Compresses older conversation turns into summaries to reduce token usage on subsequent LLM API calls. Provides tools for history compression, token counting across 14 models, cost-optimal model recommendations, and pinned facts preservation during compression. Uses Gemma 4 local compression via Ollama for fully offline operation.
Cognium trust score
64%
Tier
Scanned
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Last scanned 2026-09-01.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.