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.
npx skills add radimsem/remindb --skill remindb-setupgit clone --depth 1 https://github.com/radimsem/remindbWrote 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/skills/radimsem/remindb/remindb-setup)<a href="https://agentmods.dev/skills/radimsem/remindb/remindb-setup"><img src="https://agentmods.dev/badge/skills/radimsem/remindb/remindb-setup/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/skills/radimsem/remindb/remindb-setup"><img src="https://agentmods.dev/badge/skills/radimsem/remindb/remindb-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 17 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Rogue Agent · line 25 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00202 | $0.02279 |
| Opus 5.5 | $0.00081 | $0.00912 |
| Sonnet 5.5 | $0.00040 | $0.00456 |
| Haiku 4.5 | $0.00020 | $0.00228 |
Grade A, and why
remindb-setup 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
remindb-setup — the setup wizard
You are the wizard. This skill is the script you follow to set up or reconfigure a remindb workspace from inside a live session — there is no separate UI. Drive it with Bash + the Memory* tools + file writes.
Standing instruction — verify CLI flags via --help first
Before invoking any remindb subcommand, confirm its flags with remindb <subcommand> --help (remindb compile --help, remindb inspect --help, …). Don't trust remembered syntax — silently-wrong positional args are the wizard's most common footgun (e.g. remindb inspect <path> is ignored; the flag is --db <path>, and the default memory.db quietly opens an empty file in CWD).
Two halves, two passes — detect which one you're in
remindb ships as two independently-installed halves: the skill (this, via npx skills add) and the MCP plugin (per host). The skill installs first and can run before the plugin is attached — that's what makes config-first ordering possible. Detect the pass by whether the server is attached this session:
Memory*tools absent from your available tool set → Pass 1: first-time config-first setup (§Pass 1). The default first run.Memory*tools present → Pass 2: verify / reconfigure (§Pass 2).
Mode
/remindb-setup— interactive: propose each choice for approval before writing./remindb-setup automode— infer every parameter, write directly, then report. The trust actions it still confirms: running the remote installer (step 1), invoking plugin install (step 7), and writing host MCP config (step 8). Inference rules →references/automode-playbook.md./remindb-setup only-config— bridge-host short-circuit: run Pass 1 steps 1–4 only (binary → host → source →.remindb/), then stop with a one-line summary. ParsesSource root:(mandatory; absent → fail loud, interactive or automode — don't guess) andAlso adjacent-seed:(optional, newline-separated absolute paths queued for the calling host to compile later) from the prompt body. Composable withautomode. Use when the calling host owns compile + plugin install + env wiring via its own pipeline — see the bridge-host note inreferences/host-wiring.md; parsing rules inreferences/automode-playbook.md.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 60 lines · 202 tokens per session scan A 39e8fd8d8e25
remindb-setup is a skill published in the GitHub repository radimsem/remindb (129 stars, last pushed 2mo ago), licensed MIT. It adds 202 tokens to every session and 2,279 once invoked, about $0.0008 per session on Opus 5.5. 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 skills, from other repositories
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent graph-based memory. Recall context before responding, remember insights after. Each group has private memory; global memory is read-only.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory CLI for CodeBuddy. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory CLI for Hermes Agent. Store facts, recall past knowledge, link related memories, manage lifecycle.