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-recall)<a href="https://agentmods.dev/commands/lians-ai/lians/lians-recall"><img src="https://agentmods.dev/badge/commands/lians-ai/lians/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/lians-ai/lians/lians-recall"><img src="https://agentmods.dev/badge/commands/lians-ai/lians/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 | $0.00393 |
| Opus 5 | $0.00010 | $0.00197 |
| Sonnet 5 | $0.00004 | $0.00079 |
| Haiku 4.5 | $0.00002 | $0.00039 |
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 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.
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 By default you get the current state - superseded/stale revisions are excluded at the database layer, so you never reason over contaminated context.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 after 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.
Do not make competitor capability claims without current, archived evidence.
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.
- 11d ago First seen · 41 lines · 19 tokens per session scan A ad48bbe55eaf
lians-recall is a command published in the GitHub repository Lians-ai/Lians (10 stars, last pushed 3d ago), licensed Apache-2.0. It adds 19 tokens to every session and 393 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, list, or remove a standing order the user typed themselves.
kiro-steering-custom
Command "kiro-steering-custom" from gotalab/cc-sdd, covering kiro custom steering creation, workflow, available templates, steering principles and tool guidance.