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/ebeirne/Lians2Wrote 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/ebeirne/lians2/lians-audit)<a href="https://agentmods.dev/commands/ebeirne/lians2/lians-audit"><img src="https://agentmods.dev/badge/commands/ebeirne/lians2/lians-audit.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 5.1 | $0.00020 | $0.00475 |
| Opus 5 | $0.00010 | $0.00237 |
| Sonnet 5 | $0.00004 | $0.00095 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
lians-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 7d 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
/lians-audit
Run the compliance surfaces that make Lians defensible to a regulator, examiner, or opposing counsel. Parse the operation from $ARGUMENTS and execute the matching call. Always print exactly what was returned — these are evidentiary outputs; do not paraphrase or soften them.
Operations
snapshot <agent_id> <YYYY-MM-DD>
Exhaustive knowledge-state reconstruction — every fact valid at that instant, not a ranked top-k. The one-call demo for "show me everything the agent knew on 2025-03-14."
snap = mem.snapshot(agent_id="<agent>", as_of=datetime(...))
print(snap["total"], "facts valid at", snap["as_of"])
verify
Verify the SEC 17a-4 tamper-evident SHA-256 hash chain. A broken link means the audit log was altered.
print(mem.verify_chain()) # {"status": "ok", "rows_checked": N, "violations": []}
backtest <agent_id> <YYYY-MM-DD>
Lookahead-bias detection — flags any fact the agent held that it could not have known at the simulation date. A clean report is the proof a risk committee needs.
r = mem.backtest_check(agent_id="<agent>", simulation_as_of=datetime(...))
print("clean" if r["is_clean"] else f"{len(r['flags'])} contamination flags")
erase <subject_id> <request_ref>
GDPR Art. 17 / HIPAA crypto-shred. Destroys the subject's per-subject key so all
their content becomes unreadable — the audit hash chain survives. This is
irreversible. Confirm with the user before running, and record the request_ref.
print(mem.erase(subject_id="<subject>", request_ref="<ref>"))
If the operation isn't recognized, list these four and ask which one.
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.
- 7d ago First seen · 48 lines · 20 tokens per session scan A 9f3269d91d6b
lians-audit is a command published in the GitHub repository ebeirne/Lians2 (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 475 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other commands, from other repositories
gdpr-audit
You are a senior Security & Compliance specialist. The user needs help with gdpr audit in the context of security audits, vulnerability management, gdpr/soc2/iso27001 compliance and incident response.
iam-audit
You are a senior Security & Compliance specialist. The user needs help with iam audit in the context of security audits, vulnerability management, gdpr/soc2/iso27001 compliance and incident response.
pentest-report
You are a senior Security & Compliance specialist. The user needs help with pentest report in the context of security audits, vulnerability management, gdpr/soc2/iso27001 compliance and incident response.
privacy-policy
You are a senior Security & Compliance specialist. The user needs help with privacy policy in the context of security audits, vulnerability management, gdpr/soc2/iso27001 compliance and incident response.
soc2-readiness
You are a senior Security & Compliance specialist. The user needs help with soc2 readiness in the context of security audits, vulnerability management, gdpr/soc2/iso27001 compliance and incident response.
threat-model
You are a senior Security & Compliance specialist. The user needs help with threat model in the context of security audits, vulnerability management, gdpr/soc2/iso27001 compliance and incident response.