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 unparkgit 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/unpark)<a href="https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/unpark"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/unpark/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/unpark"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/unpark.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 | $0.00010 | $0.00943 |
| Opus 5.5 | $0.00004 | $0.00377 |
| Sonnet 5.5 | $0.00002 | $0.00189 |
| Haiku 4.5 | $0.00001 | $0.00094 |
Grade A, and why
unpark 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unpark
Resume work from a parked handoff document, or read a wrapped close-out record as reference.
Process
1. Find Handoff
Check parking locations in order:
- Project
CLAUDE.md->## Handoffsor## Parking->Location: - User
~/.claude/CLAUDE.md-> same lookup - Default:
.parkinglot/in project root
If multiple files exist, group them by mode and list:
Active handoffs:
(A) jwt-authentication.md - Parked 2026-05-06
(B) fix-login-bug.md - Parked 2026-05-04
Wrapped (reference only):
(C) sanitation-skill-fix-wrapped.md - Wrapped 2026-03-30
(D) confirm-dotfiles-work-role-wrapped.md - Wrapped 2026-04-12
(E) Other location
Detect group by filename suffix (-wrapped.md) and the file's first heading (Parked: vs Wrapped:). Filename and heading should agree; if they disagree, trust the heading and note the mismatch.
2. Branch on Mode
After the user picks a file, read it and check the first heading.
# Parked:-> continue with Continuation Flow below# Wrapped:-> switch to Reference Flow below
Continuation Flow
2a. Read and Present
Read the handoff and present a summary:
Resuming: [Topic]
Parked: [Date]
Branch: [branch]
Current state: [Brief summary]
Next steps:
1. [Step 1]
2. [Step 2]
2b. Validate
Check that the handoff is still valid:
- Git branch matches (or can be checked out)
- Worktree exists (if specified)
- Key files still exist
- Decisions still seem relevant
2c. Handle Validation Results
If valid:
Validation passed. Ready to continue with: [first next step]
Proceed?
(A) Yes, continue
(B) Review the full handoff first
(C) Adjust the plan
If stale or invalid:
Validation found issues:
- [Issue 1]
- [Issue 2]
Options:
(A) Update handoff and try again - I'll revise based on current state
(B) Start fresh - discard this handoff
(C) Continue anyway - I understand the context has changed
If option A: update the handoff file with current findings, then recommend unparking again.
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 · 136 lines · 10 tokens per session scan A ae9814f89155
unpark is a skill published in the GitHub repository technicalpickles/pickled-claude-plugins (12 stars, last pushed 7d ago), licensed MIT. It adds 10 tokens to every session and 943 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
doc-bootstrapping
A project-documentation setup guide that creates a central set of rules, memory notes, and Diátaxis documentation folders. Diátaxis is a method that separates explanations, specifications, how-to guides, and tutorials.
suggest-automations
Offer the three most common automations for a user as a single-choice card, from your own knowledge of their team and their apps, then build the one they choose once they confirm, or offer more. The system preloads it on onboarding threads, where the opening card already asked the user about themselves. Use it on…
scenario-zbrush-expert
Use when an agent drives Maxon ZBrush 2026 for any task (sculpt in ZBrush, DynaMesh, ZRemesher, UVs, export, polypaint, posing, 3D print, clean up an AI mesh in ZBrush), when writing ZBrush Python (zbrush.commands) or ZScript, when the ZBrush bridge is not answering, a palette path or set() does nothing, a scripted…
company-brain
Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so an agent can answer on your team's behalf. Team-scope sibling to second-brain — personal notes go there, not here. Modes — capture, compile (wiki pages + INDEX.md), query (trust-weighted, saved to outputs/)…
slide-deck
When you want to draft, update, convert, or export a slide deck for a React/Next.js slide system (${SLIDEDECKREPO:-$HOME/code/your-slide-deck-site}/src/app/slides/). Writes TypeScript Slide[] arrays using your primitives (Eyebrow, Heading, Accent, Body, BulletList, Divider, TwoCol, GradientText), 12 cycling brand…
session-cleanup
Identify stale and empty Claude Code sessions in the Agent Monitor and explain the cleanup endpoint (POST /api/settings/cleanup), always showing the exact list of what WOULD be removed before anything is deleted. Cleanup permanently deletes data, so this skill previews first and requires explicit user confirmation.…