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/jolliai/jolliaiWrote 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/jolliai/jolliai/status)<a href="https://agentmods.dev/commands/jolliai/jolliai/status"><img src="https://agentmods.dev/badge/commands/jolliai/jolliai/status/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/jolliai/jolliai/status"><img src="https://agentmods.dev/badge/commands/jolliai/jolliai/status.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 | $0.00013 | $0.01060 |
| Opus 5 | $0.00006 | $0.00530 |
| Sonnet 5 | $0.00003 | $0.00212 |
| Haiku 4.5 | $0.00001 | $0.00106 |
Grade A, and why
status 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:
- status — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report Jolli Memory's installation & configuration health for this repo. This is a quick environment check, not a recall — keep the whole thing compact.
-
Call the
statustool. Render its scalar facts as a compact Markdown table (two columns — field, value; one fact per row), in this order; omit a row only where noted:- Version —
version, and whether the extension is enabled (enabled) - Hooks —
hooks.summary, plus the active runtimehooks.runtime - Data migration —
dataMigration - Account — signed in? (
account.signedIn) · Jolli API key? (account.jolliApiKeyConfigured) · Anthropic key? (account.anthropicKeyConfigured) - AI provider —
account.aiProvider: when it islocal-agent, note that memories are generated locally through the user's Claude subscription (no API key or Jolli sign-in required);jolli= Jolli proxy,anthropic= Anthropic key,null= unset (a surface-derived default applies) - Site —
account.site(omit this row when null) - Space — the bound Jolli Space
space.name, plus "agit pushauto-publishes this branch's memories here" (omit this row entirely whenspaceis null / the repo isn't bound) - Memory — the
storedMemoriescount, plus the orphan branchorphanBranch
Then, BELOW the table under an "AI integrations" heading, list each detected integration as its own bullet, rendering the integration's
statusstring verbatim (that string is the whole value — it already embeds the session count with its unit when there are any, e.g.Claude — hook installed (9 sessions), or justCodex — detected & enabledwhen there are none; do not add a count yourself — there is no separate number field). - Version —
-
Call the
queue_statustool (no wait) and add one line: memory generation is idle or still in progress (mention the active/stale counts only if non-zero). -
Decide whether memory generation can actually run, using the provider-aware rule — a blind "any key present" check is wrong, because a pinned provider is only satisfied by its own credential:
account.aiProviderislocal-agent→ can generate (runs through the user's local Claude subscription; no API key or Jolli sign-in needed).account.aiProviderisjolli→ can generate only ifaccount.jolliApiKeyConfigured.account.aiProviderisanthropic→ can generate only ifaccount.anthropicKeyConfigured.account.aiProviderisnull/ unset → can generate ifaccount.jolliApiKeyConfiguredORaccount.anthropicKeyConfigured.
(
account.signedInalone does NOT enable generation — an OAuth token is a sync credential, not a generation one.)If it can generate, do not lead with a warning — and when the provider is
local-agent, do not show a not-signed-in warning at all (signing in is only for sharing to a Jolli Space). If it cannot generate, lead with a prominent warning that outranks every other line: memory generation is disabled for the current provider (account.aiProvider), so commits produce no memories. Name the missing piece — for example "provider isanthropicbut no Anthropic key is set", "provider isjollibut no Jolli API key is set", or "no provider credential at all" — then tell the user how to fix it: set the matching key, run/jolli:loginto sign in to Jolli, or switch to the local Claude subscription (no key needed). -
Close with a one-line health verdict — call out anything missing (not signed in / no key, hook not installed, migration pending), otherwise say it looks healthy.
Do not list branches, topics, or commit summaries — that is what
/jolli:recall and /jolli:search are for; point the user there if they want
the recorded memory itself.
If the status MCP tool is unavailable (an older Jolli that predates it), fall
back to running the bundled CLI through its stable dispatch script (a plugin-only
user has no global jolli on PATH), then summarise its output:
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 · 74 lines · 13 tokens per session scan A 5820177cf020
status is a command published in the GitHub repository jolliai/jolliai (141 stars, last pushed 6d ago), licensed Apache-2.0. It adds 13 tokens to every session and 1,060 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 2026-08-30.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.