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/refresh)<a href="https://agentmods.dev/commands/wrg32786/aigent-os/refresh"><img src="https://agentmods.dev/badge/commands/wrg32786/aigent-os/refresh/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/refresh"><img src="https://agentmods.dev/badge/commands/wrg32786/aigent-os/refresh.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 | $0.00019 | $0.00120 |
| Opus 5.5 | $0.00008 | $0.00048 |
| Sonnet 5.5 | $0.00004 | $0.00024 |
| Haiku 4.5 | $0.00002 | $0.00012 |
Grade A, and why
refresh 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 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.
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
Do a manual context refresh:
- Run the
context-capsuleskill: write and validate a capsule. - If validation passed, reply with exactly two short lines: the capsule path, and "Run /clear now. The new session will name this capsule and continue from it."
- If it did not validate, say what failed and do not suggest /clear.
You cannot type /clear yourself; only the user can. Do nothing after those lines.
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 · 12 lines · 19 tokens per session scan A 14a92cc08597
refresh is a command published in the GitHub repository wrg32786/aigent-os (25 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 120 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 2026-10-28.
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.