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.
npx skills add seungyeop-lee/beads-starter --skill bds-backupgit clone --depth 1 https://github.com/seungyeop-lee/beads-starterWrote 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/seungyeop-lee/beads-starter/bds-backup)<a href="https://agentmods.dev/skills/seungyeop-lee/beads-starter/bds-backup"><img src="https://agentmods.dev/badge/skills/seungyeop-lee/beads-starter/bds-backup/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/seungyeop-lee/beads-starter/bds-backup"><img src="https://agentmods.dev/badge/skills/seungyeop-lee/beads-starter/bds-backup.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 | $0.00026 | $0.00933 |
| Opus 5.5 | $0.00010 | $0.00373 |
| Sonnet 5.5 | $0.00005 | $0.00187 |
| Haiku 4.5 | $0.00003 | $0.00093 |
Grade A, and why
bds-backup 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 2d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Beads Backup
Back up this repository's beads database to a location off this machine, or restore it from such a backup.
On Activation
Decide from the user's request whether this is a backup or a restore. If unclear, ask.
Run read-only checks without asking. Ask for confirmation before commands that change the database, the backup destination, or the machine: show the commands first, then ask.
Facts Under This Preset
These hold for the beads-starter preset (bd init --shared-server ...). Rely on them; do not hedge about them.
bd backupworks in shared-server mode. Auto-backup is off, so a backup happens only whenbd backup syncruns.- A backup covers only the current repository's database, not other projects on the shared server. Back up each repository separately.
- A restore replaces only the current repository's database. Other projects' databases and the shared server itself are untouched.
.beads/is gitignored, so git holds no copy of the issues and nothing records the backup path on another machine. The user must remember the path.bd backup restorewithout a path reads.beads/backup/, not the configured destination. Always pass the path.- Restore always needs
--force, because the database exists as soon asbd inithas run.--forcereplaces the whole database: every change since the backup's last sync is lost. - After a restore, the backup's path is registered as the destination. No
bd backup initis needed afterwards.
Backup
- Run
bd backup status. - If a destination is configured, confirm with the user that it is still the right one. Otherwise ask where to store the backup. It must be a directory that survives losing this machine and sits outside the repository: an external drive or a synced folder (e.g.,
~/Dropbox/beads-backup/<repo>). Never pick the path yourself. Do not use a DoltHub URL:bd backup restorereads only a directory. - If the destination is new or changed, run
bd backup init <path>. - Run
bd backup sync, thenbd backup statusto confirm the sync time. - Tell the user the path and that they must remember it; a restore on a new machine needs it. Remind them that later changes are not backed up until they run
bd backup syncagain.
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.
- 2d ago First seen · 50 lines · 26 tokens per session scan A 9e83ca104f2a
bds-backup is a skill published in the GitHub repository seungyeop-lee/beads-starter (1 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 933 once invoked, about $0.0001 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 2026-10-14.
Other skills, from other repositories
moai-domain-database
Database specialist covering PostgreSQL, MongoDB, Redis, Oracle, and cloud database platforms (Neon, Supabase, Firestore). Use for schema design, query optimization, indexing strategies, data modeling, or cloud database selection. Cloud vendor guide absorbed from moai-platform-database-cloud.
moai-platform-database-cloud
Cloud database platform specialist covering Neon (serverless PostgreSQL), Supabase (PostgreSQL 16 with real-time), and Firebase Firestore (NoSQL with offline sync). Use when choosing or setting up cloud databases.
designing-data-intensive-applications
Apply Martin Kleppmann-inspired data-system rules when designing reliability, scalability, consistency, replication, transactions, streams, or schema evolution.
implementing-domain-driven-design
Apply Vaughn Vernon-inspired implementation DDD rules when building aggregates, domain events, repositories, application services, or context integrations.
patterns-of-enterprise-application-architecture
Apply Martin Fowler-inspired enterprise architecture rules when choosing layers, service layers, transaction scripts, domain models, repositories, mappers, or DTOs.
optimize
Analyze and suggest performance improvements for code, queries, or systems.