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 agentmods add commands/gotempsh/temps/servicesgit clone --depth 1 https://github.com/gotempsh/tempsWrote 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/gotempsh/temps/services)<a href="https://agentmods.dev/commands/gotempsh/temps/services"><img src="https://agentmods.dev/badge/commands/gotempsh/temps/services.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.04510 |
| Opus 5 | $0.00000 | $0.02255 |
| Sonnet 5 | $0.00000 | $0.00902 |
| Haiku 4.5 | $0.00000 | $0.00451 |
Grade A, and why
services 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 yesterday.
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 — 520 lines — stays where its author put it; the contents beside it link to each section on GitHub.
services command reference
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
Contents
services listservices createservices showservices removeservices startservices stopservices typesservices projectsservices updateservices upgradeservices importservices linkservices unlinkservices connectservices envservices env-varservices logsservices slow-queriesservices enable-pg-stat-statementsservices metricsservices restore-capabilitiesservices list-backupsservices restoreservices restore-runsservices restore-run
services (alias: svc)
Manage external services (databases, caches, storage)
Subcommands:
list(ls) - List all external servicescreate(add) - Create a new external serviceshow- Show service detailsremove(rm) - Remove a servicestart- Start a stopped servicestop- Stop a running servicetypes- List available service typesprojects- List projects linked to a serviceupdate- Update a serviceupgrade- Upgrade a service to a newer versionimport- Import an existing external servicelink- Link a service to a projectunlink- Unlink a service from a projectconnect- Get connection info for a service by name or slugenv- Show environment variables for a linked serviceenv-var- Get a specific environment variablelogs- View persisted logs for an external serviceslow-queries- Show slowest PostgreSQL queries from pg_stat_statementsenable-pg-stat-statements- Enable pg_stat_statements on a standalone Postgres service by restarting its container (drops active connections briefly)metrics- Resource and engine metrics for a database/cache/storage servicerestore-capabilities- Show what restore modes a service supports (in-place / new service / PITR)list-backups- List backups stored on an S3 sourcerestore- Restore a service from a backup (in-place, new service, or PITR)restore-runs- List recent restore runs for a servicerestore-run- Show a single restore run
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.
- yesterday First seen · 520 lines · 0 tokens per session scan A 5cf37979fadb
services is a command published in the GitHub repository gotempsh/temps (712 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,510 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 2026-09-03.
Other commands, from other repositories
cloudflare-kv:optimize
Analyze KV usage patterns and suggest optimizations - identifies missing TTLs, cacheTtl opportunities, bulk operations, and cost savings.
cloudflare-kv:setup
Interactive KV namespace setup wizard - creates namespaces, configures bindings, and generates Worker code.
cloudflare-kv:test
Test KV namespace connection and operations - validates configuration, performs CRUD tests, and reports diagnostics.
cache-manage
Command "cache-manage" from jazz-max/ruflo-hub, covering cache-manage, usage, options, examples and view cache stats.
cache-manage
Command "cache-manage" from amangit1314/repo-rag, covering cache-manage, usage, options, examples and view cache stats.
clear-redis-db
Command "clear-redis-db" from Advance-Technologies-Foundation/clio, covering clear-redis-db, command type, name, description and synopsis.