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 antonillos/safeselect --skill safeselect-setupgit clone --depth 1 https://github.com/antonillos/safeselectWrote 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/antonillos/safeselect/safeselect-setup)<a href="https://agentmods.dev/skills/antonillos/safeselect/safeselect-setup"><img src="https://agentmods.dev/badge/skills/antonillos/safeselect/safeselect-setup/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/antonillos/safeselect/safeselect-setup"><img src="https://agentmods.dev/badge/skills/antonillos/safeselect/safeselect-setup.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 | $0.00043 | $0.00451 |
| Opus 5.5 | $0.00017 | $0.00180 |
| Sonnet 5.5 | $0.00009 | $0.00090 |
| Haiku 4.5 | $0.00004 | $0.00045 |
Grade A, and why
safeselect-setup 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 5d 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
SafeSelect setup and recovery
Use SafeSelect MCP tools first, then supported CLI commands. Inspect current configuration before changing it; registration and configuration are writes. Read setup recipes and effects before making changes.
- Resolve the application repository and environment. Never guess among multiple
environments.
config_validateand redactedconfig_showdiagnose config. - If an external bastion, VPN, or tunnel is known unavailable, stop and ask the
user to restore it manually. Do not call
check,connectorreconnect, or try shell SSH/VPN commands; wait for the user's confirmation before resuming. - With that route available and only the database session closed/disconnected,
call
reconnectonce directly, withoutcheckfirst. Retry the original bounded operation once only after success. Stop after failed recovery; never alternatecheckandreconnect. If route availability is unknown, usecheckat most once to distinguish the cause. For a startupSAFESELECT_SIDECAR_CONNECTION_FAILED, report the diagnostic instead of treating it as an established database session that merely needs reconnecting. - For missing JDBC drivers, use
driver_list;driver_downloadsupports PostgreSQL. Register other trusted JARs withdriver_addand SHA-256 checking. - Reuse configured secret sources. Never print passwords, put them in JDBC URLs,
process arguments, committed files or reports. Use
config_set_passwordonly when the user authorizes storing a secret through the available secure channel. - Change configuration or integration only within the user's requested scope. Do not invoke destructive config or uninstall tools merely to diagnose failure.
CLI connection commands do not change the agent's active MCP session. A terminated server must be restarted by its host after the cause is corrected.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 35 lines · 43 tokens per session scan A 44ada5baeafe
safeselect-setup is a skill published in the GitHub repository antonillos/safeselect (0 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 451 once invoked, about $0.0002 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 2026-10-24.
Other skills, from other repositories
diesel-guard
Lints Diesel and SQLx Postgres migrations for unsafe schema changes that lock tables or cause downtime, and authors custom Rhai checks. Use when reviewing, writing, or fixing SQL migrations, when diesel-guard reports a violation, when configuring diesel-guard.toml, or when the user mentions migration safety, table…
database
Query and manage SQLite, PostgreSQL, and MySQL databases from the command line. Use when the user asks to run SQL queries, inspect database schemas, create or alter tables, import or export data, manage indexes, analyze query performance with EXPLAIN, back up or restore databases, or perform CRUD operations via…
managing-supabase
Supabase CLI for database management, Edge Functions, migrations, and local development. Use for managing Postgres databases, deploying serverless functions, and debugging Supabase projects.
cli-forge-data
Design and implement safe PostgreSQL database changes for Rust/SQLx applications. Use for new schemas, migrations, constraints, indexes, repositories, transaction boundaries, state machines, idempotency, concurrency control, queues, multi-tenancy, soft deletion, ledgers, outbox/inbox, repair jobs, or corrections…
manage_services
Operate the running Enterprise Demo stack: services, the Postgres database, and scheduled jobs.
postgresql
A guide for administering PostgreSQL, a database system that stores application data and supports SQL queries. It covers connections, users and permissions, database objects, backups, extensions, and query optimisation.