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 emaballarin/ccplugins/plugin install mfWrote 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/emaballarin/ccplugins/park)<a href="https://agentmods.dev/skills/emaballarin/ccplugins/park"><img src="https://agentmods.dev/badge/skills/emaballarin/ccplugins/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/emaballarin/ccplugins/park"><img src="https://agentmods.dev/badge/skills/emaballarin/ccplugins/park.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 | $0.00047 | $0.01591 |
| Opus 5.5 | $0.00019 | $0.00636 |
| Sonnet 5.5 | $0.00009 | $0.00318 |
| Haiku 4.5 | $0.00005 | $0.00159 |
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 6d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mf:park — scratchpads → project, before a reboot
Session scratchpads live under /tmp, which a reboot usually clears, taking with it every probe, intermediate result and script that would then have to be regenerated. Park copies what is worth keeping into <project root>/.mf/park/<session-id>/, each file checked against its source; /mf:unpark restores it afterwards. all in the arguments skips the triage and parks every file. Empty directories and special files (FIFOs, sockets, devices) are never kept.
Steps
1. Locate the scratchpads
- This session's: the scratchpad directory your system prompt names. Its parent directory's name is the session id, and must equal
$CLAUDE_CODE_SESSION_ID. If the directory is missing or the two disagree, stop and report both: a wrong path parks an empty snapshot that looks fine. - The project's others: the sibling session directories,
<this scratchpad>/../../*/scratchpad, each named by its own session id. Other sessions may still be running; a park copies them as they are now. - Project root:
git rev-parse --show-toplevel, else the working directory.
A scratchpad counts when it holds a file or a symlink. For each, record its session id, path, entry count (find <sp> \( -type f -o -type l \) | wc -l) and bytes (du -sb <sp>).
Done when every scratchpad of the project holding an entry is listed with its counts, or the run stopped with the reason.
2. Triage (skipped under all)
Sort every entry of each scratchpad into keep or drop, with a one-line reason. A directory whose contents share one fate — a cache, a virtualenv — is one row.
- Drop what nothing will need again: regenerable byproducts (
__pycache__/,.pytest_cache/,node_modules/, virtualenvs, build output); empty files; a file whose content now lives elsewhere — committed to the project, written to memory — naming where; a version superseded by a later one nothing still uses; a probe whose answer is already recorded. - Keep everything else, and anything uncertain: a wrong drop costs the work, a wrong keep costs disk.
- Another session's scratchpad: this session lacks the context of why its files exist, so drop only regenerable byproducts there.
- Give the size of any kept entry over 100 MB, so the person can choose to drop it. Name any kept symlink that points outside the scratchpad: it is parked as a link and keeps pointing there, and an absolute one into the old scratchpad dangles once restored into a new session.
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.
- 6d ago First seen · 79 lines · 47 tokens per session scan A bd3f3ca32da9
park is a skill published in the GitHub repository emaballarin/ccplugins (4 stars, last pushed 7d ago), licensed MIT. It adds 47 tokens to every session and 1,591 once invoked, about $0.0002 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 2026-10-10.
Other skills, from other repositories
review-scheduler
(macOS only) Spaced repetition review scheduler for Obsidian. Based on the Ebbinghaus forgetting curve, auto-reminds you to review articles at optimal intervals via macOS launchd + screen unlock detection. Triggers: "/review-scheduler", "set up review reminders", "start review scheduler", "stop review scheduler".
user-profile
Use to create or update the user's anchor profile — a single private file (/bettersense-work-reflections/profile.md) that captures who the user is, what they do, what context other skills need to know about them. Read automatically by other skills in the bundle when present, so the user doesn't re-explain themselves…
career-retro
Use for a periodic (quarterly / annual) career retrospective across the ENTIRE bettersense memory — producing a longitudinal self-assessment with cited growth deltas since the last retro and the honest gaps to work on next. Trigger phrases include "run my career retro", "where am I in my career", "annual…
i-have-adhd
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".
claude-reflect
Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something for future sessions.
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. Modes — capture, compile (wiki pages + INDEX.md), query (trust-weighted, saved to outputs/), review (verify / deprecate / supersede…