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/jolli-claude-pluginWrote 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/jolli-claude-plugin/init)<a href="https://agentmods.dev/commands/jolliai/jolli-claude-plugin/init"><img src="https://agentmods.dev/badge/commands/jolliai/jolli-claude-plugin/init.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.01171 |
| Opus 5 | $0.00024 | $0.00585 |
| Sonnet 5 | $0.00010 | $0.00234 |
| Haiku 4.5 | $0.00005 | $0.00117 |
Grade A, and why
init 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 6d 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.
This is a copy
100% identical to init — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jolli Init
One-shot setup for the current repository: make sure the user is signed in, enable Jolli's memory generation for this repo, then bind the repo to a Jolli Space so the branch's memories can be pushed and shared.
$ARGUMENTS is an OPTIONAL Space id, slug, or name to bind to. When present,
skip the interactive Space picker in Step 4 and bind to it directly.
Work through the steps in order. Stop and report if a step fails — later steps depend on earlier ones.
Step 1: Check current state
Call the status tool and read account.signedIn,
account.jolliApiKeyConfigured, and account.anthropicKeyConfigured. This tells
you whether Step 2 (sign-in) is needed.
If the status MCP tool is unavailable (an older Jolli), fall back to the
bundled CLI through its stable dispatch script and read its output:
"$HOME/.jolli/jollimemory/run-cli" status
If run-cli does not exist, the plugin's session bootstrap has not run yet — ask
the user to fully restart the app (Cmd+Q) so the plugin installs itself, then
re-run /jolli:init.
Step 2: Sign in (only if needed)
Memory generation itself needs no sign-in — the plugin defaults to the
local-agent provider, generating summaries through the user's local Claude
subscription. Signing in is required only to bind and share a Space (Step 4),
and Space binding authenticates with a Jolli credential specifically (a Jolli
sign-in or a Jolli API key); an Anthropic key does nothing for it. So run the
login flow now whenever Step 1 shows the user is not signed in AND has no
Jolli API key (account.jolliApiKeyConfigured is false) — regardless of whether
an Anthropic key is present, since an Anthropic key can't bind a Space. If they
already have a Jolli sign-in or a Jolli API key, skip this step. The login flow
opens the browser and waits on a loopback callback:
"$HOME/.jolli/jollimemory/run-cli" auth login
This is interactive and can take up to a minute — wait for it to return, do not background it. Never ask the user for passwords, tokens, or callback URLs. If it fails, surface the reason and stop (the later steps need auth). If the user already has a Jolli sign-in or a Jolli API key, skip this step.
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.
- 6d ago First seen · 103 lines · 48 tokens per session scan A 71ad9ef4ee74
init is a command published in the GitHub repository jolliai/jolli-claude-plugin (2 stars, last pushed 8d ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,171 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to init, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.