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-remember)<a href="https://agentmods.dev/commands/lians-ai/lians/lians-remember"><img src="https://agentmods.dev/badge/commands/lians-ai/lians/lians-remember/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-remember"><img src="https://agentmods.dev/badge/commands/lians-ai/lians/lians-remember.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 | $0.00014 | $0.00438 |
| Opus 5 | $0.00007 | $0.00219 |
| Sonnet 5 | $0.00003 | $0.00088 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
lians-remember 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 9d 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-remember — 100% identical, 6 lines differ
What it actually says
/lians-remember
Persist a fact to Lians memory so it survives across this and future sessions. Lians applies supersession automatically: if the new fact contradicts an existing one (same ticker+metric, same patient+condition, same matter+claim), the older fact is marked superseded and disappears from future recall - but stays auditable via point-in-time queries.
What to do
- Parse the fact from: $ARGUMENTS
- Determine the event_time - when the fact became true (business time), not now. If the user wrote "as of ", use it. Otherwise default to today and say so.
- Infer structured metadata where obvious, so supersession can key on it:
- finance →
{"ticker": "...", "metric": "..."} - healthcare →
{"patient_id": "...", "condition": "..."} - legal →
{"matter_id": "...", "claim_type": "..."}
- finance →
- Write it. Prefer the Python SDK if
liansis importable; otherwise call the REST API with the env varsLIANS_URL/LIANS_API_KEY.
from lians import LiansClient # or LocalLiansClient for local SQLite
from datetime import datetime, timezone
mem = LiansClient(base_url=os.environ["LIANS_URL"], api_key=os.environ["LIANS_API_KEY"])
mem.add(
agent_id=os.environ.get("LIANS_AGENT_ID", "claude-session"),
content="<the fact>",
event_time=datetime(YYYY, M, D, tzinfo=timezone.utc),
metadata={...},
)
- Confirm what was stored, the event_time used, and any metadata inferred.
Never invent an event_time precision you don't have - if the user only gave a date, store the date, not a fabricated timestamp.
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.
- 9d ago First seen · 44 lines · 14 tokens per session scan A a8ecd7e33cad
lians-remember is a command published in the GitHub repository Lians-ai/Lians (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 14 tokens to every session and 438 once invoked, about $0.0001 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.
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?".
mempalace-status
Show the current state of your memory palace — wings, rooms, drawer counts, and suggestions.
save-session-learnings
Document session learnings to CLAUDE.md and AGENTS.md. Use after completing significant tasks, debugging sessions, or discovering project patterns.
iai-directive
Record a standing order the user typed themselves, as an explicit memory directive.
init-workspace-flow-questions
Phase 8 Questions of init-workspace-flow.