github-url> and iterated one or more skills — save the iterated versions
  • You ran /skills-load <github-url> but never clicked Save plugin — save it now so you can install with one click
  • You want a named snapshot of the current in-context skill state

How it works

Skills loaded via /skills-load are injected into the conversation as ### LOADED SKILL: {name} blocks. This skill gathers skills from two sources unconditionally — (A) conversation markers, which preserve any iterations, and (B) already-installed skills-toolkit plugins on disk — then cross-references them to pick the right action: save iterations, install a load that was never saved, save originals post-compaction, or report nothing to do. The result is packaged as a .plugin file presented for install via Cowork's "Save plugin" button.

Step 1: Discover loaded skills (two sources)

Skills can come from two sources. Gather from BOTH, then decide which to use.

Source A: Conversation markers (primary — captures iterations)

Find all ### LOADED SKILL: {name} markers in this conversation. For each marker, extract:

  • The skill name (from the header)
  • The description (from the **Description:** line)
  • The body content (everything until the next --- separator or next ### LOADED SKILL: block)

This source preserves any iterations you made during the conversation. It's the happy path when conversation context is intact.

Read the full file on GitHub · 337 lines

Files

What ships with it

1 file 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.

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.

  1. 12d ago First seen · 337 lines · 104 tokens per session scan A a28f5b4d5959

Subscribe to this mod's changes

skills-save is a skill published in the GitHub repository idan-yaron/claude-cowork-skills-toolkit (5 stars, last pushed 5mo ago), licensed MIT. It adds 104 tokens to every session and 3,326 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.

Related

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…

dryvist/claude-code-plugins · 102 tokens

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…

dryvist/claude-code-plugins · 96 tokens

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…

dryvist/claude-code-plugins · 94 tokens

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.

dryvist/claude-code-plugins · 63 tokens

ship

Commit, push, create PR(s), and auto-finalize — full automation pipeline. Handles uncommitted changes and recently created PRs.

dryvist/claude-code-plugins · 30 tokens

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…

dryvist/claude-code-plugins · 111 tokens