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/fmflurry/settings-opencodeWrote 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/fmflurry/settings-opencode/db-backup-check)<a href="https://agentmods.dev/commands/fmflurry/settings-opencode/db-backup-check"><img src="https://agentmods.dev/badge/commands/fmflurry/settings-opencode/db-backup-check/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/fmflurry/settings-opencode/db-backup-check"><img src="https://agentmods.dev/badge/commands/fmflurry/settings-opencode/db-backup-check.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 | $0.00029 | $0.00512 |
| Opus 5.5 | $0.00012 | $0.00205 |
| Sonnet 5.5 | $0.00006 | $0.00102 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
db-backup-check 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 27d 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
DB Backup Check Command
Delegate to the postgres-dba agent to audit this repository's PostgreSQL backup/restore posture (gc-platform-postgres, postgres:16-alpine).
Task
Load the postgres-backup-restore skill and audit:
- Archiving configured?
SHOW archive_mode/archive_command/archive_timeout/wal_level - Archiver healthy?
pg_stat_archiver—failed_count,last_failed_time(failures →pg_walfills → PANIC shutdown) - Last successful dump? check
./backups/(or ask the user where dumps live); verify readability withpg_restore -l; confirm globals (roles) coverage - Volume persistence?
docker volume inspect postgres-data— data must sit on the named volume at/var/lib/postgresql/data - PITR possible today? base backup + WAL archive present, or not (PG16 has NO native incremental backups)
Produce a gap report (CRITICAL → HIGH → MEDIUM → LOW) and advisory setup commands — archiving enablement, pg_dump/pg_basebackup recipes, PITR recovery steps — each as a ⚠️ HUMAN CONFIRMATION REQUIRED block. Compose changes are recommended as handoffs to coder via the conductor. Nothing is executed.
Scope
- If
$ARGUMENTSis provided (e.g.,/db-backup-check pitr): audit that focus area (archiving, pitr, dumps, or volume) - If
$ARGUMENTSis empty: audit the full backup posture
$ARGUMENTS
Output Format
Return the structured report per the postgres-dba agent specification:
- Severity tiers: CRITICAL → HIGH → MEDIUM → LOW
- Evidence: exact query/command + observed values per finding
- Remediation: human-confirmation blocks for all backup/restore/config commands;
coderbriefs for compose changes - Restore drill: state whether a drill is recorded and due (checklist in the skill)
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.
- 27d ago First seen · 38 lines · 29 tokens per session scan A 342dc0122ad4
db-backup-check is a command published in the GitHub repository fmflurry/settings-opencode (171 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 512 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 2026-09-20.
Other commands, from other repositories
trex.db.setup
Start a fresh PostgreSQL container and run all migrations. If a database already exists, this will tear it down first.
psql-query
Run ad-hoc PostgreSQL analytics queries against dev/test database.
db
Set up or operate Supabase Postgres for this project.
splunk-observability-database-monitoring-setup
Render and validate Splunk Observability Cloud Database Monitoring collector configuration for MongoDB, PostgreSQL, Microsoft SQL Server, MySQL, MariaDB, and Oracle through the Splunk OTel Collector. Keeps secrets out of chat, argv, and rendered files; DB credentials are referenced through Kubernetes Secrets or local…
pg-indexes
Review unused indexes that are safe to drop (pgbot).
rls-plan
Supabase RLS + access-control audit + remediation plan — no SQL until approved.