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 smixs/iva-agent --skill background-checkgit clone --depth 1 https://github.com/smixs/iva-agentWrote 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/smixs/iva-agent/background-check)<a href="https://agentmods.dev/skills/smixs/iva-agent/background-check"><img src="https://agentmods.dev/badge/skills/smixs/iva-agent/background-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/skills/smixs/iva-agent/background-check"><img src="https://agentmods.dev/badge/skills/smixs/iva-agent/background-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 | $0.00032 | $0.00594 |
| Opus 5.5 | $0.00013 | $0.00238 |
| Sonnet 5.5 | $0.00006 | $0.00119 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
background-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 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.
What it actually says
Check a background job
A check observes a job; it does not keep a model turn open until the job finishes.
- Read a bounded status snapshot: the job's checkpoint/progress file, a short tail
of its log, or
systemctl --user show <unit> -p ActiveState -p SubState -p Result -p ExecMainStatus. For the cause, readjournalctl --user -u <unit> -n 50 --no-pager. A PID alone does not prove progress or completion. Use a short tool timeout; nosleep,tail -f, status checks in a loop or wait for process exit. - Return the observed state and its evidence: completed, still running, failed or unknown. Still running means say what remains; never report it as complete. Stop checking after that snapshot. A Reminder returns the status as its final text: code delivers it. Do not send the report yourself, invent a keepalive or create another Reminder inside that turn. Arrange a later check only in the owner's chat, if asked.
- A failed custom script: preserve its output and resume checkpoint, find the
failing input and show the cause before suggesting a restart. Colliding PDF
basenames need a job-owned temporary directory and unique paths per input,
not overwriting
/tmp/<basename>. A restart can repeat external side effects; establish resume safety and the owner's authorization first. - An interrupted
memory-night: readiva diagnoseand its Schedules section, the failed job's log, the raw day invault/daily/and its cache indata/memory/night/. A day not processed that night is not proof that a Card was deleted. The next night resumes an unfinished day from its cache. Never delete that cache, raw days or Cards to repair a provider timeout; never switch the night model behind the owner's back. Restore the configured provider, then check the next run.iva jobs ackacknowledges a failure; it does not perform the missing work. If bytes are actually missing, preserve the files and Git evidence and loadreport-problem.
Existing Watch and Brief read failures of user timer services and installed
plugin/MCP services. They do not supervise arbitrary detached processes, detect
a hung but live process, or restart a custom script. Keep a persistent capability
in a plugin, and use a Routine for recurring work; do not build another scheduler
or watchdog in the chat. Before fixing a Watch failure, follow watch: read-only
until the owner's Fix tap.
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 Changed 5a837eed5897
- 7d ago First seen · 41 lines · 32 tokens per session scan A 0318f5308a2c
background-check is a skill published in the GitHub repository smixs/iva-agent (240 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 594 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 2026-10-09.
Other skills, from other repositories
research-report
Research report on companies, competitors, markets or products: research a company, compare competitors, market landscape, funding, pricing, launches. Also to save a brief, summary or snapshot built from search results.
ideation
Generate project ideas through creative constraints. Use when the user says 'I want to build something', 'give me a project idea', 'I'm bored', 'what should I make', 'inspire me', or any variant of 'I have tools but no direction'. Works for code, art, hardware, writing, tools, and anything that can be made.
slacrawl
Archive and search Slack workspace messages, threads, and channels via the slacrawl CLI. Supports API sync, Slack export ZIP import, local desktop cache import, and full-text search.
apple-notes
Manage Apple Notes via the memo CLI on macOS (create, view, search, edit).
obsidian
Read, search, and create notes in the Obsidian vault.
designer_guide
Guidance for creating and editing designs using the designer tool.