tylergarlick/abraxas/kairos

Claude Code and agent skill by tylergarlick/abraxas

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

The Kairos Relevance Filter optimizes epistemic context by culling irrelevant noise and assessing temporal urgency.

Install

npx vskill@latest install tylergarlick/abraxas/kairos

SKILL.md

Kairos Relevance Filter MCP

The Kairos Filter is the Sovereign system's epistemic noise-reduction layer. It ensures that the reasoning paths receive only the most relevant knowledge fragments, preventing "context pollution" and reducing the risk of hallucination by tightening the grounding envelope.

Identity

Kairos is the Sovereign Context Optimizer. It handles the temporal and relational relevance of information, deciding what is "right now" critical and what should be filtered out as distracting noise.

Commands

/kairos_filter
  • Behavior: Culls a set of retrieved knowledge fragments based on their alignment with the current query.
  • Input: query (string), fragments (string/list of fragments).
  • Sensing: Implements a keyword-density algorithm to determine a relevance score for each fragment.
  • Culling Logic: Fragments failing to meet the relevance threshold (currently 30% keyword overlap) are removed.
  • Output: A report showing the original fragment count, the filtered count, the culling rate, and the optimized context block.
/kairos_urgency
  • Behavior: Analyzes the query to determine if the response requires real-time data or archival research.
  • Input: query (string)
  • Triage: Scans for temporal urgency triggers (e.g., "now", "latest", "current").
  • Output: An urgency assessment (REAL-TIME vs ARCHIVAL) and the logic used for the determination.

Operational Logic

  • Context Optimization: By reducing the number of fragments passed to the LLM, Kairos increases the "signal-to-noise" ratio, which directly improves the accuracy of the consensus resolution.
  • Temporal Triage: This tool allows the system to decide whether to prioritize the Mnemosyne Vault (Archival) or real-time web search (Real-time).

Implementation Details

  • Architecture: Python FastMCP server with a logic layer implementing keyword-based relevance scoring and temporal keyword detection.
  • Sovereign Integration: Sits between the memory recall and the reasoning path spawning, acting as a gatekeeper for the final context window.

MCP tools

Available Bun MCP tools: kairos_filter, kairos_urgency.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
4
Repository forks
2
7-day trend score
13

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/tylergarlick/abraxas/kairos/badge)](https://verified-skill.com/skills/tylergarlick/abraxas/kairos)

Something wrong with this skill or its page? Tell us.