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/login)<a href="https://agentmods.dev/commands/jolliai/jolli-claude-plugin/login"><img src="https://agentmods.dev/badge/commands/jolliai/jolli-claude-plugin/login/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/jolli-claude-plugin/login"><img src="https://agentmods.dev/badge/commands/jolliai/jolli-claude-plugin/login.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 | $0.00034 | $0.00566 |
| Opus 5 | $0.00017 | $0.00283 |
| Sonnet 5 | $0.00007 | $0.00113 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
login 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.
This is a copy
100% identical to login — 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jolli Login
Sign the user in to Jolli. Signing in saves the credentials Jolli needs to bind
this repo to a Space and share memories with teammates (a git push then
auto-publishes the branch's memories to the bound Space).
Memory generation does not require signing in. By default the Claude Code
plugin generates memories locally through your existing Claude subscription (the
local-agent provider) — no Anthropic API key and no Jolli account needed.
Signing in is about sharing to a Space, and it does not change that: after
login, summaries still run locally.
Step 1: Run the login flow
Run the Jolli CLI through its stable dispatch script (resolves the installed Jolli automatically — no path guessing). It opens the system browser to the Jolli login page and waits on a local loopback callback while the user completes sign-in:
"$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. Sign-in happens entirely in the user's browser; never ask the user for passwords, tokens, or callback URLs.
If the command is not found, the plugin's session bootstrap has not run yet —
ask the user to fully restart the app (Cmd+Q) so the plugin installs its hooks,
then try /jolli:login again.
Step 2: Report the outcome
- Success — the CLI prints
Signed in successfully!withAuth token: savedandJolli API Key: saved. Tell the user they can now bind this repo to a Jolli Space (/jolli:init) and share memories on push. Note that memory generation keeps running locally through their Claude subscription — logging in did not change the summary engine. - Failure — the CLI prints
Login failed: <reason>. Surface the reason and suggest retrying/jolli:login. If the browser did not open, tell the user the CLI also printed a login URL they can open manually.
Note: no key required to generate memories
Memory generation works out of the box via the local Claude subscription — no Anthropic API key, no Jolli sign-in. Sign in only when you want to share memories to a Jolli Space, or bring your own Anthropic / Jolli key if you'd rather not use the local subscription for summaries.
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 · 53 lines · 34 tokens per session scan A 79ac83cab446
login is a command published in the GitHub repository jolliai/jolli-claude-plugin (2 stars, last pushed 11d ago), licensed Apache-2.0. It adds 34 tokens to every session and 566 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 login, 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.