🎁 Get the FREE AI Skills Starter Guide β€” Subscribe β†’
BytesAgainBytesAgain
πŸ¦€ ClawHub

continuity-kernel

by @tkuehnl

OpenClaw continuity kernel for fail-open llm_input injection, deterministic runtime contracts, and shadow-mode eval receipts.

Versionv0.2.0
βš™οΈ Configuration

run_shadow_eval.py options:

  • --layer TEXT β€” Active P0 layer name
  • --chunk TEXT β€” Active chunk id/name
  • --suite core-shadow|memoryarena-mini|memoryarena-mini-perturb β€” Task suite for eval scoring
  • --perturb-profile none|deletion|noise_injection|reorder β€” Deterministic perturb profile for memoryarena-mini-perturb
  • --selector-mode deterministic|dual_route_experimental β€” Selector mode tag for A/B eval receipts
  • --compaction-policy size_only|attention_preserving_experimental β€” Compaction policy label for dropped-field A/B eval comparison
  • --runs N β€” Number of evaluated shadow runs (default: 100)
  • --trace-jsonl PATH β€” JSONL file containing observed shadow outcomes (repeatable)
  • --trace-dir PATH β€” Directory scanned for *.jsonl observed shadow outcomes (repeatable)
  • --append PATH β€” JSON file path to append snapshot results
  • --allow-synthetic β€” Permit synthetic fallback for non-core suites when traces are unavailable (forced pass=false)
  • --artifacts-root PATH β€” Directory for summary receipts (default: ~/.cache/continuity-kernel/p0-evals)
  • Runtime persistence defaults:

  • ContinuityHookAdapter() uses ~/.local/state/continuity-kernel/continuity.db
  • Override default path with CONTINUITY_KERNEL_DB_PATH
  • Use :memory: only as explicit opt-in test mode
  • View on ClawHub
    TERMINAL
    clawhub install continuity-kernel

    πŸ§ͺ Use this skill with your agent

    Most visitors already have an agent. Pick your environment, install or copy the workflow, then run the smoke-test prompt above.

    πŸ” Can't find the right skill?

    Search 60,000+ AI agent skills β€” free, no login needed.

    Search Skills β†’