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 marcelopaniza/mempenny/plugin install mempennyWrote 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/commands/marcelopaniza/mempenny/restore)<a href="https://agentmods.dev/commands/marcelopaniza/mempenny/restore"><img src="https://agentmods.dev/badge/commands/marcelopaniza/mempenny/restore.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.05307 |
| Opus 5 | $0.00017 | $0.02653 |
| Sonnet 5 | $0.00007 | $0.01061 |
| Haiku 4.5 | $0.00003 | $0.00531 |
Grade B, and why
restore scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
**Trust bound:** the MANIFEST file itself is co-located with the backup. An attacker with full write access to the backup dir can modify both the manifest and the files and keep them consistent. The integrity check defen How it starts
The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Restore a previously-taken memory backup. Safe by default: always takes a timestamped snapshot of the current memory dir before overwriting, so a bad restore is itself reversible.
Step 1 — Parse arguments
The user invoked this command with: $ARGUMENTS
- Positional arg — a specific backup name (e.g.,
memory.backup-20260417143052) OR the literal wordlatest. If omitted, we'll list backups and prompt the user interactively. --dir <path>— absolute path to the memory directory to restore INTO. If not set, auto-detect the current project's memory dir (same logic as/mempenny:clean).--lang <code>— output language. Defaults toMEMPENNY_LOCALEoren.
Step 2 — Load locale strings
2a — Validate <lang> before reading (H2: path traversal guard)
Before constructing the locale path, validate that <lang> matches the regex ^[a-zA-Z]{2,3}(-[A-Za-z0-9]{2,8})?$. If it does not match, treat it exactly like a missing locale: silently reset <lang> to en and warn with errors.locale_missing.
Read ${CLAUDE_PLUGIN_ROOT}/locales/<lang>/strings.json. Fall back to en if the file is missing (warn with errors.locale_missing). You need restore.* and errors.* keys.
Step 3 — Locate the target memory directory
If --dir <path> was passed, apply the following validation before using it. On any failure, print errors.memory_dir_not_found and STOP:
Validate --dir <path> (C-class shell-injection guard):
- Regex: the candidate path must match
^/[A-Za-z0-9/_.\ -]{1,4096}$(alphanumerics, slash, underscore, dot, hyphen, space only). - Realpath: run
realpath "<candidate>"via Bash. Use the resolved value for all subsequent steps. - Depth: reject if the realpath equals
/or has fewer than 2 path components. - Existence + not-a-symlink:
[ -d "$resolved" ] && [ ! -L "$resolved" ]. (It's OK if the directory does not exist yet — restore will create it. Skip check 4 if the path does not exist, but still apply checks 1–3.)
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 · 310 lines · 0 tokens per session scan B 7ed3747d7981
restore is a command published in the GitHub repository marcelopaniza/mempenny (2 stars, last pushed 17d ago), licensed MIT. It adds 34 tokens to every session and 5,307 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
instinct-import
Import instincts from external sources.
learn
Extract patterns and learnings from current session.
mempalace-init
Set up MemPalace — install the package, initialize a palace, register the MCP server with Cursor, and verify everything works.
mempalace-status
Show the current state of your memory palace — wings, rooms, drawer counts, and suggestions.
ingest
Ingest source material into an active wiki. Accepts URLs, file paths, PDFs, freeform text, or processes the inbox. Supports tweets via Grok MCP.
design-import
Scaffolds React components from a Claude Design handoff bundle and stops at files on disk: no stories, no tests, no pull request. Use when handed a claude.ai/design URL or a local bundle file; when that same scaffold should carry on through test generation, browser verification and an opened PR, run /ork:design-ship…