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/wrg32786/aigent-osWrote 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/wrg32786/aigent-os/autorefresh-setup)<a href="https://agentmods.dev/commands/wrg32786/aigent-os/autorefresh-setup"><img src="https://agentmods.dev/badge/commands/wrg32786/aigent-os/autorefresh-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/commands/wrg32786/aigent-os/autorefresh-setup"><img src="https://agentmods.dev/badge/commands/wrg32786/aigent-os/autorefresh-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 | $0.00016 | $0.00340 |
| Opus 5.5 | $0.00006 | $0.00136 |
| Sonnet 5.5 | $0.00003 | $0.00068 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade B, and why
autorefresh-setup scanned grade B with 1 finding 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 today.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
3. **Your settings (read-only check).** Look at the user's `~/.claude/settings.json` and project `.claude/settings.json` and tell them whether `idleCompaction` is set. The aigent-os runner expects `"idleCompaction": fals What it actually says
Print the following guidance to the user. Do not run any installer, do not edit settings files, do not download anything.
- What this plugin gives you. Manual-trigger refresh:
/refreshwrites a capsule, you run/clear, and the SessionStart hook points the fresh session at the capsule. The PreCompact hook cannot write or save anything useful: if no valid capsule exists it only leaves a marker, and the SessionStart hook after the compaction then says no capsule existed and asks you to run/capsule. Run/capsulebefore compaction if you want context preserved. - What it cannot do. A plugin is loaded by Claude Code, so it cannot launch Claude Code or type
/clearfor you. Fully hands-off refresh at a context threshold needs a runner that owns the terminal session. That runner is part of the full aigent-os install, not this plugin. - Your settings (read-only check). Look at the user's
~/.claude/settings.jsonand project.claude/settings.jsonand tell them whetheridleCompactionis set. The aigent-os runner expects"idleCompaction": false. Say what you found and that they can change it themselves; do not edit it. - For hands-off refresh. Point them to the aigent-os repository (https://github.com/wrg32786/aigent-os) and its INSTALL.md. When aigent-os is installed in a project, this plugin detects it and stays silent, so the two never double-fire.
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.
- today First seen · 11 lines · 16 tokens per session scan B bfd6c71c8d3d
autorefresh-setup is a command published in the GitHub repository wrg32786/aigent-os (25 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 340 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-28.
Other commands, from other repositories
patterns
Scan recent sessions for recurring patterns and turn them into captures (rules, concept notes, writing seeds).
cierre
A sales call just ended: turn its transcript into the full follow-up (CRM, tasks, email draft, reminder, coaching).
deconstruct
First-principles analyst: surface hidden assumptions, find foundational truths, rebuild from scratch.
diagnose
Run a self-check on your AI Brain Starter install (CLAUDE.md, Meta folder, skills, hooks, MCPs).
instinct-import
Import a portable YAML instinct pack with confidence-gated merge (Instinct Engine).
meeting-todos
Extract action items from a meeting note and route them to the right to-do file.