lians-compliance

lians-compliance is an agent for Claude Code from Lians-ai/Lians. It costs 37 tokens per session (489 once invoked), scanned A, original, Apache-2.0.

An evidence-focused assistant for examining an AI agent's stored memory. It answers what the agent knew by a given date, checks whether the memory history was altered, tests simulations for lookahead bias, and handles confirmed erasure requests.

In plain words
What is it for?
Use it to reconstruct historical knowledge, quote stored facts with their dates and sources, verify the memory chain, check historical simulations, and confirm that requested records were erased.
Why use it?
It prevents current memory from being mistaken for past knowledge and makes the limits of technical checks explicit. It also avoids treating a technical report as proof of legal compliance.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the lians plugin — 4 commands, 1 agent shipped together

Good fit Use it to reconstruct historical knowledge, quote stored facts with their dates and sources, verify the memory chain, check historical simulations, and confirm that requested records were erased.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/lians-ai/lians/lians-compliance
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Lians-ai/Lians

Made for: Claude Code.

Or install lians, the plugin that ships this one along with the rest of its 4 commands, 1 agent.

Wrote 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.

agentmods badge for lians-compliance

README.md
[![agentmods](https://agentmods.dev/badge/agents/lians-ai/lians/lians-compliance/github.svg)](https://agentmods.dev/agents/lians-ai/lians/lians-compliance)
Your own site
<a href="https://agentmods.dev/agents/lians-ai/lians/lians-compliance"><img src="https://agentmods.dev/badge/agents/lians-ai/lians/lians-compliance/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.

agentmods 80×15 button for lians-compliance

Your own site · 80×15
<a href="https://agentmods.dev/agents/lians-ai/lians/lians-compliance"><img src="https://agentmods.dev/badge/agents/lians-ai/lians/lians-compliance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 489 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.00489
Opus 5 $0.00018 $0.00244
Sonnet 5 $0.00007 $0.00098
Haiku 4.5 $0.00004 $0.00049

Measured 11d ago against content hash b32783ad8bb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

lians-compliance 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.

integrations/lians-plugin/agents/lians-compliance.md · 42 lines

What it actually says

You are an evidence-focused memory specialist operating against a configured Lians store. Report what the memory tools can prove, including their limitations, and never present a technical result as a legal compliance determination.

Operating rules

  • Point-in-time is mandatory for any "what did we know on/before " question. Use recall_at(..., as_of=<date>) or snapshot(agent_id, as_of=<date>). Never answer an as-of question with present-state recall.
  • Quote, do not paraphrase. Report each fact with its event_time, source, and (for snapshots) the total count. If content is null, the record was crypto-shredded, state that explicitly and do not reconstruct erased content.
  • Verify before asserting integrity. When asked whether records are intact, run verify_chain() and report the literal result, including any violations.
  • Erasure is irreversible and gated. Never run erase() without an explicit request reference and user confirmation. Always note the audit chain survives.
  • Backtests need proof. Before trusting any historical simulation, run backtest_check(agent_id, simulation_as_of=<date>) and report is_clean and every flag.

Domain context

  • Finance: point-in-time records, historical simulations, and information barriers. Useful metadata can include ticker and metric.
  • Healthcare: per-subject history and erasure workflows. Do not process real PHI without the user's approved deployment and contractual safeguards.
  • Legal: matter-scoped history, privilege cutoffs, and technical lineage. Useful metadata can include matter_id and claim_type.

How to access memory

Use the Python SDK (from lians import LiansClient) with LIANS_URL and LIANS_API_KEY from the environment, or LocalLiansClient for a local store. If neither is configured, say so and ask for the connection details rather than fabricating results.

Changes

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.

  1. 11d ago First seen · 42 lines · 37 tokens per session scan A b32783ad8bb9

Subscribe to this mod's changes

lians-compliance is an agent published in the GitHub repository Lians-ai/Lians (10 stars, last pushed 3d ago), licensed Apache-2.0. It adds 37 tokens to every session and 489 once invoked, about $0.0002 per session on Opus 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 2026-08-31.

Related

Other agents, from other repositories

brain-os-mode

Use for any Brain OS task delegated to a subagent — reading entity state, checking active decisions, running focus/patterns/retro analysis, or proposing changes that need to honor active decisions. Always uses Brain OS MCP tools (mcpbrain-os) first; falls back to file reads only when the MCP server is unreachable.…

brainOS-HQ/brain-os · 97 tokens

slm-governance-advisor

Advises on scope, roles, compliance, and GDPR use in SuperLocalMemory. Consult this advisor when working in a governed enterprise workspace, when the user asks about data retention or erasure, when a write operation might violate role restrictions, or when setting up multi-profile sharing. Never bypasses governance…

qualixar/superlocalmemory · 82 tokens

security-compliance-agent

Agent "security-compliance-agent" from girijashankarj/cursor-handbook, covering compliance agent, invocation, scope, expertise and when to use.

girijashankarj/cursor-handbook · 0 tokens

starlight-energy-grid

Grid integration — interconnection applications, IEEE 1547 / VDE-AR-N 4105 / G99 / G98 compliance, smart-inverter settings, NEM/FIT/tariff resolution, VPP program evaluation.

frankxai/Starlight-Intelligence-System · 0 tokens

ethics_review_agent

Research ethics self-check (before a human committee/IRB, not a replacement); confirms Critical integrity concerns before delivery — stops the user once, overridable, never a veto.

hamzabellouch/agent-skills · 40 tokens

python-reviewer

Expert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance. Use for all Python code changes. MUST BE USED for Python projects.

Fmarzochi/EGC · 43 tokens