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 parkgit 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/park)<a href="https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/park"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/park/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/park"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/park.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 121 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.01973 |
| Opus 5.5 | $0.00004 | $0.00789 |
| Sonnet 5.5 | $0.00002 | $0.00395 |
| Haiku 4.5 | $0.00001 | $0.00197 |
Grade A, and why
park 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Park
Save the current work session. Park has three modes. Pick one, write that shape, do not mix.
Modes
| Mode | Use when | Heading | Filename |
|---|---|---|---|
| Continuation | Bouncing to a new session, work continues | Parked: |
[topic-slug].md |
| Close-out | Work is done, capturing a record before walking away | Wrapped: |
[topic-slug]-wrapped.md |
| Idle checkpoint | Automated park triggered by inactivity/cache-expiry, not a user request | Checkpoint: |
[topic-slug]-checkpoint.md |
Mode Detection
Pick one mode by checking these signals in order. Stop at the first one that resolves.
- Automated trigger. If the invoking prompt explicitly identifies itself as an automated/idle-triggered park (e.g. names a watchdog, cron, or "idle-triggered" rather than a person asking) → idle checkpoint. Skip every other signal below — this must resolve without asking, since automated callers run headless and cannot answer a question.
- Explicit user hint.
- "park, I'm done" / "wrap this up" / "park to close it out" / "park as record" → close-out
- "park, switching sessions" / "park to continue" / "park, picking back up later" → continuation
- Terminal-state inference. If all major next steps are done, no blockers remain, and the current state reads as terminal → close-out. If concrete unfinished next actions exist → continuation.
- Ambiguity fallback. Use the AskUserQuestion tool with one A/B question:
- Question: "Is this a close-out (work is done, archiving) or a continuation (planning to pick this up in a new session)?"
- Options: "Close-out (record)" / "Continuation (handoff)"
Signal 3 requires an interactive caller. Never reach it for a headless/automated invocation — signal 0 must have already resolved those.
Pick once and commit. Do not switch modes mid-write.
Before Writing
- Resolve session ID:
- Preferred: Look for a
Session ID:line in the PostToolUse hook context that this plugin injects whenagent-meta:parkis invoked. Use that value. ATranscript:line may also be present. - Fallback: Run scripts/get-session-id.sh via Bash. If empty, use
unknown.
- Preferred: Look for a
- Gather git branch, worktree path, files touched.
- Resolve output location, in order:
- Project
CLAUDE.md→## Handoffsor## Parking→Location: - User
~/.claude/CLAUDE.md→ same lookup - Default:
.parkinglot/in project root (verify it is gitignored)
- Project
- Check the injected context for a
Park destination:line. This is separate from the CLAUDE.md location above and always optional — it names a command to also send the file to once it's written, e.g. filing it into a second brain vault. Not present unless the user configuredAGENT_PARK_DESTINATIONorAGENT_PARK_DESTINATION_HELPER. Note the template if present; it's used in "After Parking" below.
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.
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 Changed · +2 lines a528e140f64d
- 1mo ago Changed · +56 lines a6aaa9b976f1
- 1mo ago Changed · +13 lines d3f021963cb8
- 1mo ago First seen · 133 lines · 10 tokens per session scan A 940d93dbfd10
park is a skill published in the GitHub repository technicalpickles/pickled-claude-plugins (12 stars, last pushed 6d ago), licensed MIT. It adds 10 tokens to every session and 1,973 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
project-memory
Generate a project-specific context file from a brief so an AI assistant remembers your editorial constraints, voice, audience, and quality bar across sessions.
review-agent-memory
Reviews agent memory and state-store configuration for correctness. Use for "review agent memory", "check state store config" or "audit agent persistence".
session-managing
A set of rules for managing knowledge across an AI session. It describes what to read when a conversation starts and how to record useful decisions, patterns, and lessons afterward.
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when (1) a command, tool, API, or operation fails; (2) the user corrects you or rejects your work; (3) you realize your knowledge is outdated or incorrect; (4) you…
run-memory
Shared step of the marketing playbooks (analyze-performance, run-paid-campaigns, research-competitors, email-lifecycle): reads the last run's record, checks whether its recommendations were done and whether they worked, and saves a short record of this run for the next one. Loaded by those playbooks; not for direct…
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/)…