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.
npx skills add ebeirne/Lians2 --skill lians-integrategit 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/skills/ebeirne/lians2/lians-integrate)<a href="https://agentmods.dev/skills/ebeirne/lians2/lians-integrate"><img src="https://agentmods.dev/badge/skills/ebeirne/lians2/lians-integrate/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/skills/ebeirne/lians2/lians-integrate"><img src="https://agentmods.dev/badge/skills/ebeirne/lians2/lians-integrate.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 | $0.00053 | $0.00699 |
| Opus 5 | $0.00026 | $0.00349 |
| Sonnet 5 | $0.00011 | $0.00140 |
| Haiku 4.5 | $0.00005 | $0.00070 |
Grade A, and why
lians-integrate 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 8d 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.
This is a copy
100% identical to lians-integrate — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integrate Lians into this repository
A pipeline skill: add Lians as the memory layer for the agent in this repo. Add a memory layer; don't rewrite the app. Work test-first.
Procedure
-
Survey the agent loop. Find where the model is called, where context is assembled, and where a turn completes. Detect the framework in use.
-
Branch.
git checkout -b lians-integrationbefore editing. -
Install the matching package:
- LangChain →
pip install lians-sdk[langchain] - LangGraph →
pip install lians-sdk[langgraph] - CrewAI →
pip install lians-sdk[crewai] - OpenAI Agents SDK →
pip install lians-sdk[openai-agents] - AutoGen →
pip install lians-sdk[autogen] - raw / unknown →
pip install lians-sdk(use the harness)
- LangChain →
-
Wire memory in.
Raw loop — use the harness:
from lians import LiansClient, LiansMemoryHarness harness = LiansMemoryHarness( LiansClient(base_url=os.environ["LIANS_URL"], api_key=os.environ["LIANS_API_KEY"]), agent_id="<this-agent>", domain="finance", # or healthcare / legal ) # before model call: context = harness.recall_context(user_query) # after model call: harness.remember(response) # or both: answer = harness.run_turn(user_query, generate=call_model)Framework — import its integration module:
from lians.langchain_integration import LiansChatHistory, build_tools from lians.langgraph_integration import create_recall_node, create_remember_node from lians.crewai_integration import build_crewai_tools from lians.openai_agents_integration import build_openai_agent_tools from lians.autogen_integration import build_autogen_tools -
Test (required). Add a test using
LocalLiansClient(no server/API key) that proves: (a) a remembered fact is recalled, and (b) a superseding write hides the stale fact fromrecallbutrecall_at(as_of=...)still sees it. Run the suite. -
Report. Summarize the diff, the env vars required (
LIANS_URL,LIANS_API_KEY,LIANS_AGENT_ID), and how to verify locally. Do not commit — leave the branch for review.
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.
- 8d ago First seen · 66 lines · 53 tokens per session scan A d278261c6ccd
lians-integrate is a skill published in the GitHub repository ebeirne/Lians2 (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 53 tokens to every session and 699 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to lians-integrate, differing in 8 lines, and is treated as a copy.
Other skills, from other repositories
brain-write
How to write to the INITE Brain knowledge graph from an agent loop — recordfact (with the conversationId / evidence[] grounding inputs), ingestdocument, linkentities, retractfact, recordfeedback, and the detectcontradiction preflight. Covers confidence picking, claim grounding, retract vs forget semantics, identityof…
brain-bitemporal
How to query the INITE Brain knowledge graph across time — the asOf parameter, validFrom/validUntil semantics, reading retracted facts, and the memorydiff "what changed between two cursors" surface. Use when the user's question has a temporal dimension ("on X date", "before Y", "what's new since last conversation").
brain-conflict
How to detect and resolve conflicting beliefs in the INITE Brain knowledge graph — the COMPETING fact status, getcompetingfacts, detectcontradiction preflight, and the human-in-the-loop adjudication workflow. Use when the timeline shows two facts disagreeing on the same predicate, or when an agent needs to decide what…
brain-recall
Recall everything brain knows about one specific entity — current profile, full bitemporal timeline, graph neighbours, and unresolved disagreements. Use when the user names a person/company/thing and asks "tell me about them", "what's their history", or "what do we still disagree about?". For a single-shot LLM…
gctrl
Use the connected GCTRL knowledge base as long-term memory over MCP. Trigger BEFORE answering any factual question about the user's organization, projects, people, systems, decisions, history, or file locations — including "what do we know about X", unfamiliar proper nouns, and "our/we" references — and AFTER…
kaeru
Cognitive memory layer for LLM agents — typed graph + bi-temporal substrate + curator API, reached through the kaeru MCP server. Use when the user wants to capture, recall, reason, or trace persistent thoughts across sessions; when re-entering a multi-session project; or when the user explicitly asks to "remember"…