Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Hivemind-OSS/Hivemindnpx agentmods add skills/hivemind-oss/hivemind/hive-backup-restoreWrote 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/hivemind-oss/hivemind/hive-backup-restore)<a href="https://agentmods.dev/skills/hivemind-oss/hivemind/hive-backup-restore"><img src="https://agentmods.dev/badge/skills/hivemind-oss/hivemind/hive-backup-restore/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/hivemind-oss/hivemind/hive-backup-restore"><img src="https://agentmods.dev/badge/skills/hivemind-oss/hivemind/hive-backup-restore.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 | $0.00080 | $0.00801 |
| Opus 5 | $0.00040 | $0.00400 |
| Sonnet 5 | $0.00016 | $0.00160 |
| Haiku 4.5 | $0.00008 | $0.00080 |
Grade A, and why
hive-backup-restore scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hive-backup-restore — snapshot, reset & restore the store
The data lives in the hive-data Docker volume (in-container path /data/shared.db). Full
reference: HIVE-ADMIN.md §1 & §5.
CLI resolve (once per shell): command -v hive >/dev/null 2>&1 || hive() { python3 -m hive.tools.cli "$@"; }
— makes every hive … line below run on an uninstalled checkout (the CLI is stdlib-only;
Windows shells: py -m hive.tools.cli <verb>; prerequisites: hive-bringup).
hive backup — safe snapshot
hive backup # snapshots the warm store NOW; prints the snapshot path
Manual (no scheduler) — run it on whatever cadence you like. Keeps the
HIVE_RETENTION__BACKUP_KEEP (default 30) most-recent snapshots in HIVE_RETENTION__BACKUP_DIR
(default <db_dir>/backups, inside the volume). For a copy that survives the volume being
destroyed, use reset's host snapshot (below) or copy a snapshot out.
hive reset — recoverable clean-start (DESTRUCTIVE)
hive reset # asks you to type 'reset' to confirm
hive reset --out ./snaps # choose the host snapshot dir (default ./hive-backups)
hive reset --yes # skip the prompt (scripted dev only)
In order: (1) snapshots the store out to the host — a pure file-level copy that works even when
the daemon can't boot against an incompatible store; (2) aborts before any destruction if that
snapshot fails (fail-safe — an accidental reset costs a restart, not the memory); (3) only then
down -v + recreate the volume empty + warm. It prints the host snapshot path and the exact
hive restore … line to roll back.
Primary use: recovering from a schema-generation crash-loop (hive up failing after a rebuild —
see hive-bringup). Also a deliberate clean slate. Prefer this over a bare
docker compose down -v, which destroys the store with no snapshot.
hive restore <snapshot.db> — roll back (DESTRUCTIVE, inverse of reset)
hive restore ./hive-backups/hive-<stamp>.db # asks you to type 'restore' to confirm
hive restore <snap> --yes # skip the prompt
Stops the daemon (releases the WAL locks), overwrites the live store with the snapshot (clearing
stale WAL sidecars), then rebuilds + restarts. Works with either a reset-produced host snapshot or
a hive backup snapshot. After it returns, recall reflects the snapshot's contents — re-check the
KPIs (hive-operate).
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.
- 9d ago First seen · 59 lines · 80 tokens per session scan A 08edd2451e2a
hive-backup-restore is a skill published in the GitHub repository Hivemind-OSS/Hivemind (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 80 tokens to every session and 801 once invoked, about $0.0004 per session on Opus 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
mssql-query
Query the stack's SQL Server (mssql-express) from the sandbox: probe, databases, tables, schema, sample rows, read-only SQL, and opt-in DML/DDL. Connection string comes from GADBCONNECTIONSTRING in the Guide's Environment variables. Use when the user wants to inspect or query the GuideAnts database.
db-schema
Apply when designing database schemas, writing migrations, or reviewing table structure. Covers naming, keys, indexes, constraints, nullability, and migration safety.
github-code-review
Comprehensive GitHub code review with AI-powered swarm coordination.
github-multi-repo
Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration.
Pair Programming
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…
Skill Builder
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.