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/hyperb1iss/uniflyWrote 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/hyperb1iss/unifly/unifly-audit)<a href="https://agentmods.dev/commands/hyperb1iss/unifly/unifly-audit"><img src="https://agentmods.dev/badge/commands/hyperb1iss/unifly/unifly-audit/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/hyperb1iss/unifly/unifly-audit"><img src="https://agentmods.dev/badge/commands/hyperb1iss/unifly/unifly-audit.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 | $0.00022 | $0.00261 |
| Opus 5.5 | $0.00009 | $0.00104 |
| Sonnet 5.5 | $0.00004 | $0.00052 |
| Haiku 4.5 | $0.00002 | $0.00026 |
Grade A, and why
unifly-audit 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 11d 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
UniFi Security Audit
Load unifly skill and unifly skill commands before inspecting the network.
Use the installed guide and command help for authentication, enumeration,
identifiers, and output fields. Inspect returned schemas before filtering.
Apply the optional profile argument consistently; when omitted, retain the configured default. Review WiFi security settings, firewall policy scope and ordering, device firmware availability, and network isolation. Distinguish intended guest access from an unintended exposure. Assess findings against the user's network requirements instead of assigning severity from a single field such as missing logging or WPA2 support.
Keep the audit read-only. Report evidence, impact, proposed remediation, and checks unavailable with the current access. Failed dependency queries leave resource usage unknown; they do not establish that deletion is safe.
If unifly skill is unavailable, use unifly --help and explain that the
binary needs updating before it can supply version-matched guidance.
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.
- 11d ago Changed · -64 lines · -6 tokens per session eebd36f95212
- 1mo ago First seen · 93 lines · 28 tokens per session scan A 18157f566def
unifly-audit is a command published in the GitHub repository hyperb1iss/unifly (272 stars, last pushed 4d ago), licensed Apache-2.0. It adds 22 tokens to every session and 261 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 2026-08-30.
Other commands, from other repositories
computer
Drive a computer's screen, mouse, and keyboard.
role
Set this Claude session's agent-bus role so other sessions can address it (e.g. /role frontend, /role backend, /role tester).
auto-insights
Show or configure auto-generated insights from the claudectl brain — friction patterns, suggested rules, and workflow improvements.
brain
Toggle the claudectl brain gate on/off/auto for this session.
inbox
Drain pending agent-bus messages addressed to this session's role.
brain-stats
Show claudectl brain learning metrics — accuracy, correction rate, and effectiveness.