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.
git clone --depth 1 https://github.com/HelloRuru/claude-memory-engineWrote 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/helloruru/claude-memory-engine/recover)<a href="https://agentmods.dev/commands/helloruru/claude-memory-engine/recover"><img src="https://agentmods.dev/badge/commands/helloruru/claude-memory-engine/recover/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/commands/helloruru/claude-memory-engine/recover"><img src="https://agentmods.dev/badge/commands/helloruru/claude-memory-engine/recover.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 | $0.00000 | $0.00417 |
| Opus 5.5 | $0.00000 | $0.00167 |
| Sonnet 5.5 | $0.00000 | $0.00083 |
| Haiku 4.5 | $0.00000 | $0.00042 |
Grade A, and why
recover 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.
What it actually says
/recover -- Disaster Recovery + Cross-Device Sync
Restore memory from your GitHub backup when local memory files are lost or corrupted. Also works for cross-device sync.
Prerequisites
You need a GitHub repo set up as your memory backup (the one you push to with /backup or /sync). If you haven't created a backup repo yet, this command won't work.
Cross-Device Sync (v1.6)
bash ~/.claude/scripts/hooks/memory-backup.sh pull
The pull mode does two things:
git pullfrom GitHub to get the latest- Distribute
repo/memory/*.mdinto every local project directory that has amemory/folder (newer file wins, won't overwrite local changes)
This solves the "Device A pushed but Device B can't see it" problem -- each device has different working directories, so projects/ paths differ. Global memory must be actively distributed.
When to Use
- Switched to a new computer and need to bring over memories from another device
- Local memory files were accidentally deleted
- SessionStart hook isn't working
- Memory files appear corrupted or empty
- Another device pushed new memory and you want to pick it up (for routine use,
/syncis more convenient)
Steps
- Protect current state -- Run
/backupfirst to push any remaining local changes - Pull from GitHub --
bash ~/.claude/scripts/hooks/memory-backup.sh pull - Verify -- Read MEMORY.md, scan all index entries
- Report -- "Recovered! Found {N} index entries, {M} memory files"
Notes
- Under normal conditions, SessionStart hook auto-loads the last session summary + recent memory changes. You should NOT need this command regularly
- This is the "break glass" option for when the automated system fails
- Always push before pulling to avoid overwriting local changes
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 · 41 lines · 0 tokens per session scan A 3c1909ab3961
recover is a command published in the GitHub repository HelloRuru/claude-memory-engine (134 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 417 tokens. 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 2026-08-30.
Other commands, from other repositories
context-stats
Display context window usage and token statistics.
sync
Session bootstrap - read project context, restore saved state, show status. Quick orientation with optional deep dive.
handoff
Write a session handoff document for continuity.
checkpoint
Write a new link in the continuum chain summarizing decisions/changes since the last link.
dream
Roll up the last N links into a single phase-digest link; originals move to archived/ (never deleted).
hades-show-proposals
Show pending Asphodel memory update proposals.