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/unpark)<a href="https://agentmods.dev/skills/emaballarin/ccplugins/unpark"><img src="https://agentmods.dev/badge/skills/emaballarin/ccplugins/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/emaballarin/ccplugins/unpark"><img src="https://agentmods.dev/badge/skills/emaballarin/ccplugins/unpark.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 | $0.00040 | $0.01025 |
| Opus 5.5 | $0.00016 | $0.00410 |
| Sonnet 5.5 | $0.00008 | $0.00205 |
| Haiku 4.5 | $0.00004 | $0.00103 |
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 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mf:unpark — project → scratchpad, after a reboot
Restores the snapshots /mf:park left in <project root>/.mf/park/, verifies every entry, then pops each one: its manifest is copied into the scratchpad as PARKED-<session-id>.md and the snapshot is deleted. --keep in the arguments retains the snapshots; --beside restores, beside them, the parked versions of entries the target already holds differently (step 3).
Steps
1. Find the snapshots and this session
- Project root:
git rev-parse --show-toplevel, else the working directory. Snapshots are the directories<root>/.mf/park/*/, each named by the session id it came from; itsMANIFEST.mdgives the source path, the date and the counts. A directory named<id>.partialis a park that was killed midway: report it, and restore nothing from it. With no snapshot, say so and stop. - This session: the scratchpad your system prompt names, and
$CLAUDE_CODE_SESSION_ID.
Done when each snapshot is listed with its session id, parked date and file count.
2. Choose what goes where
- This session's snapshot (resumed: the ids match) goes into this scratchpad. Its manifest's
from:should be this same path; if it is not, say so, restore here anyway, and give the old → new path. - Another session's snapshot comes in only on the person's word: a snapshot taken into this session is no longer where its own session will look when resumed. List them and ask which, if any, to bring in. One goes into this scratchpad; several go into subdirectories of it named by their session ids.
- The rest stay parked. Name them: each comes back by resuming its own session and running
/mf:unparkthere.
Done when every snapshot has a destination or is named as staying parked.
3. Restore, verify, pop
For each snapshot being restored:
bash "${CLAUDE_PLUGIN_ROOT}/scripts/unpark.sh" "<root>/.mf/park/<session-id>" "<target>" [--keep] [--beside]
The script checks the snapshot against its own records, then puts each entry in place under a temporary name, renames it and compares it, so an interrupted restore never leaves a partial file under a real name. It never overwrites: an entry already at the target that differs from the snapshot, or one reached through a symlinked directory, is listed as FAILED with the reason and left as it is. Its exit status:
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 · 51 lines · 40 tokens per session scan A b3c99704f223
unpark is a skill published in the GitHub repository emaballarin/ccplugins (4 stars, last pushed 7d ago), licensed MIT. It adds 40 tokens to every session and 1,025 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…