signetai

Navigate Signet ontology and knowledge graph state from Codex.

Use Signet-specific recall and source search from Codex without confusing it with Codex native memory.

Save explicit notes into Codex native memory through Signet.

Search Signet transcript/session evidence from Codex.

Diagnose Signet memory, recall, source, session, embedding, and graph issues from runtime truth without bypassing scope or provenance.

Run explicit Signet recall through the canonical scoped recall path, preserving scores, sources, provenance, supplementary context, and session dedupe metadata.

Save an explicit scoped memory through Signet. Use only when the user clearly asks to remember something or when a tool/harness must persist an explicit memory row.

Operate Signet as the local source-backed substrate for agent identity, scoped memory, provenance, ontology, skills, secrets, sources, and harness integrations.

Maintain Signet's living ontology and memory substrate from transcripts, memory artifacts, source artifacts, notes, summaries, and imported records.

Interactive interview to set up your Signet workspace (~5-10 minutes). Writes identity files to ~/.agents/ — does not access external APIs, send data anywhere, or execute arbitrary code. Use when user runs /onboarding or says 'set up my agent'.

Automatically benchmark your custom memory implementation against established systems like Supermemory. Set up a public benchmark, or create your own. Compare solutions against quality, latency, features and cost, easily, with a simple UI and CLI.

Design agents with genuine humanity — craft SOUL.md, IDENTITY.md, USER.md, and AGENTS.md files that produce agents people actually connect with. Use when: (1) creating a new agent's personality and identity files, (2) refining an existing agent's voice, tone, or depth, (3) an agent wants to self-improve by rewriting its own configuration files, (4) reviewing agent files for authenticity and diagnosing why an agent feels robotic or hollow, (5) the user says "design an agent," "shape their personality," "make them feel more real," "agent identity," "soul file," or "agent architect."

Guide for discovering, installing, and creating effective skills. This skill should be used when users want to discover and install existing skills (e.g., "how do I do X", "find a skill for X", "is there a skill that can...") or create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Search the web and scrape pages using the local tool stack: SearXNG (meta-search), Lightpanda (fast headless fetch), and Agent-Browser (full browser automation). This is your DEFAULT web skill — use it whenever you need to look something up, research a topic, fetch a webpage, extract content from a URL, check current information, find documentation, do competitive research, or answer any question that benefits from live web data. Triggers on any form of: search for, look up, google, find out, research, what's the latest on, fetch this page, scrape this site, check this URL, pull info from, web search, or any task where current web information would improve your answer. Even if the user doesn't explicitly ask you to search — if answering well requires current info you don't have, use this skill. NOT for interactive browser automation like form filling or clicking (use [[agent-browser]] or [[browser-use]]).