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/Lians-ai/LiansWrote 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/lians-ai/lians/lians-integrate)<a href="https://agentmods.dev/commands/lians-ai/lians/lians-integrate"><img src="https://agentmods.dev/badge/commands/lians-ai/lians/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/commands/lians-ai/lians/lians-integrate"><img src="https://agentmods.dev/badge/commands/lians-ai/lians/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 | $0.00017 | $0.00531 |
| Opus 5.5 | $0.00007 | $0.00212 |
| Sonnet 5.5 | $0.00003 | $0.00106 |
| Haiku 4.5 | $0.00002 | $0.00053 |
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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- lians-integrate — 100% identical, 4 lines differ
What it actually says
/lians-integrate
Integrate Lians as the memory layer for the agent in this repository. Work test-first and keep the diff minimal - you are adding a memory layer, not rewriting the app.
Procedure
-
Survey. Identify the agent loop: where the model is called, where context is assembled, and where turns complete. Detect the framework (or honor the one named in $ARGUMENTS). If none, use the raw harness.
-
Branch. Create a feature branch
lians-integrationbefore editing. -
Add the dependency. Choose the matching extra:
pip install lians-sdk[langchain]/[langgraph]/[crewai]/[openai-agents]/[autogen]- raw / unknown framework →
pip install lians-sdkand use the harness.
-
Wire it. Prefer the harness for raw loops:
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 at once: answer = harness.run_turn(user_query, generate=call_model)For a framework, import its integration module instead (
from lians.langchain_integration import build_tools, etc.). -
Test. Add a test that proves recall-before/remember-after works and that a superseding write hides the stale fact. Use
LocalLiansClientso the test needs no server or API key. 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 the user to review. If tests fail, stop and report - do not mark the integration done.
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.
- 1mo ago First seen · 49 lines · 17 tokens per session scan A 082a582fced5
lians-integrate is a command published in the GitHub repository Lians-ai/Lians (16 stars, last pushed today), licensed Apache-2.0. It adds 17 tokens to every session and 531 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 2026-08-31.
Other commands, from other repositories
wrap
Close the session cleanly. Update entity state. Capture decisions. Detect momentum shifts.
start
"What accumulated? What's blocking? Where do I begin?".
tree-ring-certify
Generate Tree Ring harness or recall-quality evidence without confusing it with the full framework release suite.
save-session-learnings
Document session learnings to CLAUDE.md and AGENTS.md. Use after completing significant tasks, debugging sessions, or discovering project patterns.
ijfw-audit
Run the IJFW audit gate for the current workflow phase. Usage: /ijfw-audit [phase name].
iai-directive
Record, list, or remove a standing order the user typed themselves.