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-recall)<a href="https://agentmods.dev/commands/ebeirne/lians2/lians-recall"><img src="https://agentmods.dev/badge/commands/ebeirne/lians2/lians-recall/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/ebeirne/lians2/lians-recall"><img src="https://agentmods.dev/badge/commands/ebeirne/lians2/lians-recall.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 | $0.00019 | $0.00402 |
| Opus 5 | $0.00010 | $0.00201 |
| Sonnet 5 | $0.00004 | $0.00080 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
lians-recall 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.
What it actually says
/lians-recall
Retrieve the facts Lians holds that are relevant to $ARGUMENTS. By default you get the current state — superseded/stale revisions are excluded at the database layer, so you never reason over contaminated context.
What to do
- Parse the query and any "as of " clause from $ARGUMENTS.
- Recall:
from lians import LiansClient # or LocalLiansClient
mem = LiansClient(base_url=os.environ["LIANS_URL"], api_key=os.environ["LIANS_API_KEY"])
# Present state (default)
res = mem.recall(agent_id=os.environ.get("LIANS_AGENT_ID", "claude-session"),
query="<query>", k=5)
# Point-in-time — "what did we know on that date?"
res = mem.recall_at(agent_id=..., query="<query>",
as_of=datetime(YYYY, M, D, tzinfo=timezone.utc))
for m in res["memories"]:
print(m["event_time"], m["content"])
- Present the facts with their event_time and source so the user can judge
recency and provenance. If a fact's
contentisnull, it was crypto-shredded (GDPR/HIPAA erasure) — say so rather than guessing. - If nothing is found, say so plainly. Do not fabricate recalled facts.
When the user asks an audit-style question ("what did we know on X", "before the
trade", "before the privilege cutoff"), always use recall_at with that date —
this is the point-in-time guarantee mem0 and Zep cannot provide.
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 · 41 lines · 19 tokens per session scan A 5e27efe6ae70
lians-recall is a command published in the GitHub repository ebeirne/Lians2 (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 402 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
lesson
Capture a lesson learnt as durable archival memory in kaeru.
recall
Recall what kaeru knows about a topic — search then drill the top hit.
kaeru
kaeru re-entry ritual — load process state + epistemic state for an initiative.
tree-ring-recall
Recall durable Tree Ring Memory context before starting or resuming work.
tree-ring-update
Check for or install a verified Tree Ring Memory CLI update without changing installation scope.
tree-ring-certify
Generate Tree Ring harness or recall-quality evidence without confusing it with the full framework release suite.