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 skills add technicalpickles/pickled-claude-plugins --skill checkoutgit clone --depth 1 https://github.com/technicalpickles/pickled-claude-pluginsWrote 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/technicalpickles/pickled-claude-plugins/checkout)<a href="https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/checkout"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/checkout/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/technicalpickles/pickled-claude-plugins/checkout"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/checkout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00023 | $0.00750 |
| Opus 5.5 | $0.00009 | $0.00300 |
| Sonnet 5.5 | $0.00005 | $0.00150 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
checkout 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 1mo 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Checkout
Overview
Check out a PR, branch, or ref into an isolated worktree with relevant context.
Announce: "Using git:checkout to set up a worktree for {target}..."
When to Use
- User wants to review a PR locally
- User wants to work on a specific branch in isolation
- User provides PR URL/number or branch name
- Following
git:inboxwhen user picks a PR
Input Formats
Accept:
- Full PR URL:
https://github.com/{owner}/{repo}/pull/{number} - Short PR:
{repo}#{number}or#{number}(infer repo from cwd) - PR number only:
{number}(infer owner/repo from git remote) - Branch name:
feature/auth,main, etc. - Ref: commit SHA, tag
Workflow
For PRs
1. Parse PR Reference
# Get owner/repo from current directory if needed
gh repo view --json owner,name -q '"\(.owner.login)/\(.name)"'
2. Fetch PR Details
gh pr view {number} --json title,body,author,state,baseRefName,headRefName,url,reviews,reviewRequests
3. Set Up Worktree
REQUIRED: Use superpowers:using-git-worktrees skill for directory selection.
# Fetch the PR branch
git fetch origin {headRefName}
# Create worktree
git worktree add .worktrees/pr-{number}-{short-desc} origin/{headRefName}
Naming: pr-{number}-{2-3-word-description} (e.g., pr-1234-add-oauth)
4. Present Context
## PR #{number} Ready for Review
**Title:** {title}
**Author:** @{author}
**Branch:** {headRefName} → {baseRefName}
**URL:** {full_url}
### Summary
{1-3 sentence summary from PR body}
### Files Changed ({count})
{Grouped by directory}
### Review Status
{Existing reviews, requested reviewers}
---
**Worktree ready at:** `{full_path}`
For Branches
1. Create Worktree
# For existing branch
git worktree add .worktrees/{branch-slug} {branch}
# For new branch
git worktree add .worktrees/{branch-slug} -b {branch}
2. Report Ready
**Worktree ready at:** `{full_path}`
**Branch:** {branch}
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.
- 1mo ago First seen · 125 lines · 23 tokens per session scan A fe803131ba2b
checkout is a skill published in the GitHub repository technicalpickles/pickled-claude-plugins (12 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 750 once invoked, about $0.0001 per session on Opus 5.5. 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
ecosystem-managing
A codebase maintenance guide covering releases, cleanup, and project handoffs. A release means publishing a new software version; a handoff is documentation that helps another developer take over the project.
git-precommit
A pre-commit workflow that coordinates updates to project memory, documentation, changelogs, roadmaps, architecture notes, and commit messages before code is saved to Git.
release
A release-preparation workflow for software projects. It covers checks before publishing, version-number updates, changelog and documentation updates, and deployment checks.
Worktree Manager
Manage git worktrees for parallel development with conflict prevention and wave-aware execution strategy. Use when creating feature branches, starting parallel work sessions, merging worktree PRs, or coordinating multiple Claude sessions.
commit-message
A guide for writing clear, traceable Git commit messages using the Conventional Commits format, which labels changes such as features, bug fixes, documentation, and refactoring.
datalad
Retrieves, versions, and publishes scientific datasets with DataLad and git-annex, and captures computational provenance with datalad run, rerun, and containers-run. Use when cloning or fetching data from OpenNeuro, DANDI, datasets.datalad.org, or any DataLad dataset; when a file in a dataset reads as a broken symlink…